context-layer-health-check — Claude Code skill: wiki review
The context-layer-health-check Claude Code skill checks a context wiki after changes are consolidated. It triages missed entries, conflicting claims, and outdated priorities.
no license 150 installs ★ 101 updated 2026-10-24
npx skills add PostHog/ai-plugin --skill context-layer-health-check -a claude-codeWhat context-layer-health-check does
The skill audits a context wiki after changes have been consolidated. It reads recent wiki-miss: entries from git log --merges to guide the review, then looks for conflicting claims, conclusions without evidence, repeated low-value activity, stale priorities, overlapping subjects, and concepts that lack a page of their own.
It changes content only where evidence supports a fix. Unresolved conflicts get a **Disagreement:** marker, and remaining work goes into the run summary. The final checks are scripts/lint and scripts/lint --report. The skill leaves AGENTS.md, CLAUDE.md, generated indexes, scripts/, and Space paths untouched; the server manages wiki structure and tooling.
What it helps with
- spot conflicting claims in a context wiki
- find conclusions without supporting evidence
- flag outdated priorities and overlapping subjects
- identify concepts that lack an owning page
Example prompts for the agent
- Review the context wiki after the latest changes were consolidated.
- Triage recent wiki misses and find conflicting claims.
- Check for outdated priorities and topics without their own pages.
How to install context-layer-health-check
1Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill context-layer-health-check -a claude-code2Manually: put the files in place
~/.claude/skills/context-layer-health-check/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/context-layer-health-check/
1Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill context-layer-health-check -a codex2Manually: put the files in place
.agents/skills/context-layer-health-check/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill context-layer-health-check -a cursor2Manually: put the files in place
.cursor/skills/context-layer-health-check/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install PostHog/ai-plugin skills/context-layer-health-check2Manually: put the files in place
.github/skills/context-layer-health-check/SKILL.md1Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill context-layer-health-check -a gemini-cli2Platform CLI
gemini skills install https://github.com/PostHog/ai-plugin --path skills/context-layer-health-checkManually: put the files in place
.devin/skills/context-layer-health-check/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill context-layer-health-check -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about context-layer-health-check
How do I install context-layer-health-check in Claude Code?
Run npx skills add PostHog/ai-plugin --skill context-layer-health-check -a claude-code. The skill file is at ~/.claude/skills/context-layer-health-check/SKILL.md.
What does context-layer-health-check do?
It reviews a context wiki after consolidation, looking for contradictions, unsupported conclusions, stale priorities, and concepts without their own pages. It finishes by running scripts/lint and scripts/lint --report.
Which files does context-layer-health-check leave unchanged?
It does not edit AGENTS.md, CLAUDE.md, generated indexes, scripts/, or Space paths. The server owns the wiki structure and its tooling.