发现 tools 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。
This skill orchestrates complete feature development using specialized agents. Use when the user says "build feature", "implement feature", "develop feature end-to-end", "full feature lifecycle", "orchestrate d...
Brief description of what this skill does and when to use it. Include trigger keywords that users would naturally mention.
Use when needing Claude bot review recommendations from PR - automatically waits for workflows (including Claude review) to complete, then extracts recommendations and returns concise summary without loading fu...
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool cal...
Create a new AFI skill in afi-skills from a canonical template, including SKILL.md and initial eval stubs, while keeping domains, risk levels, and determinism aligned with existing patterns.
This skill should be used when processing files in the inbox/ directory, organizing unstructured input, classifying content, or extracting actionable information. Triggered by requests like "process inbox", "or...
This skill should be used when refining hypotheses, checking testability, improving specificity, or designing verification strategies. Triggered by requests like "refine hypothesis", "validate hypothesis", "che...
Optimize LeadFraud.org pages for search engines and AI answer engines. Use this skill when creating or structuring content pages to maximize organic visibility and AI citation potential.
Capture and apply continuous improvements to Codex CLI skills during regular work. Use when a user wants to refine a skill, add a new skill after repeating a workflow, or keep skills up to date based on recent...
このスキルは外部のAI エージェントを実行するためのスキルです。 実装や調査の作業を別のAIエージェントに委譲してください。 あなた（メインのClaude）はユーザーとの対話・設計判断・方針決定に専念し、 実際の調査や実装は...
Review Agent Skills and provide findings and improvement suggestions from the perspective of official specification compliance and best practices. Use for skill review requests, SKILL.md quality checks, skill s...
Stack prompts in queue while agent runs, minimizing context switches to achieve sustained 6k lines per day output and preserved flow state. Use for heavy coding sessions, iterative refinements, rapid iteration...
Scrape external documentation (API references, library docs, protocol specifications) and generate Claude Agent Skills in SKILL.md format. Use when creating skills from documentation, integrating third-party kn...
Central CLAUDE.md file with project guidelines auto-injected into system prompt, achieving 10% accuracy lift in multi-hop reasoning through consistent context. Use for repo-wide context, coding standards enforc...
Capture task outcomes, score performance, and derive rules as token priors for continual learning without model weight changes. Use for post-task feedback, experience capture, pattern extraction, and learning f...
Meta-skill to generate new Claude Agent Skills from natural-language descriptions. Use when creating skills, building custom workflows, generating new capabilities, or extending Claude's functionality. Outputs...
Route tasks to small model by default, escalate to large model only on low confidence detection, achieving 87% faster learning and 10-30x cost reduction while maintaining accuracy. Use for cost optimization, co...
Extract lessons from task failures using Reflector agent, merge insights via Curator pattern, achieving 10% accuracy improvement without context collapse. Use for post-failure analysis, lesson extraction, self-...
Auto-detect and load minimal context from Skills folders using progressive disclosure, trimming 1400 tokens from system prompt through metadata-first loading. Use when optimizing token usage, managing multiple...
Convert repeated tasks into versioned skills, track performance gaps, and iteratively polish through Git version control. Use for identifying repeated patterns, improving skill consistency, tracking skill evolu...
Orchestrate the SFH-OS fractal horn design pipeline. Use when the user wants to design a horn, run the full pipeline, manage iterations, or resolve conflicts between acoustic and manufacturing requirements. Thi...
Intelligent test generation from components, functions, and APIs
Local cloud server providing API access to skills and files for Claude.ai
Model Context Protocol server exposing AI Factory tools to Claude Desktop
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。