Skill4Agent
Skill4Agent
All SkillsSearchTools
|
Explore
Skill4Agent
Skill4Agent

AI Agent Skills Directory with categorization, English/Chinese translation, and script security checks.

Sitemap

  • Home
  • All Skills
  • Search
  • Tools

About

  • About Us
  • Disclaimer
  • Copyright

Help

  • FAQ
  • Privacy
  • Terms
Contact Us:osulivan147@qq.com

© 2026 Skill4Agent. All rights reserved.

All Skills

Total 31,386 skills, AI & Machine Learning has 5082 skills

Categories

Showing 12 of 5082 skills

Per page
Downloads
Sort
AI & Machine Learningsubconscious-systems/skil...

subconscious-dev

Build AI agents with Subconscious platform. Use when user wants to: build an agent, create an AI agent, use Subconscious, build with TIM, create agent with tools, research agent, search agent, tool-calling agent, subconscious.dev, TIMRUN, tim, tim-edge, timini, tim-gpt, tim-gpt-heavy. Do NOT use for generic OpenAI/Anthropic/LLM tasks without Subconscious.

🇺🇸|EnglishTranslated
2
AI & Machine Learningjkeskikangas/skills

reviewing-skills

Reviews and grades an agent skill directory (SKILL.md plus supporting resources) for specification compliance, clarity, token efficiency, safety, robustness, and portability. Use when a user wants a rubric-based critique with a weighted score/grade and concrete, minimal patch suggestions.

🇺🇸|EnglishTranslated
2
AI & Machine Learningjoelhooks/joelclaw

recall

Fan-out search across all memory sources when context is unclear or vaguely referenced. Triggers on: 'from earlier', 'remember when', 'what we discussed', 'that thing with', 'the conversation about', 'did we ever', 'what happened with', 'you mentioned', 'we talked about', 'earlier today', 'last session', 'the other day', or any vague reference to past context that needs resolution before the agent can act.

🇺🇸|EnglishTranslated
2
AI & Machine Learningneolabhq/context-engineer...

sadd:launch-sub-agent

Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification

🇺🇸|EnglishTranslated
2
AI & Machine Learningneolabhq/context-engineer...

customaize-agent:create-command

Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration

🇺🇸|EnglishTranslated
2
AI & Machine Learningneolabhq/context-engineer...

sadd:multi-agent-patterns

Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.

🇺🇸|EnglishTranslated
2
AI & Machine Learningneolabhq/context-engineer...

sadd:do-competitively

Execute tasks through competitive multi-agent generation, multi-judge evaluation, and evidence-based synthesis

🇺🇸|EnglishTranslated
2
AI & Machine Learningneolabhq/context-engineer...

fpf:reset

Reset the FPF reasoning cycle to start fresh

🇺🇸|EnglishTranslated
2
AI & Machine Learningjoelhooks/joelclaw

skill-review

Audit and maintain the joelclaw skill inventory. Use when checking skill health, fixing broken symlinks, finding stale skills, or running the skill garden. Triggers: 'skill audit', 'check skills', 'stale skills', 'skill health', 'skill garden', 'broken skill', 'skill review', 'fix skills', 'garden skills', or any task involving skill inventory maintenance.

🇺🇸|EnglishTranslated
2
AI & Machine Learningathola/claude-night-marke...

escalation-governance

NEVER escalate without investigation first. This is the Iron Law. Use when evaluating whether to escalate models, facing genuine complexity requiring deeper reasoning, novel patterns with no existing solutions, high-stakes decisions requiring capability investment. Do not use when thrashing without investigation - investigate root cause first. DO NOT use when: time pressure alone - urgency doesn't change task complexity. DO NOT use when: "just to be safe" - assess actual complexity instead.

🇺🇸|EnglishTranslated
2
AI & Machine Learningjoelhooks/joelclaw

skos-taxonomy

Design, apply, and maintain SKOS taxonomies for joelclaw agent workflows. Use when defining concept schemes, classifying agent inputs/outputs, mapping to external vocabularies, or integrating taxonomy metadata with Typesense retrieval.

🇺🇸|EnglishTranslated
2
AI & Machine Learningathola/claude-night-marke...

risk-classification

Inline risk classification for agent tasks using a 4-tier model. Hybrid routing: GREEN/YELLOW use heuristic file-pattern matching, RED/CRITICAL escalate to war-room-checkpoint for full reversibility scoring.

🇺🇸|EnglishTranslated
2
1...129130131132133...424
Page