发现 content media llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Customer workspace initialization skill (Japanese UI). Provides inbox (information accumulation), meeting minutes management, and auto-classification rules. Use for "setup customer workspace" or "add inbox feat...
End-to-end machine learning pipelines on Databricks including data exploration, feature engineering, model training with hyperparameter optimization, MLflow experiment tracking, model registration to Unity Cata...
Add or change allowed commands in AI agent permission configs (OpenCode, Claude Code)
Create Claude Code slash commands and OpenCode command files that delegate to skills. Use when creating new commands or refactoring existing ones to follow the delegation pattern.
Create subagent definitions for Claude Code and OpenCode that delegate to skills. Use when creating new subagents or refactoring existing ones to follow the delegation pattern.
Multi-specialist collaborative work review using independent subagents for comprehensive analysis
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or to...
Use this skill when entering a new or legacy project for the first time, to scan and localize global skills for project-specific conventions. Triggers on "onboard", "init skills", "localize skills", "project se...
Create new AI agent skills for this project. Use when asked to create a skill, add a skill, or document a new module for AI context.
Meta-skill that analyzes the Trail of Bits Testing Handbook (appsec.guide) and generates Claude Code skills for security testing tools and techniques. Use when creating new skills based on handbook content.
Use multiple Claude agents to investigate and fix independent problems concurrently
Skills wiki intro - mandatory workflows, search tool, brainstorming triggers
Multi-agent autonomous startup system. Triggers on "Loki Mode". Takes PRD to deployed product with zero human intervention. Requires --dangerously-skip-permissions flag.
Process large document corpora (1000+ docs, millions of tokens) through knowledge graph construction and stateful multi-hop reasoning. Use when (1) User provides a large corpus exceeding context limits, (2) Que...
Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical rese...
Enables AI agents to use Braintrust for LLM evaluation, logging, and observability. Includes scripts for querying logs with SQL, running evals, and logging data.
Semantic memory recall using FTS5 and Chroma. Use PROACTIVELY whenever the user asks about past events, themes, conversations, or when historical context would enrich a response. Trigger words: remember, when d...
Debug Samara session management, message batching, and task routing. Use when messages are scrambled, batching seems wrong, group chats behave oddly, or concurrent tasks interfere with each other. Trigger words...
Self-referential iteration mode for completing complex tasks autonomously. Use when a task requires multiple attempts, trial-and-error, or persistent effort until success. Based on the Ralph Wiggum methodology....
Access accumulated learnings and insights. Contains technical discoveries, personal insights, and lessons from past experience. Use when asked about past experience, what was learned, how something works based...
Search through memory files - learnings, decisions, observations, questions, episodes, reflections. Use when looking for past insights, recalling why a decision was made, finding what was learned about a topic,...
Check if a specific action is possible and what might be blocking it. Use when asking if you can do something, checking permissions, verifying a capability exists, or troubleshooting why something isn't working...
Final Approach - the landing sequence. Runs Go Poll with review agents (mission-control, telemetry, flight-director) using Haiku model. Supports A+ skip rule for efficient re-reviews.
Use this skill to coordinate concurrent agent work. Activates when tasks can be parallelized, during multi-agent workflows, or when orchestrating independent work streams.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。