Skip to main content
skillsmp

菜单

LLM 与 AI

浏览 LLM 集成、AI 开发和语言模型的 agent skills

分类、GitHub Stars 和来源更新时间只用于组织与排序目录，不代表 SkillsMP 背书、质量认证、安全审核或适用性保证。使用前请进入详情页检查来源。

137,570 个结果

discord-clawd
392.1k
openclawopenclaw/openclaw
Use to talk to the Discord-backed OpenClaw agent/session; not for archive search.

Skill 内容语言： 英语

configure-channel
392.1k
openclawopenclaw/openclaw
Configure and prove a chat channel with non-interactive one-liners; secrets only as SecretRefs.

Skill 内容语言： 英语

discord
392.1k
openclawopenclaw/openclaw
Discord messaging workflows through OpenClaw's message tool.

Skill 内容语言： 英语

imsg
392.1k
openclawopenclaw/openclaw
Use the imsg CLI from OpenClaw agents for iMessage/SMS DMs, groups, replies, reactions, polls, watching, and private-API actions.

Skill 内容语言： 英语

voice-call
392.1k
openclawopenclaw/openclaw
Start voice calls via the OpenClaw voice-call plugin.

Skill 内容语言： 英语

gemini
392.1k
openclawopenclaw/openclaw
Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.

Skill 内容语言： 英语

openai-whisper
392.1k
openclawopenclaw/openclaw
Local speech-to-text with the Whisper CLI (no API key).

Skill 内容语言： 英语

sag
392.1k
openclawopenclaw/openclaw
ElevenLabs text-to-speech with mac-style say UX.

Skill 内容语言： 英语

chief-of-staff
293.0k
mattpocockmattpocock/skills
Pursue a long-running goal in a single session by co-ordinating subagents.

Skill 内容语言： 英语

agent-introspection-debugging
279.6k
affaan-maffaan-m/ECC
Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

Skill 内容语言： 英语

dmux-workflows
279.6k
affaan-maffaan-m/ECC
Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.

Skill 内容语言： 英语

agent-harness-construction
279.6k
affaan-maffaan-m/ECC
AI エージェントのアクション空間、ツール定義、観測フォーマットを設計・最適化して完了率を向上させます。

Skill 内容语言： 日语

ai-regression-testing
279.6k
affaan-maffaan-m/ECC
AI 支援開発のためのリグレッションテスト戦略。データベース依存なしのサンドボックスモード API テスト、自動化されたバグチェックワークフロー、同じモデルがコードを書いてレビューする AI のブラインドスポットを捕捉するパターン。

Skill 内容语言： 日语

autonomous-loops
279.6k
affaan-maffaan-m/ECC
自動Claude Codeループのパターンとアーキテクチャ — シンプルな順序パイプラインからRFC駆動マルチエージェントDAGシステムまで。

Skill 内容语言： 日语

openclaw-persona-forge
279.6k
affaan-maffaan-m/ECC
为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡， 输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。 如当前环境提供已审核的生图 skill，可自动生成统一风格头像图片。 当用户需要创建、设计或定制 OpenClaw 龙虾灵魂时使用。 不适用于：微调已有 SOUL.md、非 OpenClaw 平台的角色设计、纯工具型无性格 Agent。 触发词：龙虾灵魂、虾魂、OpenClaw 灵魂、养虾灵魂、龙虾角色、龙虾定位、 龙虾剧本杀角色、龙虾游戏角色、龙虾 NPC、龙虾性格、龙虾背景故事、 lobster soul、lobster character、抽卡、随机龙虾、龙虾 SOUL、gacha。
strategic-compact
279.6k
affaan-maffaan-m/ECC
任意の自動コンパクションではなく、タスクフェーズを通じてコンテキストを保持するための論理的な間隔での手動コンパクションを提案します。

Skill 内容语言： 日语

team-builder
279.6k
affaan-maffaan-m/ECC
並列チームを構成して派遣するためのインタラクティブなエージェント選択ツール

Skill 内容语言： 日语

token-budget-advisor
279.6k
affaan-maffaan-m/ECC
回答する前に、どれだけの回答深度を消費するかについてユーザーに情報に基づいた選択を提供する。ユーザーが回答の長さ、深さ、またはトークンバジェットを明示的に制御したい場合にこのスキルを使用する。トリガー条件："token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión corta", "quiero controlar cuánto usas"、またはユーザーが回答のサイズや深さの制御を明示的に求めるその他の明確なバリエーション。トリガーしない条件：ユーザーが現在のセッションでレベルを指定済み（そのレベルを維持）、リクエストが明らかに一言の回答、または「token」が認証/セッション/支払いトークンを指している。

