Agent skill

Meeting To Tree

by first-tree-ai in first-tree-ai/first-tree

Turn exact meeting records that the user supplies into durable Context Tree updates.

Apache-2.0Auto-check passedProductivity & Automation

Install Meeting To Tree

skills CLI
$ npx skills add first-tree-ai/first-tree --skill meeting-to-tree -a claude-code

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

GitHub CLI
$ gh skill install first-tree-ai/first-tree meeting-to-tree --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/first-tree-ai/first-tree.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/.experimental/meeting-to-tree .claude/skills/meeting-to-tree && 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
meeting-to-tree
GitHub stars
154
Token cost
~1.8k tokens
SKILL.md length
941 words
Files
3
Skills in repo
9
Repo updated
First seen
Licence
Apache-2.0

At a glance

Turn exact meeting records that the user supplies into durable Context Tree updates.

  • Works in 5 steps: Separate proposals, discussion, and… → Scan all later material for correction,… → Keep only the surviving current statement. → …
  • A user asks to sync meeting minutes
  • SKILL.md covers Establish the meeting source, Identify durable Tree candidates, Match members and confirm… and Sync durable context, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Meeting To Tree is an agent skill from first-tree-ai/first-tree. Turn exact meeting records that the user supplies into durable Context Tree updates. Use when a user asks to sync meeting minutes, transcripts, AI notes, decision records, or related meeting artifacts into the team's Context Tree: read the exact sources, reconcile chronology, identify durable decisions and constraints, map relevant participants to First Tree members, confirm only unsettled claims, and hand the meeting source material to first-tree-write. Do not use for a summary-only request, calendar discovery…

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `agents/openai.yaml`).

It sits in Productivity & Automation, covering Meeting notes and agendas. The repository describes itself as: First-tree routes work to the right agent, gives it the same context your team has, and loops humans in only when the rules say so. Lives in your GitHub. Open source. The licence is Apache-2.0.

When your agent uses it

  • A user asks to sync meeting minutes
  • Decision records
  • Related meeting artifacts into the teams Context Tree: read the exact sources
  • Reconcile chronology

Example prompts

  • “/meeting-to-tree”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Separate proposals, discussion, and final statements.
  2. Scan all later material for correction, withdrawal, replacement,
  3. Keep only the surviving current statement.
  4. Preserve the surviving rationale, qualifiers, and consequences.
  5. Distinguish supported conclusions from uncertain interpretations.

What it can do on your machine

Read from SKILL.md and the folder at commit 13f2a38. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Meeting To Tree loads about 1.8k tokens when it runs. Until then it costs about 149 tokens; SKILL.md has 941 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~149
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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 passed

The automated check found no risky patterns in SKILL.md.

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 first-tree-ai/first-tree at commit 13f2a38, republished under its Apache-2.0 licence (© first-tree-ai). 941 words, ~1,810 tokens.

Download SKILL.mdSave it as .claude/skills/meeting-to-tree/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
meeting-to-tree
description
Turn exact meeting records that the user supplies into durable Context Tree updates. Use when a user asks to sync meeting minutes, transcripts, AI notes, decision records, or related meeting artifacts into the team's Context Tree: read the exact sources, reconcile chronology, identify durable decisions and constraints, map relevant participants to First Tree members, confirm only unsettled claims, and hand the meeting source material to first-tree-write. Do not use for a summary-only request, calendar discovery, meeting search, provider authorization, or scheduled capture.

Meeting to Tree

Turn one logical meeting's exact source artifacts into reviewable Context Tree updates. Use existing readers, First Tree member communication, and first-tree-write; do not build a parallel reader, confirmation store, or Tree writer.

Establish the meeting source

  • Require at least one concrete meeting artifact and clear intent to update the Context Tree. If either is missing, ask for it and stop.
  • Process one logical meeting at a time. When supplied artifacts may belong to different meetings, separate them using explicit source evidence or ask the user to group them.
  • Use the environment's ordinary reader for each exact provider document, attachment, local file, or pasted record. For a Feishu source, use the available Feishu reader or CLI; keep provider authorization, download, OCR, parsing, completeness, and revision handling in that reader layer.
  • Do not use a calendar, search for related meetings, scan a time window, or follow links embedded in a source to discover adjacent material.
  • Preserve the user-declared or document-visible order. If order is unknown, do not infer that one artifact overrides another.
  • If an artifact is unreadable or incomplete, identify the gap. When the gap could contain a correction or later decision, do not call the affected point settled.
  • Use the exact source through the ordinary reader in the current task. If the reader already provides a transient local file, reuse it. Do not create or retain an additional raw copy solely for this Skill. Never write raw meeting content to the Context Tree, a source repository, or parallel persistent state.

Identify durable Tree candidates

Read the available artifacts in order and identify claims that may change durable team context:

  • a decision or explicit non-choice and its surviving rationale;
  • a constraint future work must respect;
  • a durable ownership or responsibility change;
  • a cross-domain relationship.

For every candidate:

  1. Separate proposals, discussion, and final statements.
  2. Scan all later material for correction, withdrawal, replacement, disagreement, completion, or cancellation.
  3. Keep only the surviving current statement.
  4. Preserve the surviving rationale, qualifiers, and consequences.
  5. Distinguish supported conclusions from uncertain interpretations.

