spec-first
Skill0 starsChanged 13 days agoMITView on GitHub
Turn a feature request into testable acceptance criteria and a small implementation plan before editing. Use when requirements are ambiguous, a task spans several files, or a change may affect existing behavior.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- zzusp/doc-first-devtheir own version, first seen Nov 8, 2026
- vindreshsingh/engineering-skillstheir own version, first seen Oct 20, 2026
- omega1119/groundworktheir own version, first seen Oct 20, 2026
- soilSpoon/skillstheir own version, first seen Oct 20, 2026
- Kylianmgt/spec-first-skillstheir own version, first seen Oct 17, 2026
- marcin-urbanski/claude-skillstheir own version, first seen Oct 17, 2026
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- rohunvora/my-claude-skills★ 6same name
- zzusp/doc-first-dev★ 6same name
- genfeedai/genfeed.ai★ 4same name
- MissingPackage/nightshift★ 3same name
- 223mle/skills★ 1same name
- soilSpoon/skills★ 1same name
- Jinbae10/skills★ 0same name
- Kylianmgt/spec-first-skills★ 0same name
- marcin-urbanski/claude-skills★ 0same name
- omega1119/groundwork★ 0same name
2 more not listed
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 repository25 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-skill-auditSkill
- api-contract-checkSkill
- build-rescueSkill
- change-narrativeSkill
- context-handoffSkill
- data-quality-gateSkill
- dataset-workshopSkill
- dependency-careSkill
- docs-syncSkill
- experiment-ledgerSkill
- failure-forensicsSkill
- model-diff-reviewSkill
- model-eval-designSkill
- multi-agent-crosscheckSkill
- parallel-task-designSkill
- performance-proofSkill
- release-readinessSkill
- repo-scoutSkill
- research-evidence-mapSkill
- review-lensSkill
- safe-migrationSkill
- security-surfaceSkill
- sql-integrity-checkSkill
- test-driven-changeSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
3
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 22
Use a short brief:
- Distinctive: line 31
Ask a focused question only when a missing decision blocks safe progress.
- Distinctive: line 32
Do not silently broaden scope or redesign unrelated systems.
“Common” is measured: kept by at least 6 in 10 of the 9 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
Spec First
Outcome
A compact implementation brief that makes the requested behavior observable and defines what must remain unchanged.
Procedure
- Restate the requested outcome in plain language. Separate the user's goal from any proposed implementation.
- Inspect the relevant code and docs before proposing changes. Reuse repository conventions where possible.
- List acceptance criteria that can be checked through tests, commands, UI behavior, logs, or documented output.
- Record non-goals and compatibility constraints. Call out assumptions that would materially change the design.
- Identify the smallest safe change set. Group files into implementation, tests, and docs.
- Define verification in advance: the targeted test, broader regression checks, and any manual check that cannot be automated.
- For a large task, split work into independent slices with a clear integration point. Do not create artificial subtasks for a trivial change.
Deliverable
Use a short brief:
- Goal
- Acceptance criteria
- Non-goals
- Key files and design choice
- Risks / assumptions
- Verification plan
Boundaries
- Ask a focused question only when a missing decision blocks safe progress. Otherwise state a reversible assumption and continue.
- Do not silently broaden scope or redesign unrelated systems.
- Planning is not permission to deploy, spend money, contact people, or make destructive changes.
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.