This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Runs before the agent uses a tool for Bash, mcp__github__create_pull_request and mcp__github__merge_pull_request tool calls, executing validate-pr-creation.sh, validate-local-testing.sh, validate-pr-merge.sh and validate-tests-pass.sh (4 commands). From troykelly/claude-skills.
Runs after a tool call finishes for Edit, Write, Bash and mcp__github__create_pull_request tool calls, executing security-scan.sh, validate-generated-artifacts.sh, track-test-results.sh and post-pr-creation.sh (4 commands). From troykelly/claude-skills.
Runs when the agent finishes a response, executing plan-limit-account-switch.sh and check-ci-before-stop.sh (2 commands). From troykelly/claude-skills.
Use when API code changes (routes, endpoints, schemas). Enforces Swagger/OpenAPI sync. Pauses work if documentation has drifted, triggering documentation-audit skill.
Use when user requests autonomous operation across multiple issues. Orchestrates parallel workers using Task tool, monitors with TaskOutput, handles SLEEP/WAKE cycles, and works until scope is complete without user intervention.
MANDATORY when designing schemas, writing migrations, creating indexes, or making architectural database decisions - enforces PostgreSQL 18 best practices including AIO, UUIDv7, temporal constraints, and modern indexing strategies.
Use when a review finding cannot be fixed in current PR - creates properly documented tracking issue with full context, linked to parent, following full issue-driven-development process.
Use when documentation drift is detected. Comprehensively audits codebase and creates/updates Swagger, features docs, and general documentation to achieve full sync.
Use for LARGE work requiring feature-level grouping. Creates epic tracking issues, manages related issues under a common label, tracks epic progress, and coordinates with milestones.
Use when user-facing features change. Ensures features documentation is updated. Pauses work if documentation has drifted, triggering documentation-audit skill.
Use when receiving UAT feedback, bug reports, user testing results, stakeholder feedback, QA findings, or any batch of issues to investigate. Investigates each item BEFORE creating issues, classifies by type and priority, creates well-formed GitHub issues with proper project board integration.
MANDATORY before any GitHub project operations - caches project metadata to prevent rate limit exhaustion. Called by session-start. Other skills MUST use cached data.