spec-implement
Skill0 starsChanged 9 months agoMITView on GitHub
Execute open tasks from specs/{feature}/plan.md using an implement → self-validate → fix loop, updating plan.md progress after each completed task. Use this skill whenever someone wants to start or continue feature implementation guided by plan.md, run a self-validating coding loop, continue from a specific task ID, or work through phased tasks with built-in quality checks. This is the execution phase after spec-plan in the spec-driven workflow. Don't use for ad-hoc bug fixes, code review, or implementation tasks not defined in plan.md.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- benjaminthomas/spec-driven-devtheir own version, first seen Nov 8, 2026
- stjarnstrom/spec-systemtheir own version, first seen Oct 15, 2026
- anyoneanderson/agent-skillstheir own version, first seen Oct 13, 2026
- xfstudio/skillstheir own version, first seen Oct 13, 2026
- martinffx/ateliertheir own version, first seen Oct 9, 2026
- sourjya/kiro-railstheir own version, first seen Jul 8, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- martinffx/atelier★ 51same name
- sourjya/kiro-rails★ 9same name
- xfstudio/skills★ 9same name
- anyoneanderson/agent-skills★ 3same name
- benjaminthomas/spec-driven-dev★ 2same name
- stjarnstrom/spec-system★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- spec-constitutionSkill
- spec-planSkill
- spec-researchSkill
- spec-specifySkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Iron Law: No completion claims without fresh verification evidence.
- Distinctive: line 36
When testing is required to prove the task is complete, make the test change, verification command, and expected outcome explicit before …
- Distinctive: line 42
Run the actual verification command and read the output before claiming pass.
- Very specific: line 43
Update
plan.md: after each successful task: - Distinctive: line 51
Stop-the-line backflow: when findings change approved documents:
- Distinctive: line 55
If documents are updated, review and keep within 150 lines.
- Distinctive: line 61
Every task has fresh verification evidence (not stale or assumed)
“Common” is measured: kept by at least 6 in 10 of the 6 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.
Files
Implement Skill
Purpose
Implement using specs/{feature}/plan.md as the single progress source.
Iron Law: No completion claims without fresh verification evidence. If you haven't run the command in this step, you cannot claim it passes.
Input
- Existing
specs/constitution.mdwhen present specs/{feature}/spec.mdandspecs/{feature}/plan.md
Output
- Implemented code with passing tests
- Updated
specs/{feature}/plan.md(andspec.mdif findings require it) - Progress log entries with verification evidence
Steps
- Resolve
languageand shared rules fromspecs/constitution.mdwhen present; otherwise infer from workflow documents and the user's message. Ask only if still unclear. - Confirm spec/plan approval state — both must be
approvedbefore work begins — and critically review the plan for gaps, contradictions, or unclear verification before implementing. - Process open tasks from top to bottom. Set
plan.mdtoin-progresswhen work starts. - Implementation loop for each task:
- Implement the smallest coherent slice
- When testing is required to prove the task is complete, make the test change, verification command, and expected outcome explicit before claiming success
- For bug fixes, test failures, or unexpected behavior, reproduce and identify root cause before changing implementation; create the failing check first when practical
- Classify findings:
local-only(continue),plan-impacting(update plan, realign),spec-impacting(stop, return upstream) - Delegate deep investigation to
spec-researchwhen needed - Self-validate (tests, type checks, static analysis, security checks)
- Fix until green
- Run the actual verification command and read the output before claiming pass; never trust "should pass" or stale results
- Update
plan.mdafter each successful task:- Map the task or phase DoD to the fresh evidence that proves it; passing commands are not enough if they do not cover the requirement
- Mark task complete, keep
status: in-progressuntil all tasks and phase DoD items finish - Append under
## Progress Log(create if missing):- Task: [TASK_ID] | Change: [SUMMARY] | Doc Impact: [local-only|plan-impacting|spec-impacting]
- Coverage: [US/FR/DoD proven]
- Validation: [PASS/FAIL + evidence] | Next: [NEXT_TASK]
- Escalate exception cases: conflicting requirements, high-risk changes, unresolvable validation failures.
- Stop-the-line backflow when findings change approved documents:
plan-impacting: updateplan.md, realign before resumingspec-impacting: updatespec.md, reset todraft, stop until re-approved
- Confirm DoD completion per phase. Set
plan.mdtodonewhen all tasks and DoD items pass. - If documents are updated, review and keep within 150 lines.
- Suggest next step: continue
spec-implementor final completion report.
Success Criteria
plan.mdprogress matches actual implementation state- Every task has fresh verification evidence (not stale or assumed)
- Completion is backed by requirement-to-evidence mapping, not proxy green status alone
- Findings that affect plan/spec trigger document realignment before continuing
- Phase DoD items are satisfied
- Non-exception issues resolved inside the self-validation loop
Completion Guidance
- Next recommended step: continue
spec-implementor close implementation - Include completed tasks, remaining tasks, and the next task in the response
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.

