hyhmrright/logic-lens/logic-health
Claude Code and agent skill by hyhmrright/logic-lens
- community
Checking that the SKILL.md file is still in the repository.
Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic patterns. Trigger when the user requests a health view — "audit the whole codebase", "health check", "health overview", "logic health overview", "audit src/", "audit auth and payments modules", "where should I focus testing", "onboarding review", "logic overview before we ship", "give me a health overview of this module". SCOPE RULE: prefer multi-file; also trigger for a single…
Install
npx vskill@latest install hyhmrright/logic-lens/logic-healthSKILL.md
The same SKILL.md was published earlier as hyhmrright/logic-lens/logic-health.
Logic-Lens — Logic Health
Setup
Use lazy loading per ../_shared/common.md §13:
- Read
../_shared/common.mdonly for language, Iron Law, Logic Score, scope routing, Remedy discipline, config fields, and loading budget. - Read only the relevant step in
logic-health-guide.mdas you reach it. - Load
../_shared/logic-risks.md,../_shared/semiformal-guide.md,../_shared/semiformal-checklist.md,../_shared/report-template.md, and../logic-review/logic-review-guide.mdon demand when the current module trace needs them.
Process
Step 0. Language + scope routing. Detect language per common.md §1. Proceed for multi-file scopes and for single-module scopes when the user explicitly uses "health check", "health overview", or "logic health". If scope is one file and none of those health phrases appear, switch to logic-review.
Step 1. Enumerate modules and plan the sweep (guide Step 1) — prioritize public API surfaces, recently changed files, and user-flagged modules. Read .logic-lens.yaml only for ignore:, focus:, disable:, severity:, custom_risks, and trace.* fields. For broad scopes, build a ranked worklist before opening files.
Step 2. Run focused logic-review per module (guide Step 2) — apply Premises → Trace → Divergence on public-facing functions; skip internal helpers unless a trace leads into them. Apply the per-module function budget from guide Step 2 (small/medium/large line-count tiers) — do not trace all functions in large modules.
Step 3. Record findings per module (guide Step 3) — tag module, L-code, severity.
Step 4. Aggregate findings (guide Step 4) — counts by severity and by L-code; cross-reference modules.
Step 5. Compute scores (guide Step 5) — per-module Logic Score via the standard formula; overall score is the line-weighted average (per common.md §6).
Step 6. Identify systemic patterns (guide Step 6) — L-codes appearing in ≥ 3 modules or ≥ 30% of scanned modules (whichever threshold is lower) indicate codebase-wide habits; architectural enablers (heavy global state → L7; deep callee chains → L6) get explicit mention.
Step 7. Output the Health Report (guide Step 7) — standard header; Findings; Summary; then Module Breakdown, Systemic Patterns, and Recommended Priority Order (top 3–5) appended after Summary. Localize all headers if the user wrote in Chinese.
Mode line in report: Logic Health (Chinese: 逻辑体检).
Health-specific additions (append after the standard Summary):
Localize column and section headers when the user wrote in Chinese (e.g., 模块分布, 系统性模式, 优先级建议).
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/logic-health/SKILL.md
Popularity
- Repository stars
- 25
- Repository forks
- 2
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 4 Nov 2026, 15 days ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/hyhmrright/logic-lens/logic-health)