Agent skill
link-validation
Universal link validation using lychee for Claude Code sessions. Runs at session end to detect broken links and path policy violations.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/development/link-validation
SKILL.md
Link Validation Skill
Validates markdown links in your workspace using lychee.
What It Does
At session end (Stop hook), this skill:
- Discovers all markdown files in your workspace
- Runs lychee to check for broken links
- Lints paths for policy violations (absolute paths, excessive traversal)
- Outputs JSON results for programmatic consumption
Requirements
- lychee installed (
brew install lychee) - Python 3.11+ and uv
Output
Results are written to .link-check-results.md in your workspace:
# Link Check Results
**Correlation ID**: `01JEGQXV8KHTNF3YD8G7ZC9XYK`
## Lychee Link Validation
No broken links found.
## Path Policy Violations
No path violations found.
Path Policy Rules
| Rule | Severity | Description |
|---|---|---|
| NO_ABSOLUTE_PATHS | Error | Filesystem absolute paths not allowed |
| NO_PARENT_ESCAPES | Warning | Excessive ../ may escape repository |
| MARKETPLACE_RELATIVE | Warning | Plugins should use ./ relative paths |
Configuration
Override the default lychee config by placing .lycheerc.toml in your workspace root.
See config/lychee.toml for the default configuration.
References
- ADR: Link Checker Plugin Extraction
- Design Spec
- lychee Documentation
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?