All Skills

Checklist for validating tenant isolation in multi-tenant systems.

Group git changes by logic and commit them using English Conventional Commit format. Quick command: commit-grouped [lang=en], [scope=shared|api|fe], [exclude=file-pattern]

Archive multiple completed changes at once. Use when archiving several parallel changes.

Download and parse Advent of Code puzzles using aoc-cli. Extracts examples, expected outputs, and problem requirements from puzzle descriptions. Use when needing to fetch AoC puzzles, parse puzzle examples, or when user mentions downloading or reading AoC puzzle data.

Use when implementing in any language using top-down decomposition with visible hole markers, where Claude reasons about each hole's contract and fills iteratively

Implement Advent of Code solutions using Test-Driven Development. Generates test cases from puzzle examples, writes failing tests first, implements solutions incrementally, and iterates until all tests pass. Use when solving AoC puzzles, implementing solutions with TDD, or when user mentions test-driven development or writing tests.

Audit and harden existing codebases (especially AI-generated / vibe-coded ones) for production readiness. Use when the user asks to review, audit, clean up, harden, deslop, refactor, or fix quality issues across an existing codebase. Works in two phases — first a thorough multi-pass audit written to a structured file, then systematic fixes applied in safety-tiered order. Language-agnostic. Does NOT change business logic — only hardens, cleans, and robustifies.

# Perfect Test Skill A comprehensive and well-structured skill that demonstrates best practices in all areas. ## Dependencies - curl: HTTP client for API requests (`curl --version` to verify) - jq: JSON parser (`which jq` to verify installation) - Environment variable: API_KEY (obtain from https:

Processes Coles grocery invoices to extract structured data and predict future orders. Use when user uploads/pastes invoice content, asks to analyze grocery purchases, or wants shopping predictions.

Spin up parallel divergent research agents to explore an idea from every angle. Use when the user has a braindump, PRD, seed, concept, or half-formed idea they want explored. Triggers on "idea girlie", "divergent research", "explore this idea", "brainstorm this", "spin up researchers", "what are the options", "research this from different angles", "give me wild ideas", "I need divergent thinking on this", "explore the possibility space", or any variation of wanting parallel creative/strategic research on a concept.

Structure notes from a user research session into a clean debrief with insights, quotes, and implications. Paste your raw notes in and get a formatted summary ready for Notion.

Understanding and passing workflow quality gates (validate, dry, pytest, ruff, typecheck)

Generate project-level AGENTS.md guides that capture conventions, workflows, and required follow-up tasks. Use when a repository needs clear agent onboarding covering structure, tooling, testing, task flow, README expectations, and conventional commit summaries.

Generate OpenAPI 3.1 specification from existing Next.js API routes. Use when asked to generate API docs, create OpenAPI spec, document endpoints, generate Swagger file, or create API documentation.

Python resource management with context managers, cleanup patterns, and streaming. Use when managing connections, file handles, implementing cleanup logic, or building streaming responses with accumulated state.

Expert Midjourney prompt engineering skill. Use this skill when users need help crafting effective Midjourney prompts, converting natural language descriptions into optimized prompts, or want guidance on Midjourney parameters and techniques. Specializes in V7 best practices, the 7-Element Framework, and photography terminology.

Complete content creation and multiplication system for founders and indie hackers. Use for writing social posts, repurposing content, creating threads, build-in-public updates, or content planning. Triggers on "write a post", "create content", "repurpose this", "thread", "build in public", "ship update", "content calendar", "turn this into posts".

Multi-agent development workflow using Agent Teams. Supports four modes: plan (architect teammate + PM teammate debate → plan.md), dev (developer teammate + code-tester teammate + qa-tester teammate + reviewer teammate iterate → code), full (plan → approval gate → dev), and auto (plan → dev, no gate). Use when tasks benefit from collaborative agent teammates with peer messaging.

Generate terminal recordings using VHS tape files, produces GIF outputs.

Analyzes and refines agent skills by identifying quality issues, prioritizing fixes (MUST/SHOULD/NICE), gathering user feedback, and implementing improvements. Checks for common problems like time estimates, oversized SKILL.md files, poor structure, redundant content, missing examples, and unclear workflows. Use when reviewing, improving, refactoring, or auditing existing skills. Triggers include "review skill", "improve skill", "refactor skill", "skill quality", "audit skill", "fix skill", "optimize skill", "analyze skill".

This skill should be used when users want to create, manage, test, or troubleshoot KServe InferenceServices using the CLI. It provides workflows for deploying models (like Qwen2.5) via vLLM, checking their status, testing the OpenAI-compatible API, and troubleshooting common deployment issues.

Check the diff against main, and remove all AI generated slop introduced in this branch; keywords: deslop. Use only on explicit request; skip in routine implementation discussions.

Retrieves full details of a specific Stitch screen — HTML download URL, screenshot URL, dimensions. This is the final step in design retrieval before code conversion.

Optimize CLAUDE.md and docs/ ecosystem following Boris Cherny and Thariq Shihipar's best practices