archobs
Run architecture observability analysis on a git repository to measure coupling, boundary health, risk hotspots, and temporal drift. Use when you need empirical data about code structure before making architecture or refactoring decisions, or to validate that changes improved boundary discipline. NOT for choosing architecture patterns (use architecture); NOT for choosing code patterns (use design); NOT for adversarial code review (use review).
npx skills add majiayu000/claude-skill-registry --skill archobs --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Archobs (Architecture Observability) ## Overview Measure the actual coupling structure of a codebase using three signals: git co-change history, import/dependency edges, and semantic similarity. These signals are fused into a weighted graph, clustered into logical subsystems, and scored for boundary health, risk, and temporal stability. Use this skill to ground architecture and refactoring decisions in empirical data rather than intuition. The output feeds directly into `architecture`, `design`, `plan`, and `review` as evidence. Success looks like: numbered risk hotspots, measured boundary leakage, and prioritized suggestions with concrete scope. ## Chooser (Analysis Mode) - **Full report** (default): Run the complete pipeline and generate an HTML report with suggestions. Use for initial analysis or periodic health checks. - **Targeted stage**: Run a single pipeline stage (inventory, git, deps, embed, build-graph, cluster) when you only need one artifact updated. - **Suggestion loop**: Run analysis, apply one suggestion, re-analyze, repeat until convergence. Use for automated refactoring passes. - **Regression check**: Compare current metrics against a previous run. Use in `finis
- Overview
- Chooser (Analysis Mode)
- Workflow
- Combined Archobs + Trajectory Workflow
- Clarifying Questions
- Guardrails
- Map To Existing Skills
- References
- Output Template
archobs init --repo <path> --out .archobs for entry in .archobs/ .codanna/ .codannaignore .fastembed_cache lib/; do grep -qxF "$entry" .gitignore 2>/dev/null || echo "$entry" >> .gitignore done archobs report --repo <path> --out .archobs --suggestions-provider rules archobs show risks --top 10 --format json archobs show clusters --sort leakage --format json archobs show drift --format json archobs show summary --format json archobs show velocity --window 30 --compare --format json
What does the archobs skill do?
Run architecture observability analysis on a git repository to measure coupling, boundary health, risk hotspots, and temporal drift. Use when you need empirical data about code structure before making architecture or refactoring decisions, or to validate that changes improved boundary discipline. NOT for choosing architecture patterns (use architecture); NOT for choosing code patterns (use design); NOT for adversarial code review (use review).
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill archobs --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.