Agent skill

Pp Thunderbird

by mvanhorn in mvanhorn/printing-press-library

Search, read and audit the mail Thunderbird already downloaded — offline, read-only, no credentials.

Apache-2.0Auto-check: notes

Install Pp Thunderbird

skills CLI
$ npx skills add mvanhorn/printing-press-library --skill pp-thunderbird -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mvanhorn/printing-press-library pp-thunderbird --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cli-skills/pp-thunderbird .claude/skills/pp-thunderbird && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pp-thunderbird
GitHub stars
2.1k
Token cost
~8.5k tokens
SKILL.md length
3,639 words
Files
1
Skills in repo
505
Repo updated
First seen
Licence
Apache-2.0

At a glance

Search, read and audit the mail Thunderbird already downloaded — offline, read-only, no credentials.

  • Works in 6 steps: recall before any discovery → decision tree → always read warnings → …
  • Phrases: search my thunderbird mail
  • SKILL.md covers Prerequisites: Install the CLI, When to Use This CLI, Anti-triggers and Unique Capabilities, plus 6 more sections
  • Calls go, claude and npx

What it does

Pp Thunderbird is an agent skill from mvanhorn/printing-press-library. Search, read and audit the mail Thunderbird already downloaded — offline, read-only, no credentials. Trigger phrases: search my thunderbird mail, what emails need a reply, find the email from, who do I email most, use thunderbird-pp-cli.

Its SKILL.md is about 8.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Official library of CLIs generated by the CLI Printing Press. Endorsed, tested, and community-contributed. The licence is Apache-2.0.

When your agent uses it

  • Phrases: search my thunderbird mail
  • What emails need a reply
  • Find the email from
  • Who do I email most

Example prompts

  • “/pp-thunderbird”

Requirements

  • Node.js
  • Pre-approved tools (allowed-tools): Read, Bash

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. recall before any discovery
  2. decision tree
  3. always read warnings
  4. teach & after finalizing your response - always
  5. playbooks - optional flags, automatic synthesis
  6. playbook amend & when your debug response identifies a correction

What it can do on your machine

Read from SKILL.md and the folder at commit 0fdcc7a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • go
    • claude
    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pp Thunderbird loads about 8.5k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 3,639 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~8.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mvanhorn/printing-press-library at commit 0fdcc7a, republished under its Apache-2.0 licence (© mvanhorn). 3,639 words, ~8,483 tokens.

Download SKILL.mdSave it as .claude/skills/pp-thunderbird/SKILL.md (or your agent's skills folder).
name
pp-thunderbird
description
Search, read and audit the mail Thunderbird already downloaded — offline, read-only, no credentials. Trigger phrases: `search my thunderbird mail`, `what emails need a reply`, `find the email from`, `who do I email most`, `use thunderbird-pp-cli`.
allowed-tools
Read, Bash
author
Edoardo Manco
license
Apache-2.0
argument-hint
<command> [args] | install cli|mcp
<!-- GENERATED FILE — DO NOT EDIT.
     This file is a verbatim mirror of library/productivity/thunderbird/SKILL.md,
     regenerated post-merge by tools/generate-skills/. Hand-edits here are
     silently overwritten on the next regen. Edit the library/ source instead.
     See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->

Thunderbird — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the thunderbird-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

  1. Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:
    bash
    npx -y @mvanhorn/printing-press-library install thunderbird --cli-only
  2. Verify: thunderbird-pp-cli --version
  3. Ensure the reported install directory is on $PATH for the agent/runtime that will invoke this skill.

If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer). This installs into $GOPATH/bin (default $HOME/go/bin), so add that directory to $PATH instead:

bash
go install github.com/mvanhorn/printing-press-library/library/productivity/thunderbird/cmd/thunderbird-pp-cli@latest

If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.

Indexes your Thunderbird profile (mbox stores, address book, filters) into a local full-text store you can query while Thunderbird is running. Adds what no other Thunderbird tool has: awaiting-reply, correspondent ranking, filters audit and bulk-mail triage.

When to Use This CLI

Use this CLI when an agent needs to find, read, summarize or triage the user's email that Thunderbird has stored locally, without IMAP credentials. It is safe to run while Thunderbird is open and never modifies the profile. Run sync first (and again to pick up new mail): search and the audit commands read the local store, which only holds folders Thunderbird keeps for offline use.

The default profile is auto-detected; select another with --profile or THUNDERBIRD_PROFILE, and point at a non-standard Thunderbird directory (the one holding profiles.ini) with THUNDERBIRD_ROOT. THUNDERBIRD_HOME is unrelated: it relocates the CLI's own config and data.

