From act101
Use when asked about code health, quality trends, what's getting worse, or for a periodic quality check. Depth 1 — fast, trend-aware. Produces a health snapshot with hotspots, cohesion issues, test gaps, and trend comparison if prior runs exist. Replaces the codebase-analysis skill.
npx claudepluginhub act101-ai/act101 --plugin act101This skill uses the workspace's default tool permissions.
**Depth:** Level 1 (Explore).
Assesses codebase health for legacy projects by analyzing complexity, dependencies, dead code, tech debt, and git hotspots. Produces per-module health scores and prioritized rescue plans.
Runs static tools like tsc, semgrep, knip to analyze codebase for dead code, test quality, duplicates, complexity, security, architecture. Full TS/JS support; limited Python/Go/Rust. Stores structured reports.
Generates codebase health dashboard scoring PR quality, architecture, tech debt, and test quality in a single pass from twelve engineering books. For overall assessments like 'how healthy is this codebase?' or pre-release reports.
Share bugs, ideas, or general feedback.
Depth: Level 1 (Explore).
See ../analysis-protocol/references/protocol.md for: artifact directory structure,
the investigation loop, depth levels, summary format, token budget rules, and project
map structure. Read that document before proceeding.
Dispatch all available tools in a single parallel batch.
Each subagent runs one tool, saves raw JSON to raw/<tool-name>.json, returns a
structured summary.
Must-have tools:
| Tool | Purpose | MCP call |
|---|---|---|
analyze_hotspots | Complexity ranking (H1) | analyze_hotspots |
analyze_patterns | Tier 1 structural smells | analyze_patterns (use --tier fast) |
If neither must-have tool is available, report that and stop.
Extended tools (use if available, skip and note in manifest if not):
| Tool | Purpose | MCP call |
|---|---|---|
analyze_coupling | Instability overview | analyze_coupling |
analyze_cohesion | Module cohesion (H2) | analyze_cohesion |
analyze_test_gaps | Test coverage gaps (R5) | analyze_test_gaps |
analyze_inconsistencies | Sibling pattern divergence (H5) | analyze_inconsistencies |
From summaries, identify the top 3-5 findings and run one targeted follow-up each:
skeleton to characterize what's wrongKeep follow-ups to one round — this is a health check, not a full audit.
Check docs/act/ for a prior Health Check run: look for a manifest.json with
"skill": "health-check". If found:
raw/hotspots.json and raw/coupling.jsonraw/test_gaps.json exists in both runs)Verdict must reflect the trend: Improving / Stable / Degrading.
# Health Check: <project name>
## Health Summary
Verdict: **Improving** / **Stable** / **Degrading**.
One-paragraph assessment.
## Top Hotspots
Ranked list with skeleton context from follow-up. Severity and recommended fix.
Per-hotspot: file path, complexity score, what skeleton revealed, recommended action.
## Cohesion Issues
Low-cohesion modules with split recommendations.
Per-issue: module, cohesion score, suggested split boundary.
## Pattern Inconsistencies
Sibling files that diverge from group conventions.
Per-divergence: what's expected in the group, what's different in this file.
## Test Gaps
Untested files ranked by risk (coupling × blast radius if available, else coupling alone).
Per-gap: file path, risk factors, suggested test type.
## Trend
(Present only if prior run data exists)
| Metric | Previous | Current | Change |
|--------|----------|---------|--------|
| Top hotspot score | N | N | ↑/↓/= |
| Hotspot count (top 10) | N | N | ↑/↓/= |
| Mean instability | N | N | ↑/↓/= |
| Test gap count | N | N | ↑/↓/= |
What improved, what degraded, what's new since last run.
## Suggested Fixes
Prioritized list of specific act MCP tool calls or skills to run.
Updates the "Health Snapshot" section only. Appends to the Analysis History table.