智能体
Agent 规划、多步流程与编排
skill-creator
tech-leads-club
Guide for creating effective AI agent skills. Use when users want to create a new skill (or update an existing skill) that extends an AI agent's capabilities with specialized knowledge, workflows, or tool integrations. Works with any agent that supports the SKILL.md format (Claude Code, Cursor, Roo, Cline, Windsurf, etc.). Triggers on "create skill", "new skill", "package knowledge", "skill for".
session-control
Chachamaru127
"/workのセッションresume/forkを制御。ワークフロー内部用。Do NOT load for: user session management, login state, app state handling."
agent-browser
Chachamaru127
"ブラウザを手足のように操る。ページ遷移、フォーム入力、スクショ、なんでもこい。Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include 'go to [url]', 'click on', 'fill out the form', 'take a screenshot', 'scrape', 'automate', 'test the website', 'log into', or any browser interaction request. Do NOT load for: sharing URLs, embedding links, screenshot image files."
cursor-skill-creator
tech-leads-club
Creates Cursor-specific AI agent skills with SKILL.md format. Use when creating skills for Cursor editor specifically, following Cursor's patterns and directories (.cursor/skills/). Triggers on "cursor skill", "create cursor skill".
agent-browser
pedronauck
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
figma-implement-design
tech-leads-club
Translate Figma nodes into production-ready code with 1:1 visual fidelity using the Figma MCP workflow (design context, screenshots, assets, and project-convention translation). Trigger when the user provides Figma URLs or node IDs, or asks to implement designs or components that must match Figma specs. Requires a working Figma MCP server connection.
cc-cursor-cc
Chachamaru127
"Cursor PMでアイデアを検証し、Plans.mdを更新してバトンタッチ。2-Agentワークフロー対応。"
cursor-subagent-creator
tech-leads-club
Creates Cursor-specific AI subagents with isolated context for complex multi-step workflows. Use when creating subagents for Cursor editor specifically, following Cursor's patterns and directories (.cursor/agents/). Triggers on "cursor subagent", "cursor agent".
agent-browser
Chachamaru127
"ブラウザを手足のように操る。ページ遷移、フォーム入力、スクショ、なんでもこい。Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include 'go to [url]', 'click on', 'fill out the form', 'take a screenshot', 'scrape', 'automate', 'test the website', 'log into', or any browser interaction request. Do NOT load for: sharing URLs, embedding links, screenshot image files."
plan-with-agent
Chachamaru127
"アイデアをPlans.mdに落とし込む。夢を計画に変える魔法使い。Use when user mentions '/plan-with-agent', create a plan, organize tasks, feature planning, or TDD planning. Do NOT load for: implementation, reviews, or setup."
gh-aw
prowler-cloud
Create and maintain GitHub Agentic Workflows (gh-aw) for Prowler. Trigger: When creating agentic workflows, modifying gh-aw frontmatter, configuring safe-outputs, setting up MCP servers in workflows, importing Copilot Custom Agents, or debugging gh-aw compilation.
pinchtab
pinchtab
Control a headless or headed Chrome browser via Pinchtab's HTTP API. Use for web automation, scraping, form filling, navigation, and multi-tab workflows. Pinchtab exposes the accessibility tree as flat JSON with stable refs — optimized for AI agents (low token cost, fast). Use when the task involves: browsing websites, filling forms, clicking buttons, extracting page text, taking screenshots, or any browser-based automation. Requires a running Pinchtab instance (Go binary).
browser-use
aAAaqwq
AI驱动的智能浏览器自动化工具。使用LLM理解页面并自动执行任务，比传统Playwright更智能、更省token。适用于复杂交互、动态页面、需要智能决策的浏览器操作。Chrome浏览器优先。
repo-task-proof-loop
DenisSergeevitch
Repo-local workflow skill for large coding tasks. Initializes .agent/tasks/TASK_ID artifacts, installs project-scoped Codex and Claude subagents, updates AGENTS.md plus the repo's Claude guide file with the workflow, and runs a spec-freeze → build → evidence → verify → fix loop with fresh-session verification.
discover-and-wire-tools
Agenta-AI
Use find_capabilities to discover the right Agenta tools for an agent you are building, report what each integration needs to connect, and wire the tools into the new agent's config. Use when a setup/builder agent must turn a plain-language task ("post to Slack and open GitHub issues") into attached, connected, ready-to-run tools.
incoherence
solatis
Detect and resolve incoherence in documentation, code, specs vs implementation.
agent-teams
serejaris
Use when facing complex tasks needing parallel collaboration between multiple agents with shared state, coordination, and direct inter-agent communication. Triggers on "создай команду", "agent team", "параллельная работа агентов", "team of agents"
deep-audit
pedrohcgs
Comprehensive adversarial audit of a theory, proof, math/econ paper, codebase, or set of claims — decompose into components, fan out independent skeptics that must return CONCRETE defects, adjudicate every finding with a separate judge, fix all confirmed defects, then re-verify. Use when correctness must be bulletproof and single-pass or round-by-round review is too slow and too shallow. Invoke for "audit this rigorously", "find ALL the bugs/gaps", "make this rock solid", "converge faster on correctness".
verify-claims
pedrohcgs
Run Chain-of-Verification (CoVe) on a draft or a block of text with factual claims. Spawns the claim-verifier agent in a forked (fresh) context so it never sees the draft — then reports which claims are supported, contradicted, or unverifiable. Use when user says "verify these citations", "check the claims in X", "did I hallucinate anything", "fact-check this draft", "run CoVe on this", or after any text generation that asserts facts about papers, datasets, or numerical results. NOT for style/grammar review (use /proofread) or substance review (use /review-paper).
pedagogy-review
pedrohcgs
Holistic pedagogical review of a lecture deck (.qmd or .tex). Checks narrative arc, prerequisite assumptions, worked examples, notation clarity, and deck-level pacing. Use when user says "pedagogy review", "does this teach well?", "is the flow right?", "will students follow?", "review the narrative", or before teaching a deck for the first time. Read-only; produces a report.
stac-quickstart
StacDev
Help initialize and validate a Stac-enabled Flutter project and ship a first server-driven screen. Use when users ask to set up Stac CLI, run stac init/build/deploy, verify project prerequisites, or troubleshoot first-run setup and missing configuration files.
graphite-is-being-a-piece-of-shit-just-merge-my-stack
rivet-dev
Merge a stacked Graphite branch chain with gh by retargeting each PR to main and merging bottom to top, including conflict recovery via rebase.
agent-teams
devxoul
Interact with Microsoft Teams - send messages, read channels, manage reactions
ui-agent-patterns
HermeticOrmus
Patterns for delegating UI work to specialized agents. Covers synthesis-master vs specialized agents, multi-agent UI generation workflows, and orchestration strategies for complex UI tasks.