"Sent by me" (awaiting-reply, contacts top) means a message stored in a sent folder: the identities' Sent folder from prefs.js (fcc_folder) or a folder named Sent, Sent Items, Sent Messages, Posta inviata, Inviati, Gesendet, Envoyés or Enviados. Mail from your own address sitting in the Inbox (notifications, notes to self) counts as neither sent nor received.

Anti-triggers

Do not use this CLI for:

  • Sending, moving, flagging or deleting mail — drafts open prefilled in Thunderbird and you press Send yourself
  • Mail in folders Thunderbird has not synced for offline use
  • Webmail-only accounts not configured in Thunderbird

Unique Capabilities

These capabilities aren't available in any other tool for this API.

Inbox intelligence
  • drafts new --attach — Open a Thunderbird compose window with local files already attached, from the terminal or from an MCP agent (agents are limited to files inside Documents). Add --html for an HTML body that keeps the identity's signature, and --body-file <path> to read the body from a file (via MCP, files inside Documents only).

    Use it when the user wants a mail prepared with a document attached, ready to review and send themselves.

    bash
    thunderbird-pp-cli drafts new --to alice@example.com --attach ~/Documents/report.pdf --open
  • awaiting-reply — See every thread where someone is waiting on your answer, across all accounts, oldest first.

    Reach for this when asked what mail still needs a reply instead of scanning recent messages.

    bash
    thunderbird-pp-cli awaiting-reply --since 14d --agent
  • contacts top — Rank the people you exchange mail with by volume and recency, and spot frequent ones missing from your address book.

    Use it to answer who someone is to the user and when they last talked.

    bash
    thunderbird-pp-cli contacts top --since 180d --agent
Mailbox hygiene
  • filters audit — Check every message filter: how often it matches, whether it is disabled, and whether its target folder still exists.

    Use it when mail lands in the wrong folder or to clean up dead filter rules.

    bash
    thunderbird-pp-cli filters audit --since 90d --agent
  • largest — Find the biggest messages or attachments across all accounts and folders.

    Use it to free disk or mailbox quota.

    bash
    thunderbird-pp-cli largest --attachments --limit 20 --agent
  • newsletters — List mailing lists and bulk senders by volume and how much of their mail you never read.

    Use it to pick unsubscribe candidates.

    bash
    thunderbird-pp-cli newsletters --since 90d --min 3 --agent

Command Reference

accounts — Accounts and identities configured in Thunderbird

  • thunderbird-pp-cli accounts — List accounts and identities from prefs.js

attachments — Attachments of a message

  • thunderbird-pp-cli attachments list — List the attachments of a message (index, filename, type, decoded size); inline signature logos and cid: images are hidden unless --include-inline
  • thunderbird-pp-cli attachments save — Decode and save a message's attachments into a directory (--output <dir>); without --index inline parts are skipped unless --include-inline, --index N saves any part by its original index

calendar — Local Thunderbird calendar

  • thunderbird-pp-cli calendar events — List calendar events in a time window, earliest first

contacts — Address book contacts

  • thunderbird-pp-cli contacts search — Find contacts whose name or email contains the query (case-insensitive)
  • thunderbird-pp-cli contacts show — Show one contact by card id or email address
  • thunderbird-pp-cli contacts top — Rank correspondents by volume and recency

drafts — Prepare messages in a Thunderbird compose window (never sends)

  • thunderbird-pp-cli drafts new — Print the compose fields for a new message; --open opens the compose window
  • thunderbird-pp-cli drafts reply — Prepare a reply (or --all reply-all) with the original quoted; --open opens the compose window

filters — Message filter rules

  • thunderbird-pp-cli filters list — List filter rules with action, target folder and condition summary
  • thunderbird-pp-cli filters audit — Hits, disabled rules and missing target folders per filter

folders — Mail folders across all accounts

  • thunderbird-pp-cli folders — List folders with total, unread, size and offline status

messages — Messages indexed from the Thunderbird profile's mbox stores

  • thunderbird-pp-cli messages show — Show one message with headers, flags, text body and attachments (get is an alias); --no-quotes keeps only the new text of the body, --include-inline also lists inline parts
  • thunderbird-pp-cli messages list — List indexed messages, newest first
  • thunderbird-pp-cli messages auth — Show SPF, DKIM and DMARC verdicts of a message
  • thunderbird-pp-cli messages export — Export messages as the original .eml or as JSON

threads — Conversations across folders

  • thunderbird-pp-cli threads show — Show every message of a thread in chronological order with direction in/out; --last N keeps the N most recent, every row carries total_messages

Store and profile

  • thunderbird-pp-cli sync — Index the local Thunderbird profile into the offline SQLite store
  • thunderbird-pp-cli search — Full-text search of the synced store
  • thunderbird-pp-cli stats — Show per-account totals: messages, unread, flagged, folders, last message date
  • thunderbird-pp-cli profiles — List Thunderbird profiles from profiles.ini and which one is selected
  • thunderbird-pp-cli doctor — Check the Thunderbird profile, its accounts and folders, and the local store
Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

bash
thunderbird-pp-cli which "<capability in your own words>"

which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match — fall back to --help or use a narrower query. --json (and other machine formats) keep that exit-2 contract and write {"matches":[]} on stdout so agents can inspect the envelope without treating a miss as success.

