spec-finish
Skill49 starsChanged 24 days agoMITView on GitHub
Post-implementation completion workflow for Spec-backed Plans. Use after spec-implement completes to validate, review, create stacked commits, and open a PR via code-pull-request. Triggers only with an active Spec-backed Plan after spec-implement completes, including when the user says "finish", "done", or "complete" in that context.
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 12 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈12
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
- Distinctive: line 18
All Spec-backed Plan tasks are complete
- Very specific: line 22
If not complete, go back to spec-implement.
- Very specific: line 32
If the implementation faithfully follows an unnecessarily large design, stop and return to spec-plan.
- Distinctive: line 35
Update the finished SDD to describe the smaller result.
- Distinctive: line 43
Check whether README, API documentation, or changelog updates are needed.
- Distinctive: line 98
All changed files since the intended base branch's merge base
- Distinctive: line 101
No debug code left
- Distinctive: line 113
Do not rewrite history by default.
- Distinctive: line 126
Before creating the PR, present a summary to the human:
- Distinctive: line 142
Only when the summary shows Ready for PR: yes, invoke the code-pull-request skill to create the PR.
- Distinctive: line 164
If implementation is still in progress, use spec-implement
- Distinctive: line 165
If tests are failing, go back to spec-implement
- Distinctive: line 166
If review found blocking findings or ones requiring user approval, go back to spec-implement
- Distinctive: line 167
If the implementation follows an unnecessarily large design, go back to spec-plan
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.
Files
Spec Finish
Post-implementation workflow: simplify → synchronize docs → validate → review → prepare PR.
Prerequisites
Before starting, verify:
- All Spec-backed Plan tasks are complete
- Working directory has no unresolved staged or unstaged changes
- Tests pass
If not complete, go back to spec-implement.
Step 1: Compare Scope and Simplify
Compare the implementation with the original behavior and user goal before documentation or validation. Remove unrequested scope, duplicate concepts, one-consumer abstractions, and custom machinery that replaces sufficient platform behavior.
If the implementation faithfully follows an unnecessarily large design, stop and return to
spec-plan. Get approval for the smaller plan before continuing.
Update the finished SDD to describe the smaller result. Replace rejected architecture in the normative design and plan instead of preserving it as precedent; mention it only as a rejected alternative when that history remains useful.
Step 2: Update Documentation
Check whether README, API documentation, or changelog updates are needed. Make and commit any necessary documentation changes through code-commit before final validation.
Step 3: Validate
Run validation checks.
Test Suite
npm test
# or
pytest
# or
cargo testType Check
npm run typecheck
# or
python -m mypy
# or
cargo checkLint
npm run lint
# or
ruff check .
# or
cargo clippyBuild
npm run build
# or
go build ./...If any fail: Return to spec-implement to fix.
If all pass: Proceed.
Step 4: Review
Invoke the installed code-review skill through the harness's skill mechanism for one comprehensive review of the final change.
What to Review
- All changed files since the intended base branch's merge base
- Test coverage
- Documentation updates
- No debug code left
If code-review finds issues
- Minor fixes may be made here, then re-validated and reviewed.
- Findings with
blocking: trueorrequires_user_approval, and scope-changing fixes, return tospec-implement. Non-blocking findings and follow-ups do not.
Step 5: Prepare Commits
Review current commits with git log --oneline. Use code-commit for any uncommitted work.
Do not rewrite history by default. If a rebase would materially improve an unpublished stack,
show the affected range and ask for separate approval before rebasing.
Step 6: Prepare the PR
Steps 1-5 (simplification, documentation, validation, review, commits) must all be complete before proceeding. If code-review found blocking findings or ones requiring user approval, stop and return to spec-implement to fix them. Do not proceed to Step 6b.
Step 6a: Present Completion Summary
Before creating the PR, present a summary to the human:
## Completion Summary
**Feature:** [name]
**Tests:** [passed/failed]
**Type Check:** [passed/failed]
**Lint:** [passed/failed]
**Review:** [passed/issues found]
**Commits:** [N commits in stack]
**Ready for PR:** [yes/no]Step 6b: Invoke code-pull-request
Only when the summary shows Ready for PR: yes, invoke the
code-pull-request skill to create the PR. It
detects the platform (GitHub/GitLab), checks for an existing PR, finds a
template, generates the body from commits, and opens the PR via gh or glab.
Handoff
"Implementation complete. [N] commits are ready. PR package ready for approval."
Integration
This skill orchestrates other skills:
- Invokes code-review for quality check
- Invokes code-pull-request as the final step to open the PR
When NOT to Use
- If implementation is still in progress, use spec-implement
- If tests are failing, go back to spec-implement
- If review found blocking findings or ones requiring user approval, go back to spec-implement
- If the implementation follows an unnecessarily large design, go back to spec-plan
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- atelier-orchestratorSkill
- atelier-setupSkill
- code-commitSkill
- code-handoffSkill
- code-pull-requestSkill
- code-reviewSkill
- code-subagentsSkill
- oracle-codebase-designSkill
- oracle-debugSkill
- oracle-domain-modellingSkill
- oracle-grill-meSkill
- spec-brainstormSkill
- spec-implementSkill
- spec-loopSkill
- spec-planSkill
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
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.

