agentleFS
NoaiRoxNoaiRox/specialist-agent/skills/finish/SKILL.md

finish

Skill2 starsChanged 9 months agoMITView on GitHub

Use when feature implementation is complete and the branch is ready for final validation, PR creation, or merge.

  • Commits and pushes

22 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use status, bootstrap and 5 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.
  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 5 projects that use this

  • OpenAISkill

    bootstrap

    Project bootstrapping orchestrator for repos that depend on Vercel-linked resources (databases, auth, and managed integrations). Use when setting up or repairing a repository so linking, environment provisioning, env pulls, and first-run db/dev commands happen in the correct safe order.

    Also in 3 projects that use this

  • AnthropicSkill

    start

    Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.

    Also in 3 projects that use this

  • Hugging FaceSkill

    implement

    Make tests pass. Invoke after /write-tests produces failing tests.

    Also in 6 projects that use this

  • dillonluiSkill

    design-review

    Review a view or flow for UX and UI issues. Provides severity-ranked, actionable findings grounded in established design heuristics. Use when the user asks for design feedback, UX review, or UI critique.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 8 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 2

    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:

    Never skip validation: - All checks must pass

    line 217
  2. Distinctive:

    Offer cleanup: - Keep repo clean

    line 219

“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

/finish - Finalize Branch

Complete development branch with final validation and metrics.

Branch: $ARGUMENTS (or current branch)

Workflow

Step 1: Pre-Flight Checks

# Check current branch
git branch --show-current

# Check for uncommitted changes
git status

# Check for untracked files
git status --porcelain

Required:

  • All changes committed
  • No untracked files (or intentionally ignored)
  • Not on main/master branch

Step 2: Run Full Validation

# TypeScript check
npx tsc --noEmit

# Lint
npm run lint

# Tests
npm test

# Build (if applicable)
npm run build

Output:

──── Validation ────
TypeScript: PASS ✓
Lint: PASS ✓
Tests: PASS ✓ (42/42)
Build: PASS ✓

Step 3: Generate Diff Summary

# Files changed
git diff main --stat

# Commits in branch
git log main..HEAD --oneline

Output:

──── Changes ────
Files changed: 12
Insertions: +450
Deletions: -120

Commits:
  abc1234 feat: add user service
  def5678 feat: add user component
  ghi9012 test: add user tests
  jkl3456 refactor: clean up types

Step 4: Session Metrics

──── Session Metrics ────
Branch: feature/user-profile
Duration: ~45 minutes
Commits: 4

Files:
  Created: 5
  Modified: 7
  Deleted: 0

Code:
  Lines added: 450
  Lines removed: 120
  Net change: +330

Tests:
  Added: 8
  Total passing: 42/42
  Coverage: 87%

Agents used:
  @planner: 1 invocation
  @builder: 3 invocations
  @reviewer: 1 invocation

Estimated tokens: ~18,500
Estimated cost: ~$0.28

Step 5: Cleanup Checkpoints

# List checkpoints
git tag -l "checkpoint/*"

# Offer to clean
"Clean up checkpoint tags? (y/n)"

If yes:

git tag -l "checkpoint/*" | xargs -n 1 git tag -d

Step 6: Prepare for Merge

──── Ready for Merge ────

Branch: feature/user-profile
Base: main
Status: Ready ✓

Pre-merge checklist:
- [x] All tests passing
- [x] No TypeScript errors
- [x] Code reviewed
- [x] Checkpoints cleaned

Next steps:
1. Push: git push -u origin feature/user-profile
2. Create PR: gh pr create
3. Merge: After approval

Output

──── /finish ────
Branch: [branch-name]

Validation:
  TypeScript: PASS ✓
  Lint: PASS ✓
  Tests: PASS ✓ (N/N)
  Build: PASS ✓

Changes:
  Files: N changed
  Lines: +N / -N
  Commits: N

Metrics:
  Tokens: ~N
  Cost: ~$X.XX
  Agents: N used

Checkpoints: [cleaned/kept]

Status: READY FOR MERGE ✓

Commands:
  git push -u origin [branch]
  gh pr create --title "[title]" --body "[body]"

Validation Failures

If validation fails:

──── /finish ────
Branch: feature/user-profile

Validation:
  TypeScript: FAIL ✗
    Error: src/user.ts:42 - Property 'name' is missing
  Lint: PASS ✓
  Tests: FAIL ✗
    2 tests failing

Status: NOT READY ✗

To fix:
1. Resolve TypeScript errors
2. Fix failing tests
3. Run /finish again

Anti-Rationalization

ExcuseReality
"Tests pass locally, good enough"CI runs in a clean environment. Your local cache hides broken imports and missing deps.
"I'll fix the lint errors in the next PR"Technical debt compounds. Fix now or carry it forever.
"The build takes too long to run"A broken build in production takes even longer to fix. Run it.
"I already reviewed the code mentally"Mental review misses what automated checks catch. Run the full suite.

Rules

  1. Never skip validation - All checks must pass
  2. Always show metrics - Transparency in cost
  3. Offer cleanup - Keep repo clean
  4. Don't auto-merge - Human decision

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.