Recipes

Find and read a mail
bash
thunderbird-pp-cli search "contratto" --agent --select id,subject,from_addr,date

Narrow search results to the fields an agent needs, then open one with messages show.

Read a long conversation cheaply
bash
thunderbird-pp-cli threads show 3f9a1c2b7d4e --last 5 --agent --select id,date,direction,from_addr,total_messages
thunderbird-pp-cli messages show 3f9a1c2b7d4e --no-quotes --agent

Take only the latest messages of the thread, then read each without the quoted history. Inline signature images are already left out of attachment lists; on a store built by an older version, the next sync re-parses every folder once to compute the inline flag and mark quoted HTML history with >.

Who owes whom
bash
thunderbird-pp-cli awaiting-reply --since 7d --agent

Threads where the last message is inbound and you have not replied.

Unsubscribe candidates
bash
thunderbird-pp-cli newsletters --since 90d --agent

Bulk senders ranked by volume and unread share.

Draft a reply without sending
bash
thunderbird-pp-cli drafts reply "3f9a1c2e7b40" --body "Thanks, confirmed." --agent

Prints the prefilled reply fields and the thunderbird -compose command line; add --open to open the compose window. Nothing is ever sent.

Draft a new mail with an attachment
bash
thunderbird-pp-cli drafts new --to alice@example.com --subject "Report" --attach ~/Documents/report.pdf --open

Opens the compose window with the file attached; nothing is sent. Through MCP the attach parameter takes a comma-separated list and only accepts files inside the user's Documents folder (symlinks and junctions are resolved first); from the terminal any readable file works.

Draft a formatted mail (HTML body, signature)
bash
thunderbird-pp-cli drafts new --to alice@example.com --subject "Offer" --body-file ~/Documents/offer.html --html --open

--html treats the body as HTML (bold text and the like) and keeps the sending identity's HTML signature, including its image. --body-file reads the body from a file instead of --body. Through MCP both are the body-file and html parameters, and body-file only accepts files inside the user's Documents folder; from the terminal any readable file works.

Auth Setup

No authentication. The CLI reads your local Thunderbird profile read-only and never touches passwords, key4.db or logins.json. It auto-detects the default profile; override with --profile or THUNDERBIRD_PROFILE.

Run thunderbird-pp-cli doctor to verify setup.

Agent Mode

Add --agent to any command. Expands to: --json --compact --no-input --no-color.

Global format flags share one contract on promoted, novel, sync, and --deliver paths:

  • --json — one JSON document on stdout (sync progress events go to stderr)

  • --compact — keep identity/status/timestamp fields; does not change the document vs stream shape

  • --csv / --plain — tabular rows (collection envelopes unwrap to the row array)

  • --quiet — one identity value per row, no envelope

  • Pipeable — JSON on stdout, errors on stderr

  • Filterable — --select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:

    bash
    thunderbird-pp-cli accounts --agent --select id,name,identity_emails
  • Previewable — --dry-run reports what a command would do without running it

  • Offline — reads only the local Thunderbird profile and the CLI's SQLite store; no network or mail server access

  • Non-interactive — never prompts, every input is a flag

  • Read-only — do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests

Response envelope

Commands that read from the local store or the API wrap output in a provenance envelope:

json
{
  "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
  "results": <data>
}

Parse .results for data and .meta.source to know whether it's live or local. A human-readable N results (live) summary is printed to stderr only when stdout is a terminal AND no machine-format flag (--json, --csv, --compact, --quiet, --plain, --select) is set — piped/agent consumers and explicit-format runs get pure JSON on stdout.

Paths and state

Agents should treat the CLI's path resolver as part of the runtime contract:

  • Use --home <dir> for one invocation, or set THUNDERBIRD_HOME=<dir> to relocate all four path kinds under one root.

  • Use per-kind env vars only when a specific kind must diverge: THUNDERBIRD_CONFIG_DIR, THUNDERBIRD_DATA_DIR, THUNDERBIRD_STATE_DIR, THUNDERBIRD_CACHE_DIR.

  • Resolution order is per-kind env var, --home, THUNDERBIRD_HOME, XDG (XDG_CONFIG_HOME, XDG_DATA_HOME, XDG_STATE_HOME, XDG_CACHE_HOME), then platform defaults.

