verify-request
Skill16 starsChanged 37 days agoMITView on GitHub
Triage a request before any code is written — ground its intent, plane, risk class and approval needs, and return ready / needs_clarify / blocked. The intake stage (H1).
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- analyze-requirementsSkill
- be-fe-security-auditSkill
- commit-deploy-logSkill
- deep-researchSkill
- deploy-to-testSkill
- evidence-bundleSkill
- fanSkill
- fix-and-verifySkill
- impact-reviewSkill
- implement-changeSkill
- qa-gateSkill
- run-affected-testsSkill
- verify-implementationSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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 46
Before v1.6.0 the pipeline ran straight from a request into analysis.
≈ “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
verify-request
The intake node of the DAG (planning-light profile) — the first stage, and
the only one positioned to ask whether the request itself is sound.
Before v1.6.0 the pipeline ran straight from a request into analysis. A misread or under-specified request therefore produced a clean, well-reviewed, fully tested implementation of the wrong thing, and every later stage judged it against the same misreading, so nothing caught it. This stage exists for that failure and no other.
Feeds gate.analysis via gate_rules.intake_verdict_not_ready: pause in
contracts/workflow.yaml — a verdict other than ready pauses rather than
halts, because the fix is usually three answers from a human, not a rollback.
Runs on a deliberately cheap profile: intake fires on every request, and taxing the whole pipeline with the top planning model for a triage decision a small model answers well is the wrong trade.
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.