扩展智能体 Skill

「扩展智能体」分类共 662 个 Skill，按仓库 star 排序。分类自动生成，仅供参考。

全部文档与办公202 前端与设计261 需求与规划324 编码与调试449 浏览器与测试380 安全269 Git 与发布465 运维与云391 数据181 图表98 写作与翻译239 图像与视频451 营销与商业510 扩展智能体662 科研189 其他310

new-skill

hyhmrright/brooks-lint1.5k

new-skill

Scaffold a new brooks-lint analysis skill so it passes `npm run validate` and `npm run evals` on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends paired eval scenarios. Triggers when the maintainer asks to "add a new skill", "scaffold a skill", or "create a brooks-lint mode". Do NOT trigger for: editing an existing skill's content, adding a single eval to an existing skill, or authoring skills for some other plugin.

finetuning

evo-hq/evo1.5k

finetuning

This skill should be used when picking or diagnosing a training move (SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF), or when the user mentions fine-tuning, post-training, training recipe, reward design, or weight updates. Decision tree by reward shape, smoke-run gate, three failure diagnostics, five false-progress patterns. Provider recipes and I/O contract in references/.

subagent

evo-hq/evo1.5k

subagent

Protocol that evo optimization subagents follow when dispatched from /optimize. Auto-loaded by spawned subagents via their host's skill loader. The orchestrator may also invoke this skill to understand the brief shape its dispatched subagents expect + what they're required to emit -- useful when writing briefs or debugging a subagent's behavior.

subagent

evo-hq/evo1.5k

subagent

autoreview

openclaw/crabbox1.5k

autoreview

Structured code review through the shared OpenClaw agent-skills installation.

agent-design-review

mohitagw15856/pm-claude-skills1.4k

agent-design-review

Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent architecture, critique a multi-step/tool-using agent, debug an agent that loops or goes off-task, or harden an agent before launch. Produces a structured review — task fit, control flow, tools, memory/context, failure handling, cost, and safety — with prioritised findings and fixes.

parallel-execution

CloudAI-X/claude-workflow-v21.4k

parallel-execution

Patterns for parallel subagent execution using the Agent tool (formerly Task). Use when coordinating multiple independent tasks, spawning dynamic subagents, or implementing features that can be parallelized.

better-codex

noobnooc/agent1.4k

better-codex

Behavioral guardrails for Codex coding work based on common user complaints. Use when Codex is asked to implement, modify, debug, review, test, or operate on a codebase and should avoid unsafe scope expansion, stale edits, fake completion, brittle edits, shallow debugging, superficial patch-on fixes, one-off special-case code, short-term design choices that hurt maintainability, blindly following incorrect user assumptions, poor dependency choices, generic product or UI output, over-mocked tests, noisy approvals, verbose status reports, or leaking internal reasoning into project artifacts or user-facing UI.

lore

specstoryai/getspecstory1.3k

lore

SpecStory Lore - mine your SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more) into a persistent corpus, surface your reproducible workflows with corroborated evidence, and interactively forge the chosen ones into skills installed across all your agent harnesses. Use when the user wants to turn past AI coding sessions into reusable skills, asks "what could I make into a skill", "mine my lore", "forge skills from my history", or points at a .specstory/history directory.

workthreads

specstoryai/getspecstory1.3k

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still an open loop, and what was just started. Use when someone asks "what happened this week", "what is still open", "what did the team finish", "give me the weekly rollup", or wants a status report over a .specstory/history corpus.

anthropic

Anil-matcha/awesome-muse-connectors1.3k

anthropic

Check Anthropic API access and list available Claude models. Read-only. Trigger phrases: anthropic, claude models, anthropic api.

evaluating-llms-harness

OpenRaiser/NanoResearch1.3k

evaluating-llms-harness

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

peft-fine-tuning

OpenRaiser/NanoResearch1.3k

peft-fine-tuning

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

unsloth

OpenRaiser/NanoResearch1.3k

unsloth

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

oma-coordination

first-fluke/oh-my-agent1.3k

oma-coordination

Coordinate assigned specialist tasks and handoffs manually. Use when supervising a multi-agent project step by step.

oma-orchestration

first-fluke/oh-my-agent1.3k

oma-orchestration

Dispatch and supervise parallel specialist agents with durable task state. Use when automated multi-agent execution is requested.

oma-skill-creation

first-fluke/oh-my-agent1.3k

oma-skill-creation

Create or revise OMA skills and their references. Use for skill routing, execution contracts, conditional loading, and authoring validation.

establishing-project-context

GanyuanRan/Aegis1.3k

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

long-task-continuation

GanyuanRan/Aegis1.3k

long-task-continuation

Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.

subagent-driven-development

GanyuanRan/Aegis1.3k

subagent-driven-development

Use when executing a written implementation plan with independent tasks in the current session where delegation beats inline coordination cost; otherwise inline. Ad-hoc 2+ tasks without a plan use dispatching-parallel-agents.

using-aegis

GanyuanRan/Aegis1.3k

using-aegis

Use when starting a turn or checking Aegis skill routing.

agent-context-audit

AI-Builder-Club/skills1.3k

agent-context-audit

Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut ~80% of Claude Code's system prompt with no eval loss). Finds overconstraint, conflicting instructions, redundancy, stale facts, and missing "unknown knowns"; produces a scored findings report with concrete rewrites, then applies approved fixes. Use when someone says "audit my CLAUDE.md", "context audit", "unhobble this repo", "review our agent docs/skills/tools", or after upgrading to Claude 5-generation models.

open-agent-teams

AI-Builder-Club/skills1.3k

open-agent-teams

Delegate tasks to ANY CLI agent (claude, codex, aider, ...) running in a detached tmux session, with a race-safe done-signal protocol and multi-turn iteration. Use when delegating work to a non-Claude CLI agent, when the user says "tmux delegate", "run agent in tmux", "delegate to codex/aider", or when executor work should run in an observable background terminal instead of the Agent tool.

os-ask-simple

kharmanskyi/open-steps1.3k

os-ask-simple

ALWAYS invoke this skill before asking the user any technical question or offering options, and whenever they ask to be asked in plain words - "ask simple", "ask me simply", "ask me in plain words" - in any language. ALWAYS invoke it too when the user asks for your view on a technical choice: whether it is worth doing, more than the problem needs, or replaceable by something simpler, and which option you would take. Invoke it even when the code makes the answer look obvious: the checks are what make the answer more than a guess. Rewrites the question in plain words and always ends with one marked recommendation. A structural choice first passes six checks, shown as a table: effort now, simpler substitute, extra work later, lock-in, over-engineering, easy to undo. Doing nothing is always weighed.