the-own-lab/clarify
skills/clarify/SKILL.md
Reverse-question the user until the feature intent is unambiguous. Drives brief Open Questions to empty before downstream skills run.
tools
Updated Apr 22, 2026
$ install --global
skillsauthnpx skillsauth add the-own-lab/Claude-company-of-one clarifyInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 22, 2026, 11:15 AM145.6s1 file scanned
SKILL.md
- name:
- clarify
- description:
- Reverse-question the user until the feature intent is unambiguous. Drives brief Open Questions to empty before downstream skills run.
clarify
Purpose
Resolve ambiguity in the current contract before any spec / code is produced. Ask the user specific, answerable questions; record answers into the brief.
Inputs
BRIEF.md## Open Questions,## Current Contract,## Assumptions.- User's natural-language intent for this run.
Outputs
## Open Questionsreduced to empty (or only items explicitly deferred).## Assumptionsexpanded with each confirmed decision.## Current Contractrewritten if the clarification changed scope.
Procedure
- List every ambiguity in
## Current Contractor## Open Questions. - Group related questions; ask at most 5 at a time.
- For each question, offer 2–3 concrete options (A / B / C) rather than open-ended prose. This forces a decision.
- After user answers, write each decision as one bullet under
## Assumptionsand remove the question from## Open Questions. - If an answer changes the scope, rewrite
## Current Contractand highlight the delta.
Failure modes
- User defers: keep the question in
## Open Questionsand addDEFERRED — {reason}. Do not let/deventer Execute with a deferred question on a core behavior. - User answers with "do what you think": refuse; propose 2–3 concrete options and ask again. ADR-001 D3's anti-self-deception applies to design too.
- More than 10 questions surface: the feature is too big; recommend splitting
before
/thinkcontinues.
Does not do
- Does not research external facts (that is
research). - Does not write the spec artifact (that is
spec-writing). - Does not edit code.
Related Skills
the-own-lab/write-brief
documentation
VerifiedTrustedCommunity
Update BRIEF.md sections during a command run. Any skill that produces a brief-persisted artifact calls this to write it back.
SKILL.mdUpdated Apr 22, 2026
the-own-lab/verify
development
VerifiedTrustedCommunity
Post-code check: run tests + confirm TODO acceptance items map to passing tests; applies a security lens but is not a separate scan.
SKILL.mdUpdated Apr 22, 2026
the-own-lab/update-docs
documentation
VerifiedTrustedCommunity
Command post-step: write CHANGELOG + TODO once per command run. One call, not per-skill doc writes.
SKILL.mdUpdated Apr 22, 2026
the-own-lab/spec-writing
content-media
VerifiedTrustedCommunity
Author REQUIREMENTS.md + DESIGN.md + TODO.md for a feature. The three files are one contract; they ship together.
SKILL.mdUpdated Apr 22, 2026