the-own-lab/research
skills/research/SKILL.md
External-knowledge gathering step — Web Search + Context7 docs lookup. Validates that the spec/plan reflects current library reality.
development
Updated Apr 22, 2026
$ install --global
skillsauthnpx skillsauth add the-own-lab/Claude-company-of-one researchInstall 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, 11:16 AM147.6s1 file scanned
SKILL.md
- name:
- research
- description:
- External-knowledge gathering step — Web Search + Context7 docs lookup. Validates that the spec/plan reflects current library reality.
research
Purpose
Gather up-to-date external knowledge needed for the current /think or /dev run.
Uses Web Search for ecosystem context and Context7 MCP for library/API docs, since
training-data cutoffs miss recent breaking changes.
Inputs
BRIEF.md## Feature+## Current Contract.## Open Questionsthat are knowledge gaps (not design questions — those go toclarify).- Library / framework names named in the brief or spec.
Outputs
- Research notes appended to
BRIEF.mdas sub-bullets under## Assumptionsand## Open Questions. Each citation includes a URL orcontext7:<library-id>reference.
Procedure
- Identify unknowns with external answers: library version, API shape, deprecation, security advisory, ecosystem norm.
- For each library:
mcp__plugin_context7_context7__resolve-library-id→mcp__plugin_context7_context7__query-docs. Prefer this over Web Search for API docs. - For ecosystem norms / comparisons / recent incidents: Web Search with narrow queries.
- Record each finding as one bullet:
{claim} — {source}. - If research contradicts an assumption already in the brief, move that assumption
from
## Assumptionsto## Open Questionsand flag it forclarify.
Failure modes
- Context7 has no entry for the library → fall back to official docs via Web Search,
but never fabricate a version or API signature. Record
unknown — needs verificationif still uncertain. - Context7 MCP tool is unavailable (plugin not installed, MCP offline) → record one
bullet
context7 unavailable — used web search fallbackunder## Assumptions, then proceed with Web Search. Do NOT block the run on missing tooling. - A finding implies the spec is wrong → do not silently patch the spec; surface it
and let
clarifyorspec-writingupdate the spec.
Does not do
- Does not write code.
- Does not read MEMORY.md (use the brief's
## Relevant Memoryinstead). - Does not answer design-intent questions; those belong to
clarify.
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