answer-shapes
Skill0 starsChanged 4 months agoMITView on GitHub
Optional output skeletons for common coding deliverables — bug fix, code review, investigation. Apply when the deliverable is one of these shapes to keep the answer complete and parseable (root cause / fix / verification, etc.); especially helps weaker models and machine-consumed handoffs. Skip for freeform questions.
In this repository16 other files it gives its agents.
- claim-verificationSkill
- create-prSkill
- findings-ledgerSkill
- git-safetySkill
- invariant-auditSkill
- lossless-doc-compressSkill
- model-orchestrationSkill
- office-hoursSkill
- plan-reviewSkill
- prompt-caching-playbookSkill
- review-ratchetSkill
- spec-fidelity-reviewSkill
- staff-reviewSkill
- systematic-debuggingSkill
- test-adequacy-reviewSkill
- verification-before-completionSkill
The file
Files
Answer shapes
Lightweight, opt-in skeletons for the most common coding deliverables. They cost no always-on prefix (this body loads only when the skill fires). Use a shape when the deliverable is one of the three below — they make a weak model's answer complete and a strong model's output parseable for an orchestrator. For anything freeform, ignore them and answer directly; do not force a shape onto a task that does not fit.
Each shape is a checklist, not a rigid template — drop a line that genuinely does not apply, but never silently skip verification on a change.
Bug fix
- Root cause: what is actually wrong and why (not just the symptom).
- Fix: the change, cited as
file:line. - Verification: the command you ran (or would run) and the observed result.
Code review
- Summary: one or two sentences on what changed and overall assessment.
- Findings: one row each —
severity—file:line— issue — suggested fix. - Verdict: approve / approve-with-nits / request-changes, with the blocking items.
Investigation
- Question: the precise thing being answered.
- Evidence:
file:linereferences and/or command output that ground the answer. - Conclusion: the direct answer.
- Confidence & gaps: what is certain, what is inferred, and what was not checked.
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.

