skill-inspect

Included with Lifetime

$97 forever

Deep analysis of a specific skill's observation history. Use when the user says "inspect skill", "analyze skill failures", "why is X skill failing", "skill inspection", "debug skill", or "what's wrong with the X skill".

Code Review

What this skill does


# Skill Inspection

Perform a deep analysis of a specific skill's usage history to identify failure patterns and improvement opportunities.

## Workflow

1. **Identify target skill** — Determine which skill to inspect from the user's request. If not specified, read `.claude/skill-evolution/observations.jsonl` and suggest skills with the lowest success rates. Ask the user which one to inspect.

2. **Load observation history** — Read all observations for the target skill from `.claude/skill-evolution/observations.jsonl`. If no observations exist, tell the user and suggest using the skill first.

3. **Timeline analysis** — Present observations chronologically:

```
## Observation Timeline: {skill-name}

| # | Date | Outcome | Corrections | Notes |
|---|------|---------|-------------|-------|
| 1 | 2026-03-10 | completed | 0 | Clean run |
| 2 | 2026-03-12 | partial | 2 | Missed edge case in validation |
| 3 | 2026-03-13 | failed | 0 | Wrong file pattern, had to restart |
| 4 | 2026-03-14 | partial | 1 | Better but still missed X |
```

4. **Failure pattern analysis** — Group failures and partial completions by category:

   - **Missing context** — Skill didn't have enough information to proceed correctly
   - **Wrong approach** — Skill used an incorrect strategy or pattern
   - **Edge case** — Skill failed on an unusual input or scenario
   - **Unclear instructions** — Skill instructions were ambiguous, leading to wrong interpretation
   - **Outdated assumptions** — Skill references patterns/files/APIs that have changed
   - **Scope mismatch** — Skill tried to do too much or too little

   For each category with failures, show:
   - Count of affected observations
   - Specific examples from the notes/errors fields
   - The likely root cause in the SKILL.md

5. **Version comparison** — If `.claude/skill-evolution/versions/{skill-name}/` contains previous versions, compare pre/post-amendment success rates:

```
## Amendment Impact

| Version | Period | Invocations | Success Rate | Change |
|---------|--------|-------------|--------------|--------|
| v1 (original) | Mar 1-10 | 5 | 40% | — |
| v2 (amended Mar 10) | Mar 10-15 | 7 | 71% | +31% |
```

6. **Diagnosis summary** — Provide a concise summary:
   - Top 1-3 failure patterns
   - Specific lines/sections in the SKILL.md that are likely responsible
   - Confidence level (high/medium/low) for each diagnosis

7. **Next step** — Ask: "Would you like me to propose amendments to fix these issues? (Use the `skill-amend` skill)"

Files: 1

Size: 2.7 KB

Complexity: 7/100

Category: Code Review

Source: https://github.com/franchiseai/claude-code-plugins/tree/main/plugins/skill-evolution/skills/skill-inspect

Related in Code Review

gstack

Included

Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)

Code Reviewscriptsfeatured

startup-due-diligence

Included

Legal due diligence review for seed-stage and Series A startups (US, Delaware C-Corp focus). Supports both investor and founder perspectives. Capabilities include: (1) Interactive document review and issue spotting; (2) Document request list generation; (3) Cap table and SAFE/convertible note analysis; (4) Red flag identification with severity ratings; (5) Diligence report generation. TRIGGERS: due diligence, DD, startup investment, cap table review, Series A, seed round, investor diligence, legal review startup, SAFE analysis, convertible note, 409A, founder vesting.

Code Reviewscripts

interview-master

Included

This skill should be used when the user asks to "generate interview questions", "prepare for interview", "optimize resume", "conduct mock interview", "analyze git commits for resume", "generate resume from code", "review my resume", or mentions interview preparation, career assistance, or extracting project experience from git history. Provides comprehensive interview and career development guidance for both job seekers and interviewers.

Code Reviewscripts

fix-issue

Included

Fixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to avoid recurrence. Use when debugging errors, resolving regressions, fixing bugs, or triaging issues.

Code Reviewscripts

sf-apex

Included

Generates and reviews Salesforce Apex code with 150-point scoring. TRIGGER when: user writes, reviews, or fixes Apex classes, triggers, test classes, batch/queueable/schedulable jobs, or touches .cls/.trigger files. DO NOT TRIGGER when: LWC JavaScript (use sf-lwc), Flow XML (use sf-flow), SOQL-only queries (use sf-soql), or non-Salesforce code.

Code Reviewscripts

swift-development

Included

Comprehensive Swift development for building, testing, and deploying iOS/macOS applications. Use when Claude needs to: (1) Build Swift packages or Xcode projects from command line, (2) Run tests with XCTest or Swift Testing framework, (3) Manage iOS simulators with simctl, (4) Handle code signing, provisioning profiles, and app distribution, (5) Format or lint Swift code with SwiftFormat/SwiftLint, (6) Work with Swift Package Manager (SPM), (7) Implement Swift 6 concurrency patterns (async/await, actors, Sendable), (8) Create SwiftUI views with MVVM architecture, (9) Set up Core Data or SwiftData persistence, or any other Swift/iOS/macOS development tasks.

Code Reviewscripts