spec-audit
Skill16 starsChanged 17 days agoMITView on GitHub
Check whether a feature or codebase is specified well enough to hand to a developer agent - five layers (what it does, its interfaces, its architecture, how it ages, what good looks like here) - and name the decisions an agent would otherwise fill in silently. Use before the readiness gate on any feature that touches existing code, and at setup when a codebase already exists.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- veraetogrex-portfolio/solo-sddtheir own version, first seen Nov 15, 2026
- vlad-ryzhkov/ai-context-engineering-for-frontendtheir own version, first seen Nov 15, 2026
- grooownow/qa-pilottheir own version, first seen Nov 1, 2026
- pierre-lecocq/claude-skillstheir own version, first seen Oct 11, 2026
- khivi/cockpittheir own version, first seen Oct 5, 2026
- jsulmont/mcp-lisptheir own version, first seen Jun 27, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- jsulmont/mcp-lisp★ 9same name
- grooownow/qa-pilot★ 6same name
- vlad-ryzhkov/ai-context-engineering-for-frontend★ 2same name
- caseyng/Claude-skills★ 1same name
- khivi/cockpit★ 0same name
- pierre-lecocq/claude-skills★ 0same name
- veraetogrex-portfolio/solo-sdd★ 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 repository120 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/agent-agentic-workflow.mdcCursor rule
- .cursor/rules/agent-android-dev.mdcCursor rule
- .cursor/rules/agent-architect.mdcCursor rule
- .cursor/rules/agent-backend-dev.mdcCursor rule
- .cursor/rules/agent-dashboard.mdcCursor rule
- .cursor/rules/agent-debugger.mdcCursor rule
- .cursor/rules/agent-desktop-dev.mdcCursor rule
- .cursor/rules/agent-devops.mdcCursor rule
- .cursor/rules/agent-explainer-writer.mdcCursor rule
- .cursor/rules/agent-feasibility.mdcCursor rule
- .cursor/rules/agent-growth.mdcCursor rule
- .cursor/rules/agent-ios-dev.mdcCursor rule
- .cursor/rules/agent-legal.mdcCursor rule
- .cursor/rules/agent-optimizer.mdcCursor rule
- .cursor/rules/agent-orchestrator.mdcCursor rule
- .cursor/rules/agent-platform-architect.mdcCursor rule
- .cursor/rules/agent-platform-designer.mdcCursor rule
- .cursor/rules/agent-product-designer.mdcCursor rule
- .cursor/rules/agent-qa.mdcCursor rule
- .cursor/rules/agent-researcher.mdcCursor rule
- .cursor/rules/agent-reviewer.mdcCursor rule
- .cursor/rules/agent-rollback.mdcCursor rule
- .cursor/rules/agent-security.mdcCursor rule
- .cursor/rules/agent-setup.mdcCursor rule
- .cursor/rules/agent-social-media.mdcCursor rule
- .cursor/rules/agent-web-dev.mdcCursor rule
- .cursor/rules/skill-bug-fix.mdcCursor rule
- .cursor/rules/skill-commit.mdcCursor rule
- .cursor/rules/skill-context-budget.mdcCursor rule
- .cursor/rules/skill-cost-audit.mdcCursor rule
- .cursor/rules/skill-decision-log.mdcCursor rule
- .cursor/rules/skill-experiment.mdcCursor rule
- .cursor/rules/skill-founder-voice.mdcCursor rule
- .cursor/rules/skill-frontend-design.mdcCursor rule
- .cursor/rules/skill-gates.mdcCursor rule
- .cursor/rules/skill-grilling.mdcCursor rule
- .cursor/rules/skill-handoff.mdcCursor rule
- .cursor/rules/skill-human-design.mdcCursor rule
- .cursor/rules/skill-human-steps.mdcCursor rule
- .cursor/rules/skill-karpathy-guidelines.mdcCursor rule
- .cursor/rules/skill-known-reds.mdcCursor rule
- .cursor/rules/skill-legal-review.mdcCursor rule
- .cursor/rules/skill-new-feature.mdcCursor rule
- .cursor/rules/skill-observability.mdcCursor rule
- .cursor/rules/skill-ordered-steps.mdcCursor rule
- .cursor/rules/skill-performance.mdcCursor rule
- .cursor/rules/skill-readiness-gate.mdcCursor rule
- .cursor/rules/skill-release.mdcCursor rule
- .cursor/rules/skill-requirement-first.mdcCursor rule
- .cursor/rules/skill-safe-data-write.mdcCursor rule
- .cursor/rules/skill-setup.mdcCursor rule
- .cursor/rules/skill-single-source.mdcCursor rule
- .cursor/rules/skill-spec-audit.mdcCursor rule
- .cursor/rules/skill-tailoring.mdcCursor rule
- .cursor/rules/skill-twin-check.mdcCursor rule
- .cursor/rules/skill-verified-claims.mdcCursor rule
- .cursor/rules/skill-verify-green.mdcCursor rule
- bug-fixSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 29
Read only; change nothing.