  • config contains settings like config.toml and saved run profiles. data contains one mail index per Thunderbird profile at profiles/<profile hash>/data.db (doctor prints store_path; syncing another profile never touches it), feedback.jsonl and .eml files written by drafts --open. state contains persisted queries, jobs, and teach.log. cache contains regenerable cache files. No credentials are stored.

  • Run thunderbird-pp-cli doctor --fail-on warn to surface path warnings. agent-context exposes a schema v4 paths block for agents that need the resolved dirs.

  • For MCP, pass relocation through the MCP host config. The MCP binary does not inherit CLI flags:

    json
    {
      "mcpServers": {
        "thunderbird": {
          "command": "thunderbird-pp-mcp",
          "env": {
            "THUNDERBIRD_HOME": "/srv/thunderbird"
          }
        }
      }
    }

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use THUNDERBIRD_HOME or per-kind vars as durable fleet levers, and use --home only for a single invocation. Relocation is not reversible by unsetting env vars; move files manually before clearing THUNDERBIRD_HOME, or doctor will not find the store left under the former root.

Automatic learning

This CLI ships a self-capturing learning loop. The CLI does its own bookkeeping: every invocation is journaled locally, a failed flag followed by a corrected retry auto-derives a flag_alias candidate, and a teach on a query family without a playbook auto-synthesizes a playbook_candidate from the session's journal. Your job is judgment only: recall first, act on surfaced candidates, teach the final answer, playbook amend when you observe a correction. You never record failures by hand.

Step 1: recall before any discovery

Before list/search/drill commands on a new user question, pass the question as an argv or MCP tool argument to recall --agent. Do not interpolate user-controlled text into a shell command line.

Quoted recall "<question>" breaks on an apostrophe, which is ordinary English. A quoted heredoc breaks when a body line equals the delimiter, and that delimiter is published in these docs. Write the question with a non-shell file-writing tool, then read it back as data:

bash
# Write the question verbatim with your file-writing tool (no shell involved).
# Command substitution on a file only ever yields data — the shell never
# parses the file's bytes as syntax.
QUERY=$(cat /path/to/question.txt)
thunderbird-pp-cli recall "$QUERY" --agent

Prefer MCP: pass the question as the tool's query argument. "$QUERY" after a file read is argv-safe; putting the question itself in the command text is not.

The response envelope:

json
{
  "query": "...",
  "normalized": "<normalized form>",
  "query_entities": ["..."],
  "found": true | false,
  "match_score": 0.0,
  "results": [
    { "resource_id": "...", "resource_type": "...", "venue": "...",
      "confidence": 2, "entity_match": "exact|partial|unknown",
      "source": "taught|preseed|pattern", "warnings": ["..."] }
  ],
  "mismatches": [ /* only when --debug-mismatches */ ],
  "warnings": [ /* top-level */ ],
  "candidates": [
    { "id": 12, "class": "flag_alias | playbook_candidate",
      "summary": "...", "sightings": 3, "last_seen": "...",
      "rationale": "...",
      "next_action": ["<trial command>", "thunderbird-pp-cli learnings confirm 12"] }
  ],
  "playbook": {
    "query_family": "...",
    "playbook": {
      "steps": [ { "cmd": "<command with {slot} substitution>", "purpose": "..." } ],
      "entity_slots": ["$ENTITY"],
      "expected_tool_calls": 3
    },
    "slots_resolved": { "$ENTITY": { "token": "<live token>", "canonical": "<canonical>" } },
    "notes": "<workarounds + gotchas for this query family>"
  },
  "notes": "<duplicate surface for non-playbook callers>"
}

Empty-store short-circuit: if the store has no learnings, playbooks, or candidates yet (recall finds nothing and learnings list and learnings candidates are both empty), skip recall for the rest of this session instead of taxing every query; resume recall-first once something has been taught.

Step 2: decision tree

Read candidates, playbook, notes, results[0], and warnings in that order:

if Candidates present (warnings include "candidates_present"):
    -> candidates are try-then-confirm, never facts. Follow each candidate's
       two-step next_action verbatim: run the trial command first, then run
       `learnings confirm <id>` only after the trial verified the behavior.
       Reject a wrong candidate with `learnings reject <id>`.
    -> NEVER re-teach something recall surfaced as a candidate; confirm or
       reject that candidate instead of teaching a duplicate.
    -> candidates ride alongside playbooks and resource hits, not instead of
       them; continue with the branches below after acting on them.

