agentleFS
egregore-labsegregore-labs/egregore/.claude/skills/note/SKILL.md

note

Skill293 starsChanged 10 days agoMITView on GitHub

Use when the user says 'jot this down', 'note to self', 'just thinking out loud', or 'park this thought' — saves an actor-owned private draft locally and promotes it to organizational knowledge only on an explicit request.

24 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add, resume and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • tim-mccrimmonSkill

    add

    Process a document (PRD, architecture doc, security requirements, etc.) into structured context. Extracts relevant information and generates appropriate SCDs.

    Also in 3 projects that use this

  • genomewalkerSkill

    resume

    Resume a thread by loading its ~800-token context capsule

    Also in 3 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 4 projects that use this

  • GoogleSkill

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    Also in 3 projects that use this

  • SentrySkill

    skill-creator

    Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when the user says 'jot this down', 'note to self', 'just thinking out loud', or 'park this thought' — saves an actor-owned private …

    line 14
  2. Distinctive:

    No arguments: ask what to capture.

    line 18
  3. Distinctive:

    After the user explicitly approves organizational promotion, call:

    line 47
  4. Distinctive:

    Do not access another actor's note or treat policy hints as authorization.

    line 65
  5. Distinctive:

    Do not call Git, QMD, graph, telemetry, publishing, sharing, notification, or control-plane mechanics directly.

    line 66

“Common” is measured: kept by at least 6 in 10 of the 18 edited versions of this file we could read. “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

Note

Capture a half-baked thought for the active actor. Private notes are local draft state, not canonical organizational truth, and are never committed, indexed, published, shared, or notified automatically.

When to invoke

Use when the user says 'jot this down', 'note to self', 'just thinking out loud', or 'park this thought' — saves an actor-owned private draft locally and promotes it to organizational knowledge only on an explicit request.

Commands

  • No arguments: ask what to capture.
  • Content: infer a short title and one of thought, session, retrospective, or journal; write the user's meaning without polishing it into a decision.
  • list: call bash bin/knowledge.sh note-list and format the returned notes.
  • share <title> or promote <title>: select the actor's note, preview it, choose decision, finding, or pattern, and explicitly confirm promotion.

Capture

Render only the note body to a temporary file under tmp/, then call with {note-file} for that file, {title} for the title inferred from the user's words, and {note-type} for the inferred thought, session, retrospective, or journal type:

bash bin/knowledge.sh note-create \
  --title '{title}' \
  --type '{note-type}' \
  --input '{note-file}'

The Runtime adapter resolves ActorContext and authorizes the actor before local private persistence. The resulting envelope carries stable actor identity and a private policy hint. The hint describes posture; authorization remains the Runtime policy decision.

Promotion

Open the selected note through bash bin/knowledge.sh note-open "{path}". After the user explicitly approves organizational promotion, call:

bash bin/knowledge.sh note-promote \
  --path "{path}" \
  --type "{decision|finding|pattern}" \
  --title "{title}" \
  --topic "{topic}" \
  --workstream "{workstream}"

Promotion uses CanonicalArtifactWriteback: authorize, assign stable typed identity and source provenance, persist Markdown, record Git provenance, update retrieval, start background embedding, then emit content-free telemetry. The private copy remains and records the canonical target.

Boundaries

  • Do not access another actor's note or treat policy hints as authorization.
  • Do not call Git, QMD, graph, telemetry, publishing, sharing, notification, or control-plane mechanics directly.
  • share means promotion into authorized organizational Markdown, not external publication. External sharing and notification require separate permission and exact consent.

Confirm private capture with its local path. Confirm promotion with the new canonical path and writeback status.

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.