agentleFS
endlessblinkendlessblink/master-plan/skills/done/SKILL.md

done

Skill26 starsChanged 9 months agoMITView on GitHub

Task completion workflow — run tests, commit, push, and update MASTER_PLAN.md. Use when a task is finished and ready to ship. Triggers on "/done", "mark done", "task complete", "finish task", "ship it".

  • Reads credentials
  • Commits and pushes

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

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

  • 0

    Common

    Most of the 33 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run git status to see what files were modified:

    line 19
  2. Very specific:

    Use AskUserQuestion to collect:

    line 34
  3. Distinctive:

    IMPORTANT: Wait for user to provide the summary before proceeding.

    line 44
  4. Very specific:

    If package.json exists → npm test

    line 49
  5. Very specific:

    If pyproject.toml or setup.py exists → pytest

    line 51
  6. Very specific:

    If Makefile with test target → make test

    line 52
  7. Distinctive:

    If tests fail: STOP immediately. Report failures.

    line 55
  8. Distinctive:

    Search for the task ID and confirm all occurrences show strikethrough or ✅ DONE:

    line 99
  9. Distinctive:

    Prefer staging specific files by name over git add -A.

    line 113
  10. Very specific:

    Verify with grep: after updating MASTER_PLAN.md

    line 173

“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

Task Completion Workflow

Finalize a completed task: verify tests pass, commit changes, update MASTER_PLAN.md, and push.

Triggers

  • /master-plan:done - Main command
  • "mark done", "task complete", "finish task", "ship it"

Workflow

Step 1: Check What Changed

Run git status to see what files were modified:

git status
git diff --stat

Output immediately:

Files changed:
- [list of modified files]

Step 2: Get Task Information

Use AskUserQuestion to collect:

  1. Task ID (header: "Task ID")
    • Options: "Tracked task (enter ID)" or "Quick fix (no task ID)"
  2. Run tests? (header: "Tests")
    • Options: "Yes — run test suite (Recommended)" or "Skip tests"

Then ask in plain text: "What's a brief summary of the changes? (1-2 sentences)"

IMPORTANT: Wait for user to provide the summary before proceeding.

Step 3: Run Tests (unless skipped)

Detect and run the project's test command. Check in order:

  1. If package.json exists → npm test
  2. If Cargo.toml exists → cargo test
  3. If pyproject.toml or setup.py exists → pytest
  4. If Makefile with test target → make test
  5. If go.mod exists → go test ./...

If tests fail: STOP immediately. Report failures. Do NOT proceed. If tests pass: Continue. If no test command found: Warn user and continue.

Step 4: Update MASTER_PLAN.md (if tracked task)

Skip this step if user selected "Quick fix (no task ID)".

CRITICAL: Tasks may appear in multiple locations. Update ALL of them:

4a. Summary/Roadmap Table

Find the task row and update:

# Before:
| **TASK-XXX** | **Title** | **P2** | PLANNED | ... |

# After:
| ~~**TASK-XXX**~~ | ✅ **Title** | **P2** | ✅ DONE (YYYY-MM-DD) | ... |

4b. Subtask/Bullet Lists

# Before:
- TASK-XXX: Description

# After:
- ~~TASK-XXX~~: ✅ Description

4c. Detailed Section Header

# Before:
### TASK-XXX: Title (IN PROGRESS)

# After:
### ~~TASK-XXX~~: Title (✅ DONE)

4d. Verify All Updated

Search for the task ID and confirm all occurrences show strikethrough or ✅ DONE:

grep "TASK-XXX" docs/MASTER_PLAN.md

Step 5: Commit and Push

Stage all relevant files. NEVER commit:

  • .env* files
  • credentials*.json or files containing secrets
  • node_modules/, __pycache__/, target/, .venv/
  • Backup files, generated stats, lock files (unless intentional)

Prefer staging specific files by name over git add -A.

# Stage code files
git add <changed-files>
git add docs/MASTER_PLAN.md  # if tracked task

# Commit
git commit -m "$(cat <<'EOF'
feat(TASK-XXX): Brief summary from user

- Key change 1
- Key change 2

Co-Authored-By: Claude <noreply@anthropic.com>
EOF
)"

# Push
git push

For quick fixes (no task ID):

git commit -m "$(cat <<'EOF'
fix: Brief summary from user

Co-Authored-By: Claude <noreply@anthropic.com>
EOF
)"
git push

Commit prefix conventions:

  • feat(TASK-XXX): — New feature
  • fix(BUG-XXX): — Bug fix
  • chore(TASK-XXX): — Maintenance
  • refactor(TASK-XXX): — Code refactoring
  • docs(TASK-XXX): — Documentation only

Step 6: Report Completion

Output this summary:

## Task Complete

- **Task**: TASK-XXX (or "Quick fix")
- **Summary**: [user's summary]
- **Tests**: ✅ Passed (or ⏭️ Skipped)
- **Commit**: [short hash] — [message]
- **Push**: ✅ Pushed to origin
- **MASTER_PLAN.md**: Updated / N/A

Important Rules

  1. NEVER skip commit/push — Changes must be pushed to the remote
  2. ALWAYS collect summary — Don't proceed without knowing what changed
  3. Update ALL locations in MASTER_PLAN.md for tracked tasks
  4. Verify with grep after updating MASTER_PLAN.md
  5. Wait for user input — Don't assume or skip questions
  6. Test failures block completion — If tests fail, stop and report

Files to NEVER Commit

  • .env* files (secrets)
  • credentials*.json
  • Private keys, tokens
  • Generated/cached files (node_modules/, dist/, __pycache__/)
  • OS files (.DS_Store, Thumbs.db)

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.