skills/spec-finish/SKILL.md
Post-implementation completion workflow. Use after spec-implement completes to validate, review, create stacked commits, and prepare for PR. Triggers when implementation is done, when the user says "finish", "done", "complete", or after implementation tasks are finished.
npx skillsauth add martinffx/claude-code-atelier spec-finishInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Post-implementation workflow: validate → review → stack commits → prepare PR.
Before starting, verify:
If not complete → go back to spec-implement.
Run validation checks.
npm test
# or
pytest
# or
cargo test
npm run typecheck
# or
python -m mypy
# or
cargo check
npm run lint
# or
ruff check .
# or
cargo clippy
npm run build
# or
go build ./...
If any fail: Return to spec-implement to fix.
If all pass: Proceed.
Use the Skill tool to invoke code-review skill for comprehensive code review.
git log --onelinegit rebase -i <base-branch>Optional - use code-docs skill if needed.
## Completion Summary
**Feature:** [name]
**Tests:** [passed/failed]
**Type Check:** [passed/failed]
**Lint:** [passed/failed]
**Commits:** [N commits in stack]
**Ready for PR:** [yes/no]
"Implementation complete. [N] commits stacked. Ready for [submit/open PR]."
This skill orchestrates other skills:
development
Security architecture and threat modeling knowledge. Auto-invokes when designing features that handle untrusted data, authentication, authorization, external integrations, file uploads, or sensitive data. Provides risk assessment frameworks, trust boundary analysis, and security design principles — not implementation code.
testing
Adversarial review of non-trivial decisions using fresh-context scrutiny. Use when correctness matters more than speed, when stakes are high (production, security-sensitive logic, irreversible operations), or before committing significant architectural or implementation choices.
development
Compact the current conversation into a handoff document for another agent to pick up.
testing
Socratic interrogation of plans against the project's domain model and documented decisions. Use when the user wants to stress-test a plan, clarify terminology, or validate assumptions against existing domain language. Updates CONTEXT.md and ADRs inline as decisions crystallise.