Progress, plans, actions, blockers, risks, and other member-specific updates are signals, not required output categories. Consider them only when they establish or change a durable candidate above. Do not create a complete meeting summary before applying the Tree write bar.

Evidence strength matters:

  • Human-confirmed minutes or an explicit decision record may confirm an item when wording is unambiguous and no later material overrides it.
  • AI-generated notes may identify an item but cannot alone prove human confirmation.
  • A transcript confirms only what it explicitly records. Do not infer speaker identity, authority, or agreement from participation.
  • When provenance or wording is ambiguous, state the uncertainty instead of promoting it to a fact.

Before mapping members or sending any confirmation, apply the Context Tree Double Test as a preliminary filter. Keep a claim only when it both establishes or changes context future agents must respect and would remain durable if the meeting's implementation work were rewritten. first-tree-write will reapply the normal write gate after any confirmation reply.

Show full SKILL.md (436 more words)Show less

Match members and confirm unsettled claims

  • Identify participants only from the supplied meeting record. When routing a confirmation or evaluating responsibility context, match them to First Tree members using member context available in the current environment. Do not guess when names or identities are ambiguous.
  • Treat member mapping as routing information, not permission to change Context Tree ownership.
  • Keep every confirmation for this meeting in the originating task chat. Never use chat create to open a confirmation chat for an individual member or to split the meeting's confirmations across chats.
  • Request confirmation only for a claim that is AI-only, ambiguous, disputed, weakly attributed, changes ownership or durable responsibility, or is otherwise not settled by the source. Do not repeat confirmation for a clear human-confirmed minute or explicit decision record, except that an ownership or durable responsibility change still requires confirmation from the affected human.
  • Send each relevant member a concise claim-level question in that same chat. Use a separate, individually addressed tracked question for every human whose answer a claim's Tree write depends on; the questions may remain outstanding independently in the shared timeline. Incorporate each correction into the source bundle.
  • An unanswered, disputed, or unresolved claim blocks only itself. Keep it out of normal Tree content and continue with independently settled durable candidates.
  • A needed human must already participate in the originating task chat. If the environment cannot address them there, report the unresolved claim and prepared confirmation prompt; do not create another chat as a fallback. Stop before the Tree write only when no independently settled durable candidate remains.

Sync durable context

  • Treat the exact meeting artifacts, relevant confirmation replies, and the user's Tree-write intent as one meeting source bundle for first-tree-write. Do not reimplement its Tree-read, target-selection, verification, branch, or PR workflow.
  • Let first-tree-write apply the Context Tree Double Test. Sync only durable decisions, constraints, ownership or responsibility changes confirmed by the affected humans, and cross-domain relationships that future agents must respect.
  • Do not dump the transcript, the complete meeting summary, routine progress, temporary plans, task lists, or transient blockers into normal Tree content. Those remain in their source systems unless they establish durable context.
  • If nothing passes the Tree write bar, create no Tree change and explain why.
  • Let first-tree-write verify the Tree and prepare the Tree PR or MR. Stop before review or merge.

Finish

Report:

  • the Context Tree nodes changed and the Tree PR or MR, or why no Tree write was warranted;
  • any durable candidate still blocked on identity, attribution, conflict, or confirmation.

Never maintain discovery watermarks, processed ledgers, provider profiles, organizer gates, schedules, or a parallel approval state.

© first-tree-ai, 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

SKILL.md and 2 other files in skills/.experimental/meeting-to-tree of first-tree-ai/first-tree.

  • SKILL.md
  • VERSION
  • agents/openai.yaml

Open the folder on GitHubat commit 13f2a38

Compare with similar skills

Meeting To Tree 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.

Meeting To Tree compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Meeting To Tree this skillfirst-tree-ai/first-tree154—~1.8kAutomated safety check: PassApache-2.0
Meeting Notesoutline/outline41k—~551Automated safety check: PassCustom licence
Management Talkthananon/9arm-skills3.2k—~3.2kAutomated safety check: PassNone
Challenge Baseline ModelAgibotTech/genie_sim1.4k—~2.4kAutomated safety check: PassCustom licence
Handwriting Stand Uplimin112/min-skill454—~2.5kAutomated safety check: PassNone
Daily Journalravila4/claude-adhd-skills158—~2.5kAutomated safety check: PassMIT

Similar skills

  • Meeting Notes

    outline/outline

    Create meeting notes in Outline from a template; use when the user wants an agenda, notes, or a follow-up document for a meeting.

