# context-layer-health-check

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 It triages missed entries, conflicting claims, and outdated priorities.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 150 installs · ★ 101 repo stars
- Author: PostHog
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/PostHog/ai-plugin/tree/HEAD/skills/context-layer-health-check/SKILL.md
- Updated: 2026-10-24
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/context-layer-health-check

## What it 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.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add PostHog/ai-plugin --skill context-layer-health-check -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/context-layer-health-check/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/context-layer-health-check/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add PostHog/ai-plugin --skill context-layer-health-check -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/context-layer-health-check/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add PostHog/ai-plugin --skill context-layer-health-check -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/context-layer-health-check/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install PostHog/ai-plugin skills/context-layer-health-check
```

2. **Manually: put the files in place**
- File: `.github/skills/context-layer-health-check/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add PostHog/ai-plugin --skill context-layer-health-check -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/PostHog/ai-plugin --path skills/context-layer-health-check
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/context-layer-health-check/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add PostHog/ai-plugin --skill context-layer-health-check -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/PostHog/ai-plugin/tree/HEAD/skills/context-layer-health-check/SKILL.md

## When to use it
- 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
- 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.

## Similar
- [wiki-health](https://affpapa.org/en/nevibecode/skills/wiki-health.md) — skill · ★ 101 repo stars
- [intent-layer](https://affpapa.org/en/nevibecode/skills/intent-layer.md) — skill · 639 installs
- [qi-layer](https://affpapa.org/en/nevibecode/skills/haowjy-qi-layer.md) — skill · 441 installs
- [bmad-project-context](https://affpapa.org/en/nevibecode/skills/bmad-project-context.md) — skill · 17200 installs
- [mini-context-graph](https://affpapa.org/en/nevibecode/skills/mini-context-graph.md) — skill · 72 installs
- [ktx-ai-data-agents-context-layer](https://affpapa.org/en/nevibecode/skills/ktx-ai-data-agents-context-layer.md) — skill · 157 installs

From the same set: [posthog/ai-plugin](https://affpapa.org/en/nevibecode/by/posthog/ai-plugin.md) — 82 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
