Loading...
Loading...
Found 13,566 Skills
This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce worker tokens", "cross-agent memory without summarization", or discusses Attention Matching compaction, recursive language models with workers, or token explosion in hierarchical agents.
어떤 주제/과제든 받아서 스스로 팀을 구성하고 조사·분석·검토·결과도출까지 처리하는 범용 에이전트 팀 오케스트레이터. "팀으로 분석해줘", "에이전트 팀으로 조사해줘", "다각도로 검토해줘", "심층 분석 부탁해", "여러 관점으로 봐줘", "think-team", "think team" 키워드로 트리거. 단순 질문이 아닌 복합적 판단, 조사, 전략 결정이 필요한 모든 상황에서 사용.
Manage context-mode GitHub issues, PRs, releases, and marketing with parallel subagent army. Orchestrates 10-20 dynamic agents per task. Use when triaging issues, reviewing PRs, releasing versions, writing LinkedIn posts, announcing releases, fixing bugs, merging contributions, validating ENV vars, testing adapters, or syncing branches.
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.
Harness Engineering Phase 3: Establish cross-session state management to solve the problem of agents forgetting previous conversations. Create three files: tasks.json (task list), progress.md (progress record), and init.sh (environment initialization script). Use this skill immediately when the user says phrases like "establish task management", "make agent remember progress", "create tasks.json", "maintain state across sessions", "agent doesn't remember what was done last time", "create progress file", or "initialize state management". Prerequisites: harness-step1 and harness-step2 have been completed (the project has AGENTS.md and docs/ knowledge base).
Agent-optimized CLI for Bluesky (ATProto) and X (Twitter). YAML in, YAML out, exit codes for automation. Use when the task involves posting, replying, reading feeds, searching, annotating URLs, or running a sync/check/dispatch agent loop across social platforms.
RLM-style large-codebase comprehension — build a mental map of any codebase by dispatching sub-agents to explore regions without bloating main context
Autonomously submit brief, constructive internal feedback when an agent encounters material, generalizable friction and can suggest an improvement that would make agents more effective. Use this skill proactively during any task without waiting for the user to invoke it, and submit without asking permission, previewing the message, or mentioning the submission.
Scope coverage, build a testing strategy, test the feature with agent-browser, capture screenshots/video (always mandatory), upload to S3, and create a structured test report (never skip)
Pattern for progressively refining context retrieval to solve the subagent context problem
Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.
HeyGen AI avatar video creation API. Use when: (1) Generating AI avatar videos with /v2/video/generate, (2) Using Video Agent for one-shot prompt-to-video generation, (3) Working with HeyGen avatars, voices, backgrounds, or captions, (4) Creating transparent WebM videos for compositing, (5) Polling video status or handling webhooks, (6) Integrating HeyGen with Remotion for programmatic video, (7) Translating or dubbing existing videos.