requirements-distiller
Skill7 starsChanged 6 months agoMITView on GitHub
Use when turning ambiguous requests, source material, CONOPS notes, or stakeholder intent into singular, testable, traceable requirements.
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- conops-builderSkill
- decision-analysisSkill
- integration-plannerSkill
- requirements-auditorSkill
- technical-assessment-loopSkill
- validation-plannerSkill
- verification-plannerSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
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
- Distinctive: line 8
Use this skill to turn messy intent into testable obligations without smuggling in design.
- Distinctive: line 13
Do not convert goals or objectives into requirements until the obligation is specific, necessary, and testable.
- Distinctive: line 14
Write each requirement as one obligation with stable subject, required behavior, boundary/condition, and acceptance signal.
- Distinctive: line 15
Keep implementation choices deferred unless the user or source makes them constraints.
- Distinctive: line 16
Add owner/approver, trace source, rationale, acceptance criteria, verification method, and evidence artifact for each requirement.
- Very specific: line 23
Start with references/source-grounding.md, then inspect Section 4.2 pages extraction/pages/page_064.md through extraction/pages/page_068.md …
≈ “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
Requirements Distiller
Use this skill to turn messy intent into testable obligations without smuggling in design.
Workflow
- Classify input into: broad goals, measurable objectives, requirements, constraints, assumptions, implementation choices, and open questions.
- Do not convert goals or objectives into requirements until the obligation is specific, necessary, and testable.
- Write each requirement as one obligation with stable subject, required behavior, boundary/condition, and acceptance signal.
- Keep implementation choices deferred unless the user or source makes them constraints.
- Add owner/approver, trace source, rationale, acceptance criteria, verification method, and evidence artifact for each requirement.
- Mark assumptions with confirmation path and deadline when they affect scope or acceptance.
- Output a requirements matrix plus a deferred-design list and open-question list.
- Send high-risk or ambiguous requirements to
requirements-auditorbefore coding.
Source grounding
Start with references/source-grounding.md, then inspect Section 4.2 pages extraction/pages/page_064.md through extraction/pages/page_068.md and Appendix C pages extraction/pages/page_207.md through extraction/pages/page_209.md before making requirement-writing claims.
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.