Loading...
Loading...
Found 408 Skills
Universal seed data generator: MIGRATE from ORM schemas or GENERATE from entity definitions to any target format
Security audit worker (L3). Scans codebase for hardcoded secrets, SQL injection, XSS, insecure dependencies, missing input validation. Returns findings with severity (Critical/High/Medium/Low), location, effort, and recommendations.
Dependencies audit worker (L3). Checks outdated packages, unused deps, reinvented wheels, vulnerability scan (CVE/CVSS). Supports mode: full | vulnerabilities_only.
Upgrades Python pip/poetry/pipenv dependencies with breaking change handling
Configures Swagger/OpenAPI documentation
CREATE/REPLAN Epics from scope (3-7 Epics). Batch Preview + Auto-extraction. Decompose-First Pattern. Auto-discovers team ID.
Updates ALL task types (implementation/refactoring/test). Compares IDEAL plan vs existing tasks, categorizes KEEP/UPDATE/OBSOLETE/CREATE, applies changes in Linear and kanban.
Coordinates 9 specialized audit workers (security, build, architecture, code quality, dependencies, dead code, observability, concurrency, lifecycle). Researches best practices, delegates parallel audits, aggregates results into single Linear task in Epic 0.
Orchestrates full decomposition (scope → Epics → Stories) by delegating ln-210 → ln-220. Sequential Story decomposition per Epic. Epic 0 for Infrastructure.
Creates focused feature specifications with user stories, acceptance criteria, and edge cases. Lighter than PRD, focuses on single feature implementation. Use when specifying individual features after PRD approval or for standalone feature work.
Transform vague prompts into precise, well-structured specifications using EARS (Easy Approach to Requirements Syntax) methodology. This skill should be used when users provide loose requirements, ambiguous feature descriptions, or need to enhance prompts for AI-generated code, products, or documents. Triggers include requests to "optimize my prompt", "improve this requirement", "make this more specific", or when raw requirements lack detail and structure.
Optimize CLAUDE.md files using progressive disclosure. Goal: Maximize LLM working efficiency, NOT minimize line count. Use when: User wants to optimize CLAUDE.md, complains about context issues, or file exceeds 500 lines.