identify
Identify friction points, bottlenecks, bugs, and technical debt. Use for audits, debugging sessions, when something feels wrong, or before major work to surface hidden issues. This is the second system in the 5-system framework.
Best use case
identify is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Identify friction points, bottlenecks, bugs, and technical debt. Use for audits, debugging sessions, when something feels wrong, or before major work to surface hidden issues. This is the second system in the 5-system framework.
Teams using identify should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/2-identify/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How identify Compares
| Feature / Agent | identify | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Identify friction points, bottlenecks, bugs, and technical debt. Use for audits, debugging sessions, when something feels wrong, or before major work to surface hidden issues. This is the second system in the 5-system framework.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Identity System (Detection) > **Purpose:** Surface problems, friction, and bottlenecks before they compound. > **When to trigger:** Audits, debugging, pre-work analysis, or when something feels off. ## Detection Categories ### 1. Code Health Run these checks: - Type errors: `npx tsc --noEmit` - Build errors: `npm run build` - Lint issues: Check for warnings - Unused imports/variables - Circular dependencies ### 2. Performance Issues Look for: - Slow database queries (check Supabase logs) - Large bundle sizes - Unnecessary re-renders - N+1 query patterns - Missing indexes ### 3. User Experience Friction Identify: - Error states not handled gracefully - Loading states missing - Confusing user flows - Edge cases not covered - Poor error messages ### 4. Architecture Debt Spot: - Duplicated logic across files - Inconsistent patterns - Missing or premature abstractions - Tightly coupled components - God components/functions ### 5. Operational Gaps Find: - Missing error tracking/logging - No observability into failures - Manual processes that should be automated - Missing environment variables - Insecure configurations ### 6. Security Concerns Check for: - Exposed secrets or credentials - Missing input validation - SQL injection vectors - XSS vulnerabilities - Missing authentication/authorization ## Detection Process ### Quick Scan (5 min) ```bash # Run type check npx tsc --noEmit # Check for build errors npm run build # Look for TODOs and FIXMEs grep -r "TODO\|FIXME\|HACK\|XXX" src/ ``` ### Deep Scan (30 min) 1. Review recent git changes for introduced issues 2. Check Supabase logs for errors 3. Review component complexity 4. Check for missing error boundaries 5. Audit API route error handling ## Output Requirements Log all findings to `.claude/issues-registry.md`: ```markdown # Issues Registry ## Active Issues | ID | Category | Severity | Description | Location | Detected | Status | |----|----------|----------|-------------|----------|----------|--------| | I-001 | Code Health | High | Type error in auth flow | src/lib/auth.ts:45 | 2026-01-01 | Open | | I-002 | UX Friction | Medium | No loading state on submit | src/components/Form.tsx | 2026-01-01 | Open | ## Severity Levels - **Critical:** Blocks users or causes data loss - **High:** Major functionality broken or security issue - **Medium:** Degraded experience or tech debt - **Low:** Minor polish or optimization ## Resolved Issues (Move issues here when fixed, note resolution) ``` ## Rules 1. **Document everything found** - Even minor issues, log them 2. **Severity matters** - Be honest about impact level 3. **Location is key** - Include file:line for code issues 4. **Don't fix while identifying** - Separate detection from resolution 5. **Update regularly** - Keep the registry current ## Transition After identification: - Multiple issues found → Proceed to **Priority System** - Single clear issue → Proceed to **Execution System** - Blocked by confusion → Return to **Clarity System** --- *This is System 2 of 5: Clarity → Identity → Priority → Execution → Reset*
Related Skills
3-identifying-architecture
Third step in building instruction context for codebase
lets-go-rss
A lightweight, full-platform RSS subscription manager that aggregates content from YouTube, Vimeo, Behance, Twitter/X, and Chinese platforms like Bilibili, Weibo, and Douyin, featuring deduplication and AI smart classification.
grail-miner
This skill assists in setting up, managing, and optimizing Grail miners on Bittensor Subnet 81, handling tasks like environment configuration, R2 storage, model checkpoint management, and performance tuning.
astro
This skill provides essential Astro framework patterns, focusing on server-side rendering (SSR), static site generation (SSG), middleware, and TypeScript best practices. It helps AI agents implement secure authentication, manage API routes, and debug rendering behaviors within Astro projects.
tech-blog
Generates comprehensive technical blog posts, offering detailed explanations of system internals, architecture, and implementation, either through source code analysis or document-driven research.
modal-deployment
Run Python code in the cloud with serverless containers, GPUs, and autoscaling using Modal. This skill enables agents to generate code for deploying ML models, running batch jobs, serving APIs, and scaling compute-intensive workloads.
whisper-transcribe
Transcribes audio and video files to text using OpenAI's Whisper CLI, enhanced with contextual grounding from local markdown files for improved accuracy.
vly-money
Generate crypto payment links for supported tokens and networks, manage access to X402 payment-protected content, and provide direct access to the vly.money wallet interface.
ux
This AI agent skill provides comprehensive guidance for creating professional and insightful User Experience (UX) designs, covering user research, information architecture, interaction design, visual guidance, and usability evaluation. It aims to produce actionable, user-centered solutions that avoid generic AI aesthetics.
thor-skills
An entry point and router for AI agents to manage various THOR-related cybersecurity tasks, including running scans, analyzing logs, troubleshooting, and maintenance.
ontopo
An AI agent skill to search for Israeli restaurants, check table availability, view menus, and retrieve booking links via the Ontopo platform, acting as an unofficial interface to its data.
chrome-debug
This skill empowers AI agents to debug web applications and inspect browser behavior using the Chrome DevTools Protocol (CDP), offering both collaborative (headful) and automated (headless) modes.