Total 31,188 skills, AI & Machine Learning has 5047 skills
Showing 12 of 5047 skills
Diagnose and fix plugin registry issues including orphaned entries and project-scope conflicts (addresses Claude Code issue
Creates implementation-only tracker subtasks from `technical-details` using handoff-first context loading, lazy artifact reads, and compact JSON handoff output.
Execute this skill should be used when the user asks about "SPAWN REQUEST format", "agent reports", "agent coordination", "parallel agents", "report format", "agent communication", or needs to understand how agents coordinate within the sprint system. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
Design and refactor Agent Skills with concise, high-signal instructions and explicit trigger metadata. Use when creating a new skill, revising SKILL.md/README.md structure, or improving skill discoverability and portability.
Researches archives, contemporary accounts, and timeline reconstruction. Use when the album subject involves historical events that need primary source verification.
MixSeek-Plusのデバッグ機能を有効化し、ログ出力を制御します。「デバッグモードを有効化」「verbose」「ログを出力」「ログレベル」「デバッグ設定」といった依頼で使用してください。
FORGE SM Agent — Decomposes requirements into stories with test specs. Usage: /forge-stories
Generate Claude Code permissions config from session history. Use when setting up autonomous mode, configuring .claude/settings.json, avoiding --dangerously-skip-permissions, or analyzing what permissions a project needs. Reads session logs to extract Bash commands and MCP tools actually used, then generates appropriate allow/deny rules.
Creates production-grade, reusable skills that extend Claude's capabilities. This skill should be used when users want to create a new skill, improve an existing skill, or build domain-specific intelligence. Gathers context from codebase, conversation, and authentic sources before creating adaptable skills.
Install a pre-configured Claude Code statusline with model, tokens, cost, lines changed, and context usage. A batteries-included alternative to /statusline with formatting and color thresholds already defined.
Gemini CLI consultation workflow for coding agents. Use when technical tasks need Gemini consultation for decisions, planning, debugging, problem-solving, or pre-implementation guidance.
Unified CLI workflow for generating images and videos with Gemini, OpenAI, and Grok(xAI) via `ugen`. Use for tasks that require model discovery (`ugen models`), ordered multi-input composition (`--part text:...` and `--part image:...`), provider-specific option tuning (`--option`, `--options-json`), secure token handling (env or password prompt), and troubleshooting generation failures/timeouts.