Skill 内容语言： 日语

iterative-retrieval
279.6k
affaan-maffaan-m/ECC
서브에이전트 컨텍스트 문제를 해결하기 위한 점진적 컨텍스트 검색 개선 패턴

Skill 内容语言： 韩语

agent-introspection-debugging
279.6k
affaan-maffaan-m/ECC
针对AI代理故障的结构化自调试工作流程，包括捕获、诊断、受限恢复和内省报告。
ai-regression-testing
279.6k
affaan-maffaan-m/ECC
AI辅助开发的回归测试策略。沙盒模式API测试，无需依赖数据库，自动化的缺陷检查工作流程，以及捕捉AI盲点的模式，其中同一模型编写和审查代码。
brand-voice
279.6k
affaan-maffaan-m/ECC
从真实的帖子、文章、发布说明、文档或网站文案中构建基于源材料的写作风格档案，然后在内容、外展和社交工作流中重复使用该档案。当用户希望保持声音一致性而不使用通用的AI写作套路时使用。
token-budget-advisor
279.6k
affaan-maffaan-m/ECC
在回答前，为用户提供关于消耗多少响应深度的知情选择。当用户明确希望控制响应长度、深度或令牌预算时使用此技能。触发条件："token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión corta", "quiero controlar cuánto usas"，或用户明确要求控制答案大小或深度的清晰变体。不触发条件：用户已在当前会话中指定了级别（保持该级别），请求明显是单字答案，或"token"指代认证/会话/支付令牌而非响应大小。
iterative-retrieval
279.6k
affaan-maffaan-m/ECC
Pattern for progressively refining context retrieval to solve the subagent context problem
agent-harness-construction
279.6k
affaan-maffaan-m/ECC
Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent's tool set, action space, or observation format.

Skill 内容语言： 英语

agent-introspection-debugging
279.6k
affaan-maffaan-m/ECC
Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

Skill 内容语言： 英语

agentic-os
279.6k
affaan-maffaan-m/ECC
Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

Skill 内容语言： 英语

counterparty-channel-discipline
279.6k
affaan-maffaan-m/ECC
Per-channel strict prompts, mention gating, silent observation, and a communication autonomy policy for agents that sit in shared channels with external counterparties. Use when an agent joins group chats, shared channels, or DMs where outsiders can read every message and you need it to speak only when addressed, never leak internal context, and route risky content to draft-only approval.

Skill 内容语言： 英语

dmux-workflows
279.6k
affaan-maffaan-m/ECC
Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.

Skill 内容语言： 英语

gan-style-harness
279.6k
affaan-maffaan-m/ECC
GAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomously. Based on Anthropic's March 2026 harness design paper. Use when a feature should be built autonomously through generator and evaluator iteration until it clears a quality bar.

Skill 内容语言： 英语

iterative-retrieval
279.6k
affaan-maffaan-m/ECC
Pattern for progressively refining context retrieval to solve the subagent context problem. Use when a subagent lacks the context it needs and retrieval must be refined across passes.

Skill 内容语言： 英语

lead-intelligence
279.6k
affaan-maffaan-m/ECC
AI-native lead intelligence and outreach pipeline. Replaces Apollo, Clay, and ZoomInfo with agent-powered signal scoring, mutual ranking, warm path discovery, source-derived voice modeling, and channel-specific outreach across email, LinkedIn, and X. Use when the user wants to find, qualify, and reach high-value contacts.

Skill 内容语言： 英语

loop-design-check
279.6k
affaan-maffaan-m/ECC
Design a goal-oriented agent loop or review one for failure modes: spinning, Goodhart-gaming the verifier, or running a wrong answer to completion. Covers machine-decidable goals, loop types, plan/build/judge skeletons, and runaway prevention; mechanism wiring lives in autonomous-loops. Use when designing, writing, or checking an agent loop. 中文触发：写 loop、设计 loop、做一个 loop、检查 loop 对不对、loop 体检、loop 会不会跑飞、可判定目标、五个崩法、plan build judge。

