requirement-clarifier
Skill0 starsChanged 49 days agoMITView on GitHub
Clarify an ambiguous build request into a testable scope when goals, stakeholders, or acceptance criteria are unclear.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- Laffey-82/cn-agent-skillstheir own version, first seen Aug 29, 2026
- kj648/requirement-clarifiertheir own version, first seen Aug 27, 2026
- yingzhengzhang06-sys/requirement-clarifiertheir own version, first seen Jun 23, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- kj648/requirement-clarifier★ 2same name
- Laffey-82/cn-agent-skills★ 1same name
- yingzhengzhang06-sys/requirement-clarifier★ 1same 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 repository9 other files it gives its agents.
- content-qaSkill
- eval-engineering-liteSkill
- evidence-contentSkill
- failure-analyzerSkill
- faq-builderSkill
- meeting-to-actionsSkill
- project-handoffSkill
- research-synthesizerSkill
- workflow-plannerSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Use before implementation when the input leaves ownership, success, data source, or irreversible actions ambiguous.
- Distinctive: line 29
Ask only for decisions that materially change scope, risk or external state.
- Very specific: line 34
If the owner of a business rule is unknown, mark BLOCKED_OWNER_DECISION.
- Very specific: line 42
Run python3 tests/validate.py from the repository root to check this skill's contract and example provenance.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Requirement Clarifier
Purpose
Turn a vague request into a minimal, falsifiable delivery contract without making up business rules.
When to Use
Use before implementation when the input leaves ownership, success, data source, or irreversible actions ambiguous.
Inputs
request, known_constraints[], stakeholders[], optional existing_artifacts[] and decision_deadline.
Outputs
goal, in_scope[], out_of_scope[], acceptance_criteria[], assumptions[], open_decisions[], evidence_needed[].
Workflow
- Restate the user's desired outcome in one sentence and separate outcome from requested implementation.
- Extract hard constraints and existing evidence verbatim; label anything inferred as an assumption.
- Draft at most three acceptance checks that a reviewer can reproduce.
- Ask only for decisions that materially change scope, risk or external state; continue with reversible work meanwhile.
- Return the scope contract and mark each open decision with its owner and blocking effect.
Failure Handling
If the owner of a business rule is unknown, mark BLOCKED_OWNER_DECISION; do not invent a default. If source evidence is missing, mark the criterion provisional.
Example
synthetic_unverified: “Build a sample FAQ” becomes five cited answers plus a no-answer path; the approved source set remains an open decision.
Tests
Run python3 tests/validate.py from the repository root to check this skill's contract and example provenance. This is a structural test, not model-quality evidence.
Limitations
This skill cannot substitute for customer sign-off or legal/product ownership.
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.