Context Layer Health Check

From the author

Reviews context wiki quality after deterministic consolidation. Use when recent wiki-miss entries, contradictory or unsupported claims, stale priorities, near-duplicate subjects, or concepts without an owning page need semantic triage.

— the description by PostHog

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The context-layer-health-check skill provides a structured approach to auditing wiki content following deterministic consolidation. It uses recent wiki-miss entries from git logs as a primary signal to identify issues such as contradictory claims, stale priorities, near-duplicate subjects, and orphaned concepts. The process involves reviewing evidence, resolving supported conflicts, marking unresolved disagreements, and performing final linting to maintain the integrity of the knowledge base.

What it does

Analyzes recent wiki-miss entries from git logs to prioritize review tasks.
Identifies contradictory claims and unsupported conclusions within the wiki.
Detects near-duplicate subjects and concepts lacking an owning page.
Flags stale priorities that automated reports might overlook.
Resolves supported issues and marks unresolved conflicts with specific markers.
Executes linting scripts to verify the final state of the documentation.

When to use it

When you need to perform semantic triage on a wiki after consolidation.
When there are concerns about contradictory or unsupported information in the knowledge base.
When you need to identify and clean up near-duplicate subjects or orphaned concepts.
When you need to address stale priorities that are not captured by standard reports.

Advantages

Uses actual activity logs to drive the audit process.
Provides a clear mechanism for handling unresolved conflicts.
Integrates automated linting to ensure structural consistency.

Usage examples

“Run the context layer health check on the current repository.”: The agent will parse git logs for wiki-miss entries, review the wiki for semantic inconsistencies, resolve supported issues, and run the required linting scripts.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/posthog/context-layer-health-check/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip context-layer-health-check.zip -d .agents/skills

Documentation by PostHog

Read recent wiki-miss: lines from git log --merges and use them as the priority signal. Review for contradictory active claims, unsupported conclusions, repeated low-value activity, stale priorities the report cannot detect, near-duplicate subjects, concepts without an owning page, and sources worth backfilling.

Fix what evidence supports. Leave unresolved conflicts as **Disagreement:** markers and record remaining work in the run summary. Finish with scripts/lint and scripts/lint --report.

Do not edit AGENTS.md, CLAUDE.md, generated indexes, scripts/, or Space paths. The server owns wiki structure and tooling.

Files

ATTRIBUTION.mdAdded by AutoGineer871 B
LICENSELicence file added by AutoGineer1.0 KiB
SKILL.md958 B

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Claude API
AnthropicOfficial
Comprehensive reference for integrating Anthropic's Claude API, SDKs, and Managed Agents into your applications.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Medium riskHas scriptsGitHub stars of the source repository188.6k
Transformers
K-Dense· Community
Integrate Hugging Face Transformers for model loading, inference, and fine-tuning across NLP, vision, and audio tasks.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskGitHub stars of the source repository56.4k
Open Notebook
K-Dense· Community
Integrate with the self-hosted Open Notebook platform to automate research ingestion, context-aware chat, and AI-driven analysis.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository56.4k
Vision Sft
Seth Hobson· Community
A structured workflow for supervised fine-tuning of vision-language models, focusing on adapter configuration and silent failure prevention.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k
LLM Evaluation
Seth Hobson· Community
A comprehensive framework for evaluating LLM application performance using automated metrics, human feedback, and LLM-as-a-judge techniques.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k
Lora Qlora Recipes
Seth Hobson· Community
Provides configuration recipes and best-practice hyperparameters for LoRA and QLoRA supervised fine-tuning.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k