LLM & Agents

Create hierarchical project plans optimized for solo agentic development. Use when planning projects, phases, or tasks that Claude will execute. Produces Claude-executable plans with verification criteria, not enterprise documentation. Handles briefs, roadmaps, phase plans, and context handoffs.

Creates new Claude Code skills following best practices. Guides through skill structure,naming, descriptions, and progressive disclosure. Use when user wants to create a skill,build a skill, make a new capability, or asks about skill best practices.

Generate beautiful infographic PNG images from Claude Code changelog summaries. Use this skill after changelog-interpreter has generated a user-friendly summary, to create a visual representation that can be saved and shared.

Searching internet for technical documentation using llms.txt standard, GitHub repositories via Repomix, and parallel exploration. Use when user needs: (1) Latest documentation for libraries/frameworks, (2) Documentation in llms.txt format, (3) GitHub repository analysis, (4) Documentation without direct llms.txt support, (5) Multiple documentation sources in parallel

Expert on Shelby Protocol decentralized blob storage on Aptos blockchain. Coordinates 7 specialized sub-skills covering protocol architecture, SDK usage, smart contracts, CLI tools, RPC infrastructure, dApp building, and storage integration. Triggers on keywords Shelby Protocol, Shelby storage, decentralized storage, Aptos storage, blob storage, Shelby.

Generate comprehensive app-spec.txt project specifications for autonomous software development. Use this skill when the user wants to create a detailed project specification, plan a new application, or set up an autonomous development workflow. This skill produces specifications compatible with the initializer-agent + coding-agent pattern.

Expert FDA regulatory consultant specializing in medical devices, pharmaceuticals, biologics, and combination products

Generates test cases, creates mocks, identifies edge cases, analyzes coverage gaps, and supports property-based, mutation, and contract testing. Use when writing tests, improving coverage, detecting flaky tests, or implementing advanced testing strategies.

Expert on Shelby Protocol smart contracts on Aptos blockchain. Helps with blob metadata, micropayment channels, auditing system, storage commitments, placement group assignments, Move modules, and on-chain state management. Triggers on keywords Shelby smart contract, Shelby Move, blob metadata, micropayment channel, Shelby auditing, placement group assignment, storage commitment, Aptos contract.

Starts a session and generates a startup prompt for use in the target project repo. Use when user wants to start a session, generate a startup prompt, or begin working on a project.

Write Vitest unit tests and browser mode component tests for TypeScript projects. Use when asked to write tests, create test files, add test coverage, fix failing tests, test React components with browser mode, or work with Vitest testing patterns. Handles both unit testing with Given-When-Then pattern and React component testing with vitest-browser-react.

Moving average based forecasting for smoothed predictions

Tests JavaScript and TypeScript applications with Vitest including unit tests, mocking, coverage, and React component testing. Use when writing tests, setting up test infrastructure, mocking dependencies, or measuring code coverage.

Designs database schemas, data models, and database architectures

Memory system with three MCP tools: mcp__plugin_kg_kodegen__memory_list_libraries (discover namespaces), mcp__plugin_kg_kodegen__memory_memorize (store with embeddings), mcp__plugin_kg_kodegen__memory_recall (semantic search). Use for storing/retrieving knowledge by meaning. WHEN: User says "remember this", "recall", "what did I save", "my notes", "find my knowledge about". WHEN NOT: File operations (use fs_*), exact keyword search (use fs_search).

Capture important decisions made during Claude Code sessions and store them in searchable, structured format for future reference. Automatically triggers on decision keywords or manual request.

Analyze existing PHPUnit test failure logs without running tests. Use when:- User says "fix the test failures" (after manually running tests)- User says "what tests are failing?"- User points to specific log file- Tests were run outside Claude's contextDelegates to fixer agent (sonnet) to find logs, parse failures, and implement fixes.Does NOT execute tests - use phpunit-runner for that.

GitHub issue情報を取得し、対応用のタスクファイル作成をサポートします。スクリプトがissue情報を取得し、Claude Codeがその情報を元にtmp/todoフォルダにタスクファイルを作成します。

This skill should be used when the user is stuck in a git-hex-driven rebase, merge, or cherry-pick due to conflicts and wants the agent to inspect, resolve, and then continue or abort safely. Trigger phrases include: "resolve conflicts", "rebase is stuck", "conflict markers", "continue the rebase", "abort the rebase".

Parameter-efficient fine-tuning with LoRA and Unsloth. Covers LoraConfig,target module selection, QLoRA for 4-bit training, adapter merging, andUnsloth optimizations for 2x faster training.