Pp Snipd

<!-- GENERATED FILE — DO NOT EDIT.
     This file is a verbatim mirror of library/media-and-entertainment/snipd/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/". -->

Snipd — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the snipd-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:

   npx -y @mvanhorn/printing-press-library install snipd --cli-only

2. Verify: snipd-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 1.26.5 or newer). This installs into $GOPATH/bin (default $HOME/go/bin), so add that directory to $PATH instead:

go install github.com/mvanhorn/printing-press-library/library/media-and-entertainment/snipd/cmd/snipd-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.

Your snips are trapped in a mobile app. This CLI pulls them into a local SQLite mirror with a full-text index, then lets you search, quote, filter, and aggregate them in kilobytes instead of scrolling an app. The same commands are exposed as MCP tools so an agent can reason over your own listening.

When to Use This CLI

Use this CLI when you want to search, quote, or synthesize across your own Snipd snips — a concept across every transcript, the exact pull-quote for a claim, or a rolled-up view of what you have been snipping. It is ideal as an agent tool: the MCP surface returns compact ranked rows so an assistant can cite your podcast highlights without opening the app.

Anti-triggers

Do not use this CLI for:

• Do not use this to browse or discover public podcasts — it only reads your own snipped content.
• Do not use this for audio playback or downloading episodes — only the exported text (notes, quotes, transcript excerpts) is reachable.
• Do not use this to write or edit snips — it is strictly read-only over the export API.

Unique Capabilities

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

Local snip corpus that compounds

• pull — Pull your Snipd snips into a local SQLite mirror you can search and query offline — the app has no export-to-query path.

  Run this first: it is the populate step every search, quote, filter, and aggregate reads from.

  snipd-pp-cli pull --agent

• filter — Slice the corpus by show, favorite, tag, date, or duration and return compact rows or counts.

  Use this for structured slices; reach for search when the criterion is a free-text concept.

  snipd-pp-cli filter --show "Finding Our Way" --favorite --agent

• aggregate — Roll up counts and distributions across your corpus — snips per show, top tags, favorites, episode density, and timeline.

  Use this to understand the shape of your listening — where your snips cluster — in one call.

  snipd-pp-cli aggregate by-show --agent

Agent-native retrieval over your own snips

• quote — Get the verbatim pull-quote and speaker for matching snips — the distinct unit other tools concatenate into transcript prose and lose.

  Reach for this when you need a citable verbatim line, not a paraphrase or the whole transcript.

  snipd-pp-cli quote "thinking partner" --agent

• synthesize — Gather a deduped, snippet-only evidence set (title + note + quote + deep-link) scoped by query, show, or topic — sized for an agent to reason over.

  Use this to assemble the evidence for a cross-show answer without dragging full transcripts through context.

  snipd-pp-cli synthesize "AI and jobs" --limit 20 --agent

Command Reference

catalog — The upstream export catalog — which of your episodes are available to pull, and what changed

• snipd-pp-cli catalog — List your episodes available for export (ids, snip counts, batches).

Finding the right command

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

snipd-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.

Recipes

Find the quote behind a claim

snipd-pp-cli quote "thought partner" --agent

Returns the verbatim pull-quote and speaker for snips matching the phrase.

Compact evidence for a cross-show answer

snipd-pp-cli synthesize "personas vs archetypes" --limit 15 --agent --select snip_id,show,title,note,url

A deduped, snippet-only feed narrowed to exactly the fields an agent needs, from a deeply nested store.

Everything from one show

snipd-pp-cli filter --show "NN/G UX Podcast" --agent

All snips for a show as compact rows, ordered by episode and timestamp.

Where do my snips cluster?

snipd-pp-cli aggregate by-show

A one-call rollup of snip counts per show.

Auth Setup

Snipd's export API authenticates with your own Snipd account Bearer token. Get it with a one-time browser sign-in — you don't need Obsidian, the Snipd Obsidian plugin, or the mobile app (the page is titled "Obsidian integration" only because the CLI reuses Snipd's export API).

Recommended — one command: snipd-pp-cli auth login opens your browser to Snipd's sign-in page, waits while you sign in with Google, Apple, or email, then saves the token for you. Add --no-browser on a headless or SSH box to print the URL instead. Confirm with snipd-pp-cli auth status.

Manual, if you prefer: generate any random UUID (e.g. uuidgen) and call it X; open https://app.snipd.com/obsidian/auth?uuid=X and sign in; open https://api.snipd.com/v1/public/api/obsidian/auth?uuid=X and copy the token value; save it with snipd-pp-cli auth set-token <token> (or export SNIPD_TOKEN=<token> for one session). snipd-pp-cli auth setup reprints these steps any time.

The token is personal and account-scoped — read-only, stored locally, and it never leaves your machine. If it stops working, run snipd-pp-cli auth login again; re-pairing takes about a minute.

Run snipd-pp-cli doctor to verify setup.

Agent Mode

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

• 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:

  snipd-pp-cli catalog --agent --select id,name,status

• Previewable — --dry-run shows the request without sending

• Offline-friendly — sync/search commands can use the local SQLite store when available

• 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:

{
  "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 SNIPD_HOME=<dir> to relocate all four path kinds under one root.

• Use per-kind env vars only when a specific kind must diverge: SNIPD_CONFIG_DIR, SNIPD_DATA_DIR, SNIPD_STATE_DIR, SNIPD_CACHE_DIR.

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

• config contains settings like config.toml and profiles. data contains credentials.toml, data.db, cookies, and auth sidecars. state contains persisted queries, jobs, and teach.log. cache contains regenerable HTTP/cache files.

• Stored secrets live in credentials.toml under the data dir. Existing legacy config.toml secrets are read for compatibility and leave config.toml on the first auth write.

• Run snipd-pp-cli doctor --fail-on warn to surface path and credential-location 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:

  {
    "mcpServers": {
      "snipd": {
        "command": "snipd-pp-mcp",
        "env": {
          "SNIPD_HOME": "/srv/snipd"
        }
      }
    }
  }

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use SNIPD_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 SNIPD_HOME, or doctor will not find credentials 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, run:

snipd-pp-cli recall "<user's question>" --agent

The response envelope:

{
  "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>", "snipd-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 `snipd-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; snipd-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.

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 snipd-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.