if Playbook present:
    -> READ Playbook.notes verbatim FIRST (workarounds + gotchas the CLI surface doesn't expose)
    -> replay Playbook.steps in order, substituting Playbook.slots_resolved entries
       for the entity slot tokens. If a step's slot is unresolved, fall back to
       discovery for that step only.
    -> the Playbook's expected_tool_calls is a budget; if you find yourself running
       materially more, record the divergence via `thunderbird-pp-cli playbook amend`
       at end-of-session.

elif Notes present (no Playbook):
    -> read Notes verbatim before any discovery step; they carry known gotchas
       for this query family even when no structured choreography exists yet.

elif Found AND Results[0].EntityMatch == "exact" AND Results[0].Confidence >= 2:
    -> skip discovery; fetch live data for Results[*].ResourceID in parallel

elif Found AND Results[0].EntityMatch == "partial":
    -> candidate hint, NOT a hit; read the resource title to validate before trusting

elif (any row in Mismatches[] when --debug-mismatches was passed):
    -> treat as cold start; the stored learning is for a different entity
       (different canonical resolved from query_entities)

else:  // Found == false, no playbook, no notes
    -> cold start; run discovery normally; teach the answer afterward (Step 4).
       If the family has no playbook yet, that teach auto-synthesizes a
       playbook candidate from this session's journal - you do not need to
       record one by hand.

Playbook and Notes are orthogonal to the per-resource path. A recall response can carry both a Playbook AND a Results[] hit - use both: the Playbook tells you which choreography to run; the resource hits short-circuit specific steps. Default to skipping mismatches; pass --debug-mismatches only when investigating cold-start surprises.

Candidate judgment details: learnings confirm <id> prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. learnings reject <id> tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; thunderbird-pp-cli learnings candidates lists the full open set.

Graceful degradation: if learnings confirm is an unknown command, you are driving an older binary - ignore the candidates guidance and follow the rest of the protocol.

Show full SKILL.md (1,475 more words)Show less
Step 3: always read warnings
  • low_confidence: row exists at confidence<2. Treat as a hint, not a skip-discovery hit.
  • resource_not_in_store: the local store doesn't have the resource the learning points at. The match validator couldn't classify entities — direct-fetch and re-evaluate.
  • cross_alias_match (per-result): the row was taught under a different alias and matched the live query's canonical via entity_lookups (e.g., a "USA" teach satisfying a "United States" recall). Trust the resource_id.
  • similar_shape_different_entity:<canonical> (top-level): a structurally matching row exists but its canonical entity differs from the live query's. Treated as cold start; the warning carries the conflicting canonical as a hint, but the row is NOT promoted into Results.
  • ambiguous_alias (top-level): a single query entity resolved to multiple canonicals (e.g., "Cards" → Arizona Cardinals + St. Louis Cardinals). Surface the ambiguity from context before committing to a resource.
  • candidates_present (top-level): the envelope carries a candidates section. Handle it via the candidates branch in Step 2 before anything else.
  • lookup_refresh_available (top-level): an entity in the query has no lookup row yet, but synced data could provide one. Run thunderbird-pp-cli sync to refresh entity lookups.
  • Top-level no_learnings_for_query_family: the table had no rows above the Jaccard floor. Pure cold start.
Step 4: teach & after finalizing your response - always

Teaching is unconditional. After resolving a query the store could not answer, background-teach the final resource mapping - no call-count threshold, no judging whether it was "worth" learning. The teach is the anchor of the loop: it triggers playbook synthesis for a family without a playbook, and same-referent phrasings fold into one family so near-duplicate teaches do not fragment the store. Fire it after assembling your user-facing response but BEFORE emitting it, with a shell & so the call returns immediately. Pass the query the same way as recall — argv/MCP, or file-then-$QUERY. Do not splice the question into the command text:

bash
QUERY=$(cat /path/to/question.txt)
thunderbird-pp-cli teach --query "$QUERY" --resource-type <type> --resource <id1> --resource <id2>
# (append shell `&` to background it)

Silent on success. Errors only land in teach.log under the resolved state dir. Teach the most specific resource - if the user asked a broad question and you walked through parent records to find the specific answer, teach the leaf id, not the parent. The CLI uses seeded entity_lookups for cross-alias resolution at recall time, so a teach under one alias (e.g., "Niners") satisfies future queries under another alias (e.g., "49ers", "San Francisco") automatically.

PII rule: teach the structural question with identifiers stripped - never include names, emails, phone numbers, account ids, or other personal identifiers in taught queries or notes. The CLI scans teach queries for obvious email/phone shapes and warns, but does not block; strip before teaching rather than relying on the warning.

