agentleFS
mhmarkhoffmann-lobmhmarkhoffmann-lob/claude-desk/skills/done/SKILL.md

done

Skill0 starsChanged 5 months agoMITView on GitHub

Use this skill when the user ends a working session or wants to write the changelog. Trigger on: "/done", "end session", "write changelog", "wrap up", "we're done", "session beenden", "changelog schreiben", "wir sind fertig", "tschüss".

37 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use simplify, work and 4 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.
  • Hugging FaceSkill

    simplify

    Refactor code after tests pass. The "Refactor" phase of Red-Green-Refactor.

    Also in 5 projects that use this

  • vbrevikSkill

    work

    Use when the user says 'plan', 'todo', 'copy plan', 'append plan', 'resume plan', 'priorities', or 'what's next'.

    Also in 3 projects that use this

  • OpenAISkill

    transcribe

    Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 9 projects that use this

  • genomewalkerSkill

    learn

    Learn from web sources, generate SKILL.md, and store key patterns in soul memory. Trigger keywords: learn, skill-gen, web-learn, documentation, tutorial.

    Also in 3 projects that use this

  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 33 edited versions we read keep these.

  • 7

    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:

    Do not hardcode a project list.

    line 33
  2. Distinctive:

    If the match is ambiguous or missing, ask the user which project is meant.

    line 36
  3. Distinctive:

    If a project was completed:

    line 70
  4. Distinctive:

    Remove it from "Active"

    line 71
  5. Distinctive:

    Only completed work + decisions, no open items, no discussion

    line 96
  6. Distinctive:

    No entry if nothing relevant happened in the session

    line 105
  7. Distinctive:

    Always get the date via Bash, never infer it from the conversation

    line 109

“Common” is measured: kept by at least 6 in 10 of the 33 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

Session Close

Purpose

Close a session cleanly: overwrite each touched project's FOCUS.md, update BRAIN.md, and append one line per project to CHANGELOG.md.

Base path for all files below: {{BRAIN_ROOT}} (set by install.sh).


Steps

Step 1: Summarize the session

Derive from the conversation:

  • Which projects were touched?
  • What was built, changed, or decided?
  • What is the current state per project?
  • What is the concrete next step per project?

Step 2: Overwrite FOCUS.md per project

For each touched active project, fully rewrite {{BRAIN_ROOT}}/projects/<category>/<project>/FOCUS.md.

Do not hardcode a project list. Resolve the path dynamically:

  • List directories under {{BRAIN_ROOT}}/projects/*/ and match the project name (and obvious aliases) against folder names.
  • If the match is ambiguous or missing, ask the user which project is meant.

FOCUS.md format (max ~150 tokens — this is the hot state, kept deliberately small):

# FOCUS — [Project name]

State: YYYY-MM-DD

---

## What's running
[2-3 sentences]

## Next step (concrete)
[exactly one action]

## Then
- [next step]

## Open decisions
[only if actively blocking — omit if none]

## Recent sessions (max 3, non-code projects only)
- DD.MM. — what happened

Step 3: Update BRAIN.md

File: {{BRAIN_ROOT}}/BRAIN.md

For each touched project:

  • Bring the one-line status (after the project name) up to date
  • Set the Last updated: line at the top

If a project was completed:

  • Remove it from "Active"
  • Move it to "Archive" with a short closing note
  • Move the folder via Bash to {{BRAIN_ROOT}}/_archive/<category>/<name>/

Step 4: CHANGELOG.md — one line per project

File: {{BRAIN_ROOT}}/CHANGELOG.md

Current timestamp via Bash: date "+%Y-%m-%d — %H:%M"

Insert a new section at the top:

## YYYY-MM-DD — HH:MM

**[Project name]**
- [What was done / decided — max 3-5 points]

**[Project name 2]**
- [What was done / decided]

Rules:

  • Each /done call = its own section with a timestamp — never merge into existing entries
  • Max 5 points per project — condense
  • Only completed work + decisions, no open items, no discussion

Step 5: Confirm

Short summary of what was done, then sign off.


Known pitfalls

  • No entry if nothing relevant happened in the session
  • Discussion and conversation context belong in FOCUS.md ("What's running"), not CHANGELOG
  • FOCUS.md is always overwritten — never appended
  • Actually update the BRAIN.md one-line status — not just the date
  • Always get the date via Bash, never infer it from the conversation

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.