agentleFS
jame-hvjame-hv/brse-toolkit/skills/meeting-intake/SKILL.md

meeting-intake

Skill0 starsChanged 5 days agoMITView on GitHub

Use this after any meeting, call or client message that may change the project — minutes (議事録), rough notes, a transcript, a pasted chat, or just the user's one-line summary — to record the meeting, extract decisions, answers to open Q&A, new questions and tasks into the project registers, and hand the changes to change-impact.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run <py> ${CLAUDE_PLUGIN_ROOT}/scripts/brse.py config and read its JSON:

    line 14
  2. Very specific:

    Hand off: every new or superseding decision to change-impact.

    line 61
  3. Distinctive:

    Minutes for the client: only if the user asks: the draft goes to Comtor for wording.

    line 63

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Before running

<py> below = the Python recorded by /brse-toolkit:setup (runtime.python in ~/.config/brse-toolkit/config.json — read that file directly), else the first of python3, python, py -3 that runs. No Python at all → tell the user to run /brse-toolkit:setup, and continue only with steps that need no script, saying which checks were skipped.

Run <py> ${CLAUDE_PLUGIN_ROOT}/scripts/brse.py config and read its JSON:

  • error → show it to the user and stop; the config file must be fixed first.
  • workspace_root is null → the folder isn't initialized. Ask once: run /brse-toolkit:init first (recommended — memory and knowledge get saved for next time) or continue once without saving. Running as a subagent dispatched by a main agent → the parent already resolved this; proceed.
  • Otherwise use config.paths (sources, templates, outputs — relative to workspace_root), config.style, config.translation, and the files in .brse/memory/long/. Never assume a folder name the config doesn't list.
  • warnings not empty → mention them in one line (likely a typo in the config).

When to use

Something was said that may change the project: a meeting, a call, a client email/chat, an answered Q&A sheet, or the user saying "chốt là …". Works with whatever input exists — never stop because there are no formal minutes:

InputHow to read it
議事録 / minutes file (any format)brse.py kb-ingest, then read the converted part
Rough notes, pasted chat, emailread as given
Audio / videotranscribe if a tool exists (whisper on PATH); otherwise say so in one line and work from whatever text the user gives
Answered Q&A sheet from the clientingest; map each answer to its Q-xxx by number or wording
One-line summary from the user ("khách chốt dùng lại module cũ")treat as a decision with source "user, <date>"

Steps

brse.py register below = <py> ${CLAUDE_PLUGIN_ROOT}/scripts/brse.py register.

  1. Load context (no questions yet): brse.py register status, brse.py register list --open, and .brse/memory/long/. Everything already recorded is never asked again.
  2. Record the meeting: brse.py register add M --title "<topic>" --set attendees="…" --set file="<path of the raw input>". Raw input is kept, never edited.
  3. Extract, each with the exact sentence it came from:
    • Decisions → add D --source M-… --links <R/Q ids>; if it replaces an earlier decision, --supersedes D-xxx (search active D first — a contradiction with an active D is always a supersede, never two actives).
    • Answers to open Q → update Q-xxx --status answered --set answer="…", plus the decision it implies.
    • New questions / unclear points → add Q --status draft --links ….
    • Tasks → add T --owner <anh|client|BrSE|SE|QA|Comtor> --due ….
    • Requirements added / dropped → add R or update R-xxx --status out. Uncertain whether something was decided → record it as D with --status proposed; the user confirms at the gate, not by an extra question.
  4. Sync each new active decision as one line in .brse/memory/long/decisions-log.md (other skills read it).
  5. Link back: update M-… --add-links <all new ids>.
  6. Hand off every new or superseding decision to change-impact. If nothing changed the scope or approach (only tasks / notes), skip it.
  7. Minutes for the client only if the user asks: the draft goes to Comtor for wording; never send.

Output (short, conclusion first)

M-2026-11-09 recorded: 2 decisions (1 replaces D-006), 3 answers, 2 new Q, 4 tasks.
Needs your yes: D-015 (proposed) — <one line>.
→ change-impact running on D-014.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.