Step 5: playbooks - optional flags, automatic synthesis

You do not need to decide whether a session "deserves" a playbook: a teach on a family without one auto-synthesizes a playbook_candidate from the session's journal, and the next session judges it via confirm/reject. Attach explicit playbook flags only when you already hold choreography worth recording verbatim - workarounds the CLI didn't surface (silently-dropped flags, undocumented params, pagination tricks, payload gotchas). Prefer the integrated one-call form - record the resource learning and the playbook in the same teach invocation:

bash
# Common case: record both the resource learning AND the playbook in one call.
QUERY=$(cat /path/to/question.txt)
thunderbird-pp-cli teach \
  --query "$QUERY" \
  --resource-type <type> \
  --resource <id> \
  --playbook-file ~/playbooks/<shape>.json \
  --playbook-notes-file ~/playbooks/<shape>-notes.md
# (append shell `&` to background it)

# Alternate: playbook-only (no resource to record alongside).
QUERY=$(cat /path/to/question.txt)
thunderbird-pp-cli teach-playbook \
  --query "$QUERY" \
  --playbook-file ~/playbooks/<shape>.json \
  --notes-file ~/playbooks/<shape>-notes.md

Playbook files are JSON with steps, entity_slots, expected_tool_calls. Notes files are markdown carrying the gotchas verbatim. File-free callers (MCP-only agents) pass the same content inline: --playbook-json and --playbook-notes on the integrated teach form, --playbook-json and --notes on teach-playbook. On the integrated teach form, the playbook flags are optional - omit them entirely for a resource-only teach. On the standalone teach-playbook form, at least one of the playbook and notes flags must be set; both empty is rejected. Playbooks are keyed on the structural query family (entities stripped) so a recipe taught from one entity-shaped query applies to every other query of the same shape, with slots_resolved binding the live query's canonical at recall time.

When you DO find a playbook on a future recall, treat it as ground truth: replay the steps with slots_resolved substitutions, skip the discovery that the choreography already documents, and read notes before any step.

Step 6: playbook amend & when your debug response identifies a correction

If your debug-protocol response identifies a concrete correction the notes or playbook should know — a workaround, an undocumented endpoint shape, a stale field name, observed schema drift, an empty-payload fallback — fire playbook amend BEFORE emitting your user-facing response. Same fire-and-forget posture as teach. Pass the query and note as argv/MCP arguments, or write each with a non-shell file tool and read them back (QUERY=$(cat ...), NOTE=$(cat ...)). Do not interpolate either string into the command text:

bash
QUERY=$(cat /path/to/question.txt)
NOTE=$(cat /path/to/note.txt)
thunderbird-pp-cli playbook amend \
  --query "$QUERY" \
  --add-note "$NOTE"
# (append shell `&` to background it)

What counts as worth amending: a behavior you OBSERVED this session that future-you would benefit from knowing. Examples worth amending:

  • A workaround for a CLI surface that silently drops or misorders a flag.
  • An undocumented endpoint shape (response wrapped in {meta, results}, payload nested two levels deeper than the docs claim).
  • Observed schema drift (a field renamed, an index that shifted between seasons, a category label that the API now returns lower-cased).

What does NOT belong in notes:

  • The year-specific or entity-specific answer to the user's question. That's the response, not a learning.
  • Per-team / per-athlete / per-row data the playbook already retrieves at runtime.
  • Statements that paraphrase what the existing notes already say.

The amend command appends to the family's existing notes with a timestamped marker ([amend YYYY-MM-DDTHH:MMZ]: <text>). Multiple amends accumulate; the audit trail is visible. If no playbook exists yet for the family, amend creates a notes-only one (so cold-start corrections still land).

PII discipline for amend notes

playbook amend notes are designed to potentially flow upstream as shared knowledge in future versions of the Printing Press. Keep them clean of user-identifying content so the upstream-contribution path stays open without retroactive scrubbing:

  • Do NOT embed paths to user filesystems, personal API keys or tokens, user email addresses, user GitHub handles, or specific query histories tied to a single user.
  • Acceptable: endpoint shapes, undocumented field names, API gotchas, observed schema drift, workarounds for CLI surfaces, generalizable pagination or retry tactics.

If a correction is only meaningful with user-specific context, it belongs in a personal note, not in the playbook amend.

Measuring the loop

thunderbird-pp-cli learnings stats reports recall hit rate, teach-to-reuse, playbook resolution rate, and candidate confirm/reject counts from the local learn_events table. Rates are null until they have a denominator; everything stays on this machine. Use it to check whether the loop is earning its keep for this CLI.

Disabling learning
  • --no-learn on a single command short-circuits both recall and the teach write path. Use for deterministic agent flows or tests that must not be affected by accumulated learnings.
  • THUNDERBIRD_NO_LEARN=true in the environment globally disables the pipeline.