Skill 内容语言： 英语

openclaw-persona-forge
279.6k
affaan-maffaan-m/ECC
为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡， 输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。 如当前环境提供已审核的生图 skill，可自动生成统一风格头像图片。 当用户需要创建、设计或定制 OpenClaw 龙虾灵魂时使用。 不适用于：微调已有 SOUL.md、非 OpenClaw 平台的角色设计、纯工具型无性格 Agent。 触发词：龙虾灵魂、虾魂、OpenClaw 灵魂、养虾灵魂、龙虾角色、龙虾定位、 龙虾剧本杀角色、龙虾游戏角色、龙虾 NPC、龙虾性格、龙虾背景故事、 lobster soul、lobster character、抽卡、随机龙虾、龙虾 SOUL、gacha。 Use when creating, designing, or customizing an OpenClaw lobster persona — identity, SOUL.md, name, or avatar prompt.
orch-pipeline
279.6k
affaan-maffaan-m/ECC
Shared orchestration engine behind the orch-* skill family — the gated Research-Plan-TDD-Review-Commit pipeline, size classifier, agent and command map, and two human gates (plan approval, commit confirmation) that orch-* operation skills delegate to. Use indirectly via orch-add-feature, orch-fix-defect, orch-change-feature, orch-refine-code, or orch-build-mvp; read directly only when adding an orch operation or tuning shared phases.

Skill 内容语言： 英语

prompt-caching-strategy
279.6k
affaan-maffaan-m/ECC
Optimize LLM prompt caching hit rate to reduce API costs and improve latency. Analyzes prompt structure, identifies cacheable vs non-cacheable content, and recommends restructuring to maximize cache reuse. TRIGGER when: user says "prompt cache", "cache hit rate", "reduce LLM cost", "optimize token usage", "cheaper LLM calls", or asks about prompt caching strategies for OpenAI/Anthropic/other providers. DO NOT TRIGGER when: user just wants to optimize a single prompt's quality (use prompt-optimizer instead), or asks about general caching infrastructure.

Skill 内容语言： 英语

team-builder
279.6k
affaan-maffaan-m/ECC
Interactive picker that discovers available agent personas via the claude agents command and agents/ markdown globs, groups them into domains, has the user select up to five, dispatches them in parallel on one task, and synthesizes agreements and conflicts into a unified report. Use when composing a team of agents, browsing available agent personas, or running several specialist agents in parallel.

Skill 内容语言： 英语

ai-presenter-video
254.1k
NousResearchNousResearch/hermes-agent
Make a verified AI presenter video from script + image.

Skill 内容语言： 英语

kanban-video-orchestrator
254.1k
NousResearchNousResearch/hermes-agent
Plan and run multi-agent video production pipelines.

Skill 内容语言： 英语

inference-sh-cli
254.1k
NousResearchNousResearch/hermes-agent
Run 150+ AI apps (image, video, LLM) via inference.sh CLI.

Skill 内容语言： 英语

chroma
254.1k
NousResearchNousResearch/hermes-agent
Embedding database for RAG and semantic search.

Skill 内容语言： 英语

serving-llms-vllm
254.1k
NousResearchNousResearch/hermes-agent
vLLM: high-throughput LLM serving, OpenAI API, quantization.

Skill 内容语言： 英语

llava
254.1k
NousResearchNousResearch/hermes-agent
Vision-language chat: VQA, captioning, image dialogue.

Skill 内容语言： 英语

qdrant
254.1k
NousResearchNousResearch/hermes-agent
Vector search engine for production RAG systems.

Skill 内容语言： 英语

parallel-cli
254.1k
NousResearchNousResearch/hermes-agent
Agent-native web search, deep research, and enrichment.

Skill 内容语言： 英语

humanizer
254.1k
NousResearchNousResearch/hermes-agent
Humanize text: strip AI-isms and add real voice.

Skill 内容语言： 英语

n8n-create-agent-builder-eval
207.4k
n8n-ion8n-io/n8n
Authors and calibrates Instance AI evaluations that build standalone n8n Agents through Agent Builder. Use when a change under packages/cli/src/modules/agents affects build-agent routing, Agent setup, model or credential selection, tools, MCP servers, integrations, skills, tasks, testing, or user-facing build responses. Requires LangTracer access before authoring so each finished case can be published.

Skill 内容语言： 英语

n8n-create-instance-ai-eval
207.4k
n8n-ion8n-io/n8n
Authors a new Instance AI workflow or Agent eval case — written locally as JSON, calibrated against a real build, then pushed to the LangTracer suite CI runs — build cases, behaviour/process cases, credential cases, and seeded (mid-conversation) cases — with intent-driven expectations. Use when adding or changing an Instance AI eval, or debugging why one is flaky.

Skill 内容语言： 英语