Agent skill
claude-infra-integrity
Install this agent skill to your Project
npx add-skill https://github.com/nikhillinit/Updog_restore/tree/main/.claude/skills/claude-infra-integrity
SKILL.md
Skill: claude-infra-integrity (v4 optimal)
Purpose
Ensure .claude/ changes are internally consistent and CI-safe.
This skill is used by agents who modify:
- .claude/agents/*.md
- .claude/skills/*/SKILL.md
- .claude/commands/*.md
- CAPABILITIES.md
- docs/INDEX.md
- .claude/settings.json
Checklist Before Completion
Naming Consistency
- Agent filename must match
name:in frontmatter (convention for consistency) - Skill folder name must match the referenced skill name
- Command filename determines the slash command name
Reference Integrity
- Every agent
skills:entry must exist in .claude/skills/ - CAPABILITIES.md must mention every agent and command (no orphaned capabilities)
Settings Permissions Integrity
Support either settings schema:
allowedTools: ["Read", "Write"]permissions: { allow: ["Read", "Write"] }
Documentation Integrity
- Relative links in docs/*.md must resolve (no broken links)
- Prefer ASCII output for docs and CI logs
Directory Structure
- Use flat structure for agents (all in .claude/agents/)
- Avoid nested subdirectories (not guaranteed to load)
Required Validation Command
npm run validate:claude-infra
Or directly:
npx tsx scripts/validate-claude-infra.ts
Environment Variables
| Variable | Default | Effect |
|---|---|---|
| USE_EMOJI | true | Set to false in CI for ASCII output |
Failure Patterns and Fixes
Agent name mismatch
Symptom: filename foo-bar.md but frontmatter name: foo_bar
Fix: Unify on one canonical name; prefer kebab-case.
Missing skill folder
Symptom: agent references skills: statistical-testing but .claude/skills/statistical-testing/ missing
Fix: Create skill folder and add SKILL.md, or remove reference.
Tool not allowed by settings
Symptom: agent uses Bash but settings disallow it
Fix: Either adjust settings governance or remove tool usage from the agent.
Broken docs link
Symptom: docs/INDEX.md links to missing file Fix: Update the link or add the missing document.
Nested agent directory warning
Symptom: Found nested directory .claude/agents/subagents/
Fix: Move agents to flat structure in .claude/agents/
Standard Failure Block
When validation fails, the script emits:
===============================================================================
VALIDATION FAILED: Claude Infrastructure
===============================================================================
SUMMARY: N configuration error(s) found in .claude/ directory
PROBABLE_CAUSE: Agent/skill references, naming conventions, or settings are inconsistent
NEXT_STEP: Review errors above and fix configuration files
===============================================================================
Dependencies
The validator requires Node.js/tsx for TypeScript execution:
npm i -D tsx
This handles:
- YAML frontmatter parsing
- File system traversal
- Reference validation
- Link checking
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
financial-calc-correctness
statistical-testing
ui-ux-pro-max
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.
code-reviewer
Comprehensive multi-AI code review system for Python, JavaScript, and TypeScript. Use when reviewing code for quality, security, performance, or best practices. Includes automated analysis scripts, language-specific patterns, and AI collaboration workflows for complex decisions.
dependency-guardian
Automated dependency management with security scanning, update orchestration, and compatibility validation
documentation-sync
Detects code/documentation drift, validates examples, generates diagrams, auto-updates documentation
Didn't find tool you were looking for?