LLM & AI

Browse agent skills for LLM integration, AI development, and language models

Categories, GitHub stars, and source recency help organize and order the catalog. These signals are not an endorsement, quality certification, safety review, or guarantee of fit. Open a skill detail and inspect its source before use.

≥48 results

openclaw/openclaw

Use to talk to the Discord-backed OpenClaw agent/session; not for archive search.

configure-channel

openclaw/openclaw

Configure and prove a chat channel with non-interactive one-liners; secrets only as SecretRefs.

openclaw/openclaw

Discord messaging workflows through OpenClaw's message tool.

openclaw/openclaw

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

openclaw/openclaw

Start voice calls via the OpenClaw voice-call plugin.

openclaw/openclaw

Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.

openclaw/openclaw

Local speech-to-text with the Whisper CLI (no API key).

openclaw/openclaw

ElevenLabs text-to-speech with mac-style say UX.

agent-introspection-debugging

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.

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.

agent-harness-construction

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 content language: Japanese

ai-regression-testing

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 content language: Japanese

autonomous-loops

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 content language: Japanese

openclaw-persona-forge

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。

Skill content language: Chinese

strategic-compact

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 content language: Japanese

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 content language: Japanese

token-budget-advisor

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 content language: Japanese

iterative-retrieval

서브에이전트 컨텍스트 문제를 해결하기 위한 점진적 컨텍스트 검색 개선 패턴

Skill content language: Korean

agent-introspection-debugging

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。

Skill content language: Chinese

ai-regression-testing

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。

Skill content language: Chinese

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。

Skill content language: Chinese

token-budget-advisor

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。

Skill content language: Chinese

iterative-retrieval

Pattern for progressively refining context retrieval to solve the subagent context problem

Skill content language: Chinese

agent-harness-construction

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.

agent-introspection-debugging

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.

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.

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.

gan-style-harness

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.

iterative-retrieval

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.

lead-intelligence

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.

openclaw-persona-forge

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.

Skill content language: Chinese

Shared orchestration engine for the orch-* skill family. Defines the gated Research-Plan-TDD-Review-Commit pipeline, the size classifier, the agent map, and the two human gates that the orch-* operation skills delegate to. Not usually invoked directly. Not usually invoked directly; it applies when an orch-* skill delegates its gated Research-Plan-TDD-Review-Commit pipeline.

plan-orchestrate

Read a plan document, decompose it into steps, design a per-step agent chain from the ECC catalogue, and emit ready-to-paste /orchestrate custom prompts. Generative only — never invokes /orchestrate itself. Use when the user has a multi-step plan and wants to drive it through orchestrate without composing chains by hand.

ralphinho-rfc-pipeline

RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration. Use when running RFC-driven multi-agent execution with quality gates and a merge queue.

Interactive agent picker for composing and dispatching parallel teams. Use when composing and dispatching a parallel team of agents for a task.

token-budget-advisor

Offers the user an informed choice about how much response depth to consume before answering. Use this skill when the user explicitly wants to control response length, depth, or token budget. TRIGGER when: "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", or clear variants where the user is explicitly asking to control answer size or depth. DO NOT TRIGGER when: user has already specified a level in the current session (maintain it), the request is clearly a one-word answer, or "token" refers to auth/session/payment tokens rather than response size.

kanban-video-orchestrator

NousResearch/hermes-agent

Plan and run multi-agent video production pipelines.

inference-sh-cli

NousResearch/hermes-agent

Run 150+ AI apps (image, video, LLM) via inference.sh CLI.

NousResearch/hermes-agent

Embedding database for RAG and semantic search.

NousResearch/hermes-agent

Vision-language chat: VQA, captioning, image dialogue.

NousResearch/hermes-agent

Vector search engine for production RAG systems.

NousResearch/hermes-agent

Agent-native web search, deep research, and enrichment.

NousResearch/hermes-agent

Humanize text: strip AI-isms and add real voice.

serving-llms-vllm

NousResearch/hermes-agent

vLLM: high-throughput LLM serving, OpenAI API, quantization.

n8n-create-instance-ai-eval

Authors a new Instance AI workflow 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 workflow eval, or debugging why one is flaky.

Load before calling build-agent for a new or existing n8n Agent. Governs prerequisite creation, faithful handoff of the user's request, agent targeting across turns, builder questions, testing, and publishing. Use directly for routine follow-ups when the conversation already targets an Agent; rerun intent-recognition only when the requested artifact is no longer clear.

microsoft/vscode

Create a custom agent (.agent.md) for a specific job.

microsoft/vscode

Create a hook (.json) to enforce policy or automate agent lifecycle events.