speckit.implement
Skill3 starsChanged 45 days agoMITView on GitHub
Code Builder (Anti-Regression) - Deploy code in tasks with IRONCLAD protocols.
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
3
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
- could be automatic: a setting could enforce it
- Very specific: line 10
Read .agents/specs/[feature]/tasks.md, plan.md, spec.md, and .agents/memory/constitution.md.
- Distinctive: line 23
Verify after every task with targeted tests, linters, or type checks.
- Distinctive: line 26
All task acceptance criteria met, targeted and suite tests pass with zero regression, task checkbox marked, and atomic conventional commit …
- Distinctive: line 29
Never commit failing code.
“Common” is measured: kept by at least 6 in 10 of the 3 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
Mission
Execute approved implementation tasks atomically, safely, and test-first while enforcing anti-regression gates, deviation rules, and runtime consistency.
Inputs and Outputs
- Read
.agents/specs/[feature]/tasks.md,plan.md,spec.md, and.agents/memory/constitution.md. - Modify source code, configuration, tests, and task tracking checkboxes; maintain atomic git commits.
Protocol
- Respect the 15-Minute Rule: each task must be atomic, touching at most 3 files with verifiable acceptance criteria.
- Analyze blast radius before modifying code; choose direct targeted edit for isolated changes or Strangler Pattern for complex refactoring.
- Apply TDD red-green cycle: reproduce failure or create unit test first, implement minimal passing code, then verify.
- Re-anchor context against
constitution.mdevery 3 tasks to guarantee adherence to Docker-first, ENV-first, and coding standards. - Handle deviations autonomously:
- In-scope bugs: fix immediately and verify.
- Missing critical files/configs: add with documented rationale.
- Blockers: perform systematic root cause analysis before escalating.
- Architectural shifts: STOP and request explicit user confirmation.
- Verify after every task with targeted tests, linters, or type checks; run the full build/test suite at phase boundaries in Docker.
Completion Gate
All task acceptance criteria met, targeted and suite tests pass with zero regression, task checkbox marked, and atomic conventional commit created.
Guard Rails
Never commit failing code. Never hardcode secrets, tokens, or environment values. Never exceed task scope without updating plan or tasks.
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- caipe-io/ai-platform-engineering★ 437same name
- cnoe-io/ai-platform-engineering★ 437same name
- compnew2006/Spec-Kit-Antigravity-Skills★ 68same 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 repository64 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/bro-skills.mdcCursor rule
- .agents/skills/llms.txtllms.txt
- brandkitSkill
- bro-mcp-loopSkill
- ci-security-scanning-with-strixSkill
- design-taste-frontendSkill
- fix-security-vulnerabilities-with-strixSkill
- full-output-enforcementSkill
- gpt-tasteSkill
- high-end-visual-designSkill
- imagegen-frontend-mobileSkill
- imagegen-frontend-webSkill
- image-to-codeSkill
- industrial-brutalist-uiSkill
- managed-pentesting-with-strixSkill
- minimalist-uiSkill
- penetration-testing-with-strixSkill
- ponytailSkill
- redesign-existing-projectsSkill
- speckit.ai-engineerSkill
- speckit.analyzeSkill
- speckit.architectureSkill
- speckit.backendSkill
- speckit.backlogSkill
- speckit.checkerSkill
- speckit.checklistSkill
- speckit.clarifySkill
- speckit.constitutionSkill
- speckit.contentSkill
- speckit.databaseSkill
- speckit.dddSkill
- speckit.debugSkill
- speckit.devopsSkill
- speckit.diffSkill
- speckit.event-realtimeSkill
- speckit.frontendSkill
- speckit.game-embeddedSkill
- speckit.game-native-jsSkill
- speckit.geoSkill
- speckit.identity-accessSkill
- speckit.identitySkill
- speckit.mapSkill
- speckit.migrateSkill
- speckit.payment-fintechSkill
- speckit.planSkill
- speckit.quizmeSkill
- speckit.reviewerSkill
- speckit.roadmapSkill
- speckit.securitySkill
- speckit.seoSkill
- speckit.specifySkill
- speckit.sre-observabilitySkill
- speckit.statusSkill
- speckit.tasksSkill
- speckit.taskstoissuesSkill
- speckit.testerSkill
- speckit.uatSkill
- The first 60 shown.
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.