Skill Health Observer — Development agent for Claude Code
Analyze skill outcomes, score per-skill health, write SKILL_HEALTH.md.
How to install Skill Health Observer
Installs to ~/.claude/agents/scientiacapital-skills-skill-health-observer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ScientiaCapital/skills/HEAD/.claude/agents/skill-health-observer.md -o ~/.claude/agents/scientiacapital-skills-skill-health-observer.md Restart Claude Code, or start a new session, for it to be picked up.
What Skill Health Observer does
name: skill-health-observer description: "Analyze skill outcomes, score per-skill health, write SKILL_HEALTH.md. Haiku-powered, ~$0.02/run." model: haiku tools:
- Read
- Glob
- Grep
- Bash
- Write maxTurns: 8
Skill Health Observer: Outcome Analysis
You are the skill health observer for the **skills** project. Your job is to analyze outcome data from `~/.claude/skill-analytics/outcomes.jsonl` and produce a health report at `.claude/observers/SKILL_HEALTH.md`.
Data Source
Alternatives in Development
- Cs Guardian — Customer success partner for account health, churn risk, renewals, escalations, and QBRs 1.3k ★
- After Identifying Or Executing A Chain — findings.sh add chain " " --score \ --steps " step2 -> step3>" --mitre " " findings.sh update chain --status < 213 ★
- Product Owner Proxy — Define business intent as user stories with clear acceptance criteria and measurable outcomes 108 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Quick Edit
Fast haiku-powered agent for trivial single-file edits. Use for typo fixes, variable renames, small function a
Runtime Observer.Agent
Use when Architrave needs runtime/product truth: health, logs, versions, deployed digests, app launch, or drif
Hygiene Synthesizer
Combines all tool outputs and agent findings into unified health report. Generates architecture.md, calculates
Health Checker
Code health dashboard agent - structured 3-phase methodology (detect, measure, prescribe) with weighted 0-10 s
Automation Sentinel
Use this agent to monitor, analyze, and optimize the automation ecosystem (agents, commands, hooks). This is a
Git Forensics
Analyze git history for code health signals using bbu. Use when the user asks about hotspots, churn, temporal
Related Skills
Observer Daemon
Score Claude Code and Codex responses against local writing rules and record violations.
Contribution Dashboard
Read-only dashboard for the opensource-contributor state. Shows active run, score history, plateaued dimension
Verify Done
5pm ritual. Check today's outcomes, log what shipped, flag what slipped, write tomorrow's 3.