    41k GitHub stars~551 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Management Talk

    thananon/9arm-skills

    Rewrite engineer-to-engineer content for engineering-org leadership (VPs, directors, PMs, release managers, execs in an engineering-savvy company) and shape it for the channel it is going to — JIRA…

    3.2k GitHub stars~3.2k tokensUpdated 3 mo ago
    Productivity & AutomationAuto-check passed
  • Challenge Baseline Model

    AgibotTech/genie_sim

    Provision and launch the Simulation Challenge baseline inference model end to end: clone the inference code from a given git repo/branch, download the checkpoints from ModelScope into the repo's…

    1.4k GitHub stars~2.4k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed
  • Handwriting Stand Up

    limin112/min-skill

    Turn a screen recording of handwriting (or a photo of handwritten text) into a single-file HTML "continuation" — the recording plays, the ink lifts off the page as solid 3D letters, a short animated…

    454 GitHub stars~2.5k tokensUpdated 2 days ago
    Productivity & AutomationAuto-check passed
  • Daily Journal

    ravila4/claude-adhd-skills

    Draft, organize, or update development journal entries. An agent skill from ravila4/claude-adhd-skills.

    158 GitHub stars~2.5k tokensUpdated 7 mo ago
    Productivity & AutomationAuto-check passed
  • Granola

    ArtemXTech/claude-code-obsidian-starter

    Query and sync Granola meetings to Obsidian vault. An agent skill from ArtemXTech/claude-code-obsidian-starter.

    225 GitHub stars~905 tokensUpdated 5 days ago
    Productivity & AutomationAuto-check passed

More from first-tree-ai/first-tree

All 9 skills in this repo
  • First Tree File Bug

    first-tree-ai/first-tree

    File a GitHub issue about a defect in First Tree itself — the CLI, agent runtime, chat, web app, GitHub integration, GitLab integration, or Context Tree tooling — onto First Tree's own GitHub-hosted…

    154 GitHub stars~2.8k tokensUpdated 11 days ago
    Auto-check passed
  • Context Tree Review

    first-tree-ai/first-tree

    Review a GitHub pull request or GitLab merge request against the workspace-bound Context Tree when a trusted server-authored Context Reviewer run supplies provider-scoped authority.

    154 GitHub stars~8k tokensUpdated 11 days ago
    Auto-check passed
  • First Tree Welcome

    first-tree-ai/first-tree

    A skill your agent uses for a First Tree onboarding first chat, especially natural opening messages like "welcome aboard", "Please help me get started with First Tree", or "Please help me get…

    154 GitHub stars~11k tokensUpdated 11 days ago
    Auto-check passed
  • Context Tree Audit

    first-tree-ai/first-tree

    Audit stored normal content on the bound Context Tree's actual binding branch when a human explicitly asks to audit the whole tree, a domain, or specific normal paths for drift, contradictions…

    154 GitHub stars~1.9k tokensUpdated 11 days ago
    Auto-check passed
  • First Tree Read

    first-tree-ai/first-tree

    Read the applicable Context Tree before acting. An agent skill from first-tree-ai/first-tree.

    154 GitHub stars~6.1k tokensUpdated 11 days ago
    Auto-check: warnings
  • First Tree QA

    first-tree-ai/first-tree

    Act as an independent QA engineer for a software repository.

    154 GitHub stars~2.1k tokensUpdated 11 days ago
    Auto-check passed

Questions about Meeting To Tree

What does Meeting To Tree do?

Turn exact meeting records that the user supplies into durable Context Tree updates. Meeting To Tree is an agent skill from first-tree-ai/first-tree. Turn exact meeting records that the user supplies into durable Context Tree updates.

When should I use Meeting To Tree?

Meeting To Tree fits situations like: A user asks to sync meeting minutes; decision records; related meeting artifacts into the teams Context Tree: read the exact sources; reconcile chronology.

How do I install Meeting To Tree in Claude Code?

Run `npx skills add first-tree-ai/first-tree --skill meeting-to-tree -a claude-code`. Or copy the skill folder (skills/.experimental/meeting-to-tree in first-tree-ai/first-tree) into .claude/skills/meeting-to-tree in your project. Claude Code loads it when a task matches its description.

How do I install Meeting To Tree in Codex?

Run `npx skills add first-tree-ai/first-tree --skill meeting-to-tree -a codex`. Or copy the skill folder (skills/.experimental/meeting-to-tree in first-tree-ai/first-tree) into .agents/skills/meeting-to-tree in your project. Codex loads it when a task matches its description.

Can I use Meeting To Tree 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 first-tree-ai/first-tree --skill meeting-to-tree -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/meeting-to-tree, .gemini/skills/meeting-to-tree, .github/skills/meeting-to-tree and .opencode/skills/meeting-to-tree in your project.

What does Meeting To Tree need to run?

SKILL.md names no scripts, command-line tools or credentials: Meeting To Tree is instructions for the agent only.

Does Meeting To Tree access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Meeting To Tree safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Meeting To Tree use?

Meeting To Tree is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Meeting To Tree use?

About 1.8k tokens (SKILL.md is roughly 7.2k 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 Meeting To Tree?

Skills that share tags, products or a category with Meeting To Tree: Meeting Notes (outline/outline, 41k stars), Management Talk (thananon/9arm-skills, 3.2k stars), Challenge Baseline Model (AgibotTech/genie_sim, 1.4k stars) and Handwriting Stand Up (limin112/min-skill, 454 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Meeting To Tree?

first-tree-ai (a GitHub organization) maintains it in first-tree-ai/first-tree, which has 154 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on September 30, 2026.

Source: first-tree-ai/first-tree on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.