Agent Feedback

When you (or the agent) notice something off about this CLI, record it:

thunderbird-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
thunderbird-pp-cli feedback --stdin < notes.txt
thunderbird-pp-cli feedback list --json --limit 10

Entries are stored locally as feedback.jsonl under the resolved data dir. They are never POSTed unless THUNDERBIRD_FEEDBACK_ENDPOINT is set AND either --send is passed or THUNDERBIRD_FEEDBACK_AUTO_SEND=true. Default behavior is local-only.

Write what surprised you, not a bug report. Short, specific, one line: that is the part that compounds.

Output Delivery

Every command accepts --deliver <sink>. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported:

SinkEffect
stdoutDefault; write to stdout only
file:<path>Atomically write output to <path> (tmp + rename). Binary-response commands write decoded payload bytes (not the base64 JSON envelope) and print a small JSON receipt on stdout; --json/--csv do not refuse when this sink is set.
webhook:<url>POST the output body to the URL (application/json)

Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr.

Named Profiles

A profile is a saved set of flag values, reused across invocations. Use it when a scheduled or recurring agent reuses the same saved flags while providing different input each run.

thunderbird-pp-cli profile save briefing --json
thunderbird-pp-cli --profile briefing accounts
thunderbird-pp-cli profile list --json
thunderbird-pp-cli profile show briefing
thunderbird-pp-cli profile delete briefing --yes

Explicit flags always win over profile values; profile values win over defaults. agent-context lists all available profiles under available_profiles so introspecting agents discover them at runtime.

Exit Codes

CodeMeaning
0Success
1Other error (e.g. profile or store unreadable)
2Usage error (wrong arguments)
3Not found (message, contact, identity or attachment)
10Config error

Argument Parsing

Parse $ARGUMENTS:

  1. Empty, help, or --help → show thunderbird-pp-cli --help output
  2. Starts with install → ends with mcp → MCP installation; otherwise → see Prerequisites above
  3. Anything else → Direct Use (execute as CLI command with --agent)

MCP Server Installation

  1. Install the MCP server:
    bash
    go install github.com/mvanhorn/printing-press-library/library/productivity/thunderbird/cmd/thunderbird-pp-mcp@latest
  2. Register with Claude Code:
    bash
    claude mcp add thunderbird-pp-mcp -- thunderbird-pp-mcp
  3. Verify: claude mcp list

Direct Use

  1. Check if installed: which thunderbird-pp-cli If not found, offer to install (see Prerequisites at the top of this skill).
  2. Match the user query to the best command from the Unique Capabilities and Command Reference above.
  3. Execute with the --agent flag:
    bash
    thunderbird-pp-cli <command> [subcommand] [args] --agent
  4. If ambiguous, drill into subcommand help: thunderbird-pp-cli <command> --help.

© mvanhorn, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in cli-skills/pp-thunderbird of mvanhorn/printing-press-library.

Open the folder on GitHubat commit 0fdcc7a

Compare with similar skills

Pp Thunderbird next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Pp Thunderbird compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pp Thunderbird this skillmvanhorn/printing-press-library2.1k—~8.5kAutomated safety check: NotesApache-2.0
Video Downloadernexu-io/open-design100k—~339Automated safety check: PassApache-2.0
Video Downloaderdavila7/claude-code-templates32k5 repos~660Automated safety check: PassMIT
Mails So AutomationComposioHQ/awesome-claude-skills77k3 repos~734Automated safety check: PassNone
Video Downloadcalesthio/OpenMontage65k—~885Automated safety check: PassAGPL-3.0
YouTube Video DownloaderComposioHQ/awesome-claude-skills77k10 repos~668Automated safety check: PassNone

Similar skills

  • Video Downloader

    nexu-io/open-design

    Download videos from YouTube and other platforms for offline viewing, editing, or archival with support for various formats and quality options.

    100k GitHub stars~339 tokensUpdated today
    Media & CreativeAuto-check passed
  • Video Downloader

    davila7/claude-code-templates

    Downloads videos from YouTube and other platforms for offline viewing, editing, or archival.

    32k GitHub starsUsed in 5 repos~660 tokens
    Media & CreativeAuto-check passed
  • Mails So Automation

    ComposioHQ/awesome-claude-skills

    Automate Mails So tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.

    77k GitHub starsUsed in 3 repos~734 tokens
    Productivity & AutomationAuto-check passed
  • Video Download

    calesthio/OpenMontage

    Download video and audio from YouTube and 1000+ sites using yt-dlp.

    65k GitHub stars~885 tokensUpdated 5 days ago
    Media & CreativeAuto-check passed
  • YouTube Video Downloader

    ComposioHQ/awesome-claude-skills

    Downloads a single YouTube video with chosen quality, format or audio-only MP3 output, using a bundled Python script built on yt-dlp.

