Context Health Check — Development skill for Claude Code
Run a structured health check on the current conversation context and report its quality score with actionable recommendations.
How to install Context Health Check
Installs to ~/.claude/skills/danielrosehill-claude-rudder-context-health-check/SKILL.md
mkdir -p ~/.claude/skills/danielrosehill-claude-rudder-context-health-check && curl -fsSL https://raw.githubusercontent.com/danielrosehill/Claude-Rudder/HEAD/commands/context-health-check.md -o ~/.claude/skills/danielrosehill-claude-rudder-context-health-check/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Context Health Check does
description: Run a structured health check on the current conversation context and report its quality score with actionable recommendations allowed-tools: []
Run a structured health check on the current conversation context.
Analyse the full conversation history and produce a brief report covering the following dimensions. Score each out of 5 and give one line of commentary.
Dimensions
**Relevance** (5 = all context is still directly useful, 1 = most context is stale or off-topic)
Alternatives in Development
- Swot Analysis — SWOT analysis with actionable recommendations per quadrant 7.8k ★
- Bench Capture — Score the 2 bench variant folders for one size (build/acceptance/regression/conventions/capture + rubric + cro 85 ★
- Crusts — Run the CRUSTS context window analyzer and give me actionable advice 83 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Sp Health
Run knowledge base health check and auto-fix actionable issues. Triggers: /sp-context:sp-health, 'check knowle
Jobs Eval
Scoring-quality check. Build a small golden set of your own vacancies labelled fits / doesn't-fit, score them
Team Status
Get comprehensive status report for the current agent team. Shows phase progress, findings, and recommendation
Xforge Score
Run Xinu's ClaudeMD Fix — read-only health check. Grade, 8-criteria breakdown, line-by-line classification. Ch
Claude Healthline
Never-blank Rust status line for Claude Code that tells you when your agent is going wrong: agent-health score
Context Health Bar
A Chrome extension that visualizes Claude context health as a compact orb and helps you hand off long chats to
Related Agents
Config Reviewer
Adversarial reviewer that audits .claude/ configurations for bloat, redundancy, LLM capability duplication, an
Keepr
Use this agent to evaluate PR review comments and classify them into actionable recommendations. keepr (keeper
Hygiene Synthesizer
Combines all tool outputs and agent findings into unified health report. Generates architecture.md, calculates