- Distinctive: line 45
Delegate: every layer COMPLETE, or THIN only where a wrong guess is cheap to undo.
“Common” is measured: kept by at least 6 in 10 of the 7 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
<!-- Generated by tools/sync_adapters.py from skills/spec-audit/SKILL.md. Edit the source, not this file. -->Spec audit
An agent given a thin spec does not stop and ask; it fills the gaps with whatever is most common in the code it learned from. This audit finds those gaps before the work is delegated, so the founder decides them instead of the agent's habits.
The five layers follow Hamidreza Saghir's framing of under-specified coding agents, as adapted in Florian Bruniaux's Claude Code guide; this version is written for this template's files.
The five layers, and where this template keeps each
| Layer | The question | Where it lives here | If missing, the agent will |
| 1. Behaviour | What must it do, and how do we know it does? | spec.md, the requirement rows | guess the behaviour |
| 2. Interfaces | What goes in and out, what errors, what must always hold? | contract.md, types and validation in the code | handle errors optimistically, loosen types |
| 3. Architecture | What exists already, where are the boundaries, what must not be created? | design.md, docs/adr/, AGENTS.md, skills/single-source/ | duplicate an existing module, cross a boundary |
| 4. Lifecycle | What is deliberately unfinished, what is deferred and why? | docs/HISTORY.md, tools/known_red.json, p1-open-questions.md, p1-closed-decisions.md | "fix" a deliberate shortcut, or add a band-aid |
| 5. Culture | What does good look like in this project? | p1-standing-instructions.md, project.toml [style], linters, the guidelines skills | write average code in its own style |
How to run it
Read only; change nothing.
- Name the scope: one feature (its work folder) or the whole codebase.
- For each layer, look at the files in the table and at a few real code files in the area
the work will touch. Grep before reading (
skills/context-budget/). - Grade each layer: COMPLETE (an agent could work without guessing), THIN (some decisions left open) or MISSING. A grade cites the file, or the absence of one.
- For every THIN or MISSING layer, list the silent fills: the two or three concrete decisions an agent would make on its own. Examples: "creates a second auth helper because nothing says one exists"; "returns success when one of three writes failed because no error contract says otherwise".
- Mark the most dangerous fill: the one hardest to undo later (a data model, a boundary, a public interface).
Verdict
- Delegate: every layer COMPLETE, or THIN only where a wrong guess is cheap to undo.
- Delegate with review: THIN layers whose fills are listed in the brief, so the reviewer checks exactly those decisions.
- Do not delegate yet: any MISSING layer whose most dangerous fill is hard to undo. Turn the
fills into questions for the founder (
skills/grilling/) or work forarchitect, then audit again.
Report
docs/work/<id>/spec-audit.md for a feature, docs/spec-audit-<date>.md for a codebase:
| Layer | Grade | Evidence | Silent fills |
then the verdict, the most dangerous fill, and the fixes in order of how much risk each removes for how little work. No score out of 100: the grades and the named fills are what the founder acts on.
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.