    77k GitHub starsUsed in 10 repos~668 tokens
    Media & CreativeAuto-check passed
  • Export Download Debugging

    nexu-io/open-design

    Diagnose and fix browser, preview, or Electron export/download failures, especially image export issues involving Save As, Blob/Data URLs, the File System Access API, createWritable failures, and 0…

    100k GitHub stars~725 tokensUpdated today
    DevelopmentAuto-check passed

More from mvanhorn/printing-press-library

All 505 skills in this repo
  • Agent Desktop

    mvanhorn/printing-press-library

    Desktop automation through the real Rust agent-desktop CLI, published in Printing Press through a small bridge.

    2.1k GitHub stars~2.3k tokensUpdated yesterday
    Auto-check: notes
  • Gfonts

    mvanhorn/printing-press-library

    Search, browse, and download Google Fonts from the terminal via the gfonts CLI.

    2.1k GitHub stars~574 tokensUpdated yesterday
    Auto-check passed
  • Pp 1688

    mvanhorn/printing-press-library

    The free, offline Trigger phrases: search 1688 for, find a factory on 1688 for, wholesale price on 1688 for, who is the cheapest supplier on 1688 for, compare 1688 suppliers for, use 1688, run 1688.

    2.1k GitHub stars~3k tokensUpdated yesterday
    Auto-check: notes
  • Pp Activity Japan

    mvanhorn/printing-press-library

    Inspect known Activity Japan plan IDs or URLs, compare dated prices and sessions, check language-sitemap coverage, and hand off to canonical booking pages.

    2.1k GitHub stars~2k tokensUpdated yesterday
    Auto-check: notes
  • Pp Adminbyrequest

    mvanhorn/printing-press-library

    Every Admin By Request portal action, plus a local SQLite mirror of audit, events, inventory and requests for ad-hoc...

    2.1k GitHub stars~3.3k tokensUpdated yesterday
    Auto-check: notes
  • Pp Agent Capture

    mvanhorn/printing-press-library

    macOS screen capture, window recording, GIF conversion, and agent evidence bundles from the terminal.

    2.1k GitHub stars~1.6k tokensUpdated yesterday
    Auto-check: notes

Questions about Pp Thunderbird

What does Pp Thunderbird do?

Search, read and audit the mail Thunderbird already downloaded — offline, read-only, no credentials. Pp Thunderbird is an agent skill from mvanhorn/printing-press-library. Search, read and audit the mail Thunderbird already downloaded — offline, read-only, no credentials.

When should I use Pp Thunderbird?

Pp Thunderbird fits situations like: phrases: search my thunderbird mail; what emails need a reply; find the email from; who do I email most.

How do I install Pp Thunderbird in Claude Code?

Run `npx skills add mvanhorn/printing-press-library --skill pp-thunderbird -a claude-code`. Or copy the skill folder (cli-skills/pp-thunderbird in mvanhorn/printing-press-library) into .claude/skills/pp-thunderbird in your project. Claude Code loads it when a task matches its description.

How do I install Pp Thunderbird in Codex?

Run `npx skills add mvanhorn/printing-press-library --skill pp-thunderbird -a codex`. Or copy the skill folder (cli-skills/pp-thunderbird in mvanhorn/printing-press-library) into .agents/skills/pp-thunderbird in your project. Codex loads it when a task matches its description.

Can I use Pp Thunderbird in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mvanhorn/printing-press-library --skill pp-thunderbird -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pp-thunderbird, .gemini/skills/pp-thunderbird, .github/skills/pp-thunderbird and .opencode/skills/pp-thunderbird in your project.

What does Pp Thunderbird need to run?

Going by SKILL.md and its folder, Pp Thunderbird needs the command-line tools its instructions call (go, claude and npx). Our summary lists: Node.js. Its frontmatter pre-approves these tools: Read, Bash.

Does Pp Thunderbird access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Pp Thunderbird safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Pp Thunderbird use?

Pp Thunderbird is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pp Thunderbird use?

About 8.5k tokens (SKILL.md is roughly 34k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Pp Thunderbird?

Skills that share tags, products or a category with Pp Thunderbird: Video Downloader (nexu-io/open-design, 100k stars), Video Downloader (davila7/claude-code-templates, 32k stars), Mails So Automation (ComposioHQ/awesome-claude-skills, 77k stars) and Video Download (calesthio/OpenMontage, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pp Thunderbird?

mvanhorn (a GitHub user) maintains it in mvanhorn/printing-press-library, which has 2,053 GitHub stars. The repository holds 505 skills in this directory. The repository was last updated on October 7, 2026.

Source: mvanhorn/printing-press-library on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.