the-own-lab/spec-writing
skills/spec-writing/SKILL.md
Author REQUIREMENTS.md + DESIGN.md + TODO.md for a feature. The three files are one contract; they ship together.
content-media
Updated Apr 22, 2026
$ install --global
skillsauthnpx skillsauth add the-own-lab/Claude-company-of-one spec-writingInstall 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, 11:17 AM141.5s1 file scanned
SKILL.md
- name:
- spec-writing
- description:
- Author REQUIREMENTS.md + DESIGN.md + TODO.md for a feature. The three files are one contract; they ship together.
spec-writing
Purpose
Produce the three-file feature spec under docs/projects/<project>/specs/YYYY-MM-DD-<slug>/.
REQUIREMENTS defines acceptance, DESIGN defines approach, TODO defines executable
checklist. They are a single contract.
Inputs
BRIEF.md## Current Contract+## Assumptions.- Outputs from
research(validated library facts) andclarify(resolved decisions). - Existing spec in the same directory, if this is a revision.
Outputs
docs/projects/<project>/specs/YYYY-MM-DD-<verb>-<slug>/REQUIREMENTS.md.../DESIGN.md(with Non-Goals and Alternatives Considered sections — mandatory).../TODO.md(checkbox list, one per acceptance criterion or design step)
Update BRIEF.md ## Active Specs with the three paths.
Procedure
- Compute spec directory name:
<today-YYYY-MM-DD>-<imperative-verb>-<slug>(e.g.,2026-04-21-add-spec-writing-skill). - REQUIREMENTS.md — write numbered REQ-N items, each with an acceptance criterion
testable in
verify. One behavior per REQ. - DESIGN.md — Problem / Solution / Non-Goals / Alternatives Considered / Risks. Non-Goals is mandatory; empty Non-Goals means the design wasn't thought through.
- TODO.md — one checkbox per REQ acceptance and per DESIGN deliverable. Checkboxes
are what
update-docsticks post-execution. - Cross-reference: every REQ appears in TODO; every DESIGN step appears in TODO.
Failure modes
- REQ without an acceptance criterion → reject; rewrite.
- DESIGN without Non-Goals → reject; Non-Goals is what prevents scope creep.
- TODO has items not traceable to REQ or DESIGN → reject; either drop them or raise a new REQ.
- More than ~10 REQs → the feature is too big; split before continuing.
Does not do
- Does not write ADRs (that is
adr-writing). - Does not write code or tests.
- Does not edit CHANGELOG (that is
update-docs). - Does not auto-escalate to reviewer agent (
/thinknever auto-escalates, ADR-001 D4).
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-conformance
testing
VerifiedTrustedCommunity
/review Layer 1 auditor + /think self-review. Three contexts: think-self-review, review-spec, review-implementation. Also judges reconstruction drills.
SKILL.mdUpdated Apr 22, 2026