Agent Workflow Claude Skills
4 122 agent workflow skills from 665 authors. They configure the agents themselves: memory, prompts, context and other skills. Half of them fit into 1 844 tokens or less — that is what one costs your context window when the agent loads it. 778 ship runnable scripts rather than instructions alone. 5 of them cannot work without an MCP server, most often task. We also found 589 copies of these same skills sitting in other people's repositories — counted once here, not 589 times.
4 122 unique 665 authors 4 updated this month 506 from vendors
Instructions to fetch assigned Linear issues in the current cycle and potentially kick off a development session.
| installation, theming, tokens, and per-component APIs/examples. Use this skill whenever the task involves CDS components, design-system rules, theming, or choosing between web and mobile CDS packages, even if the user only says "use CDS" or names a component. Always start from the docs route index, then fetch only the pages you need to reason and implement correctly. Prefer the CDS MCP server (`list-cds-routes`, `get-cds-doc`); if MCP is unavailable, use curl against
Use when the user wants to use the UCP CLI to find, compare, buy, or track products from online merchants, or to set up and troubleshoot the local UCP profile required for merchant-scoped operations. Covers global catalog search (\"find me X under $Y\"), named-merchant transactions (\"buy this from Z.com\"), order tracking, `ucp profile init`, `ucp doctor`, carts, checkout, orders, and UCP setup/help. Falls back to merchant-hosted handoff when direct in-protocol checkout isn't available.
ComfyUI prompt engineering knowledge — CLIP text encoding syntax, weight modifiers, model-specific prompting strategies, and best practices
Keep the ComfyUI sidebar panel node-pack (comfyui-agent-panel) in step with the orchestrator after comfyui-mcp updates. Use this whenever the orchestrator was just updated (self_update, npm i -g comfyui-mcp, a new version in the ENVIRONMENT line), when a panel/bridge command fails in a way that smells like version drift ("panel is too old", a graph_/ui_ command the panel doesn't implement, a feature that works in the docs but not in the sidebar), or when the user asks to update/pin/unpin the panel. It checks the installed panel version against what THIS orchestrator build needs, RESPECTS an explicit version pin (warn-only, never move a pinned user), offers a clear way to unset the pin, runs the sync through the verified install_panel path, and reports the version RE-READ from disk. Never claim a sync that did not happen.
Drive Chrome via the DevTools Protocol from JavaScript. Run JS snippets through the `browser-harness-js` CLI — it auto-spawns a long-lived bun HTTP server holding a fully-typed CDP `Session`, and every call (`browser-harness-js 'await session.Page.navigate(...)'`) executes against the same persistent connection. Session, active target, and globals survive across calls. Use when the user wants to automate, script, or inspect a Chrome browser via CDP — single tab or multi-tab, attach to existing Chrome or to a new one launched with --remote-debugging-port.
| Emits a dev-tool-agnostic handoff manifest from ready-for-dev stories so an external dev plugin or runner can pick up and execute the work. Use when the user says "generate a handoff", "create handoff manifest", "export stories for dev", "hand off to dev tool", "produce handoff manifest", "ready to hand off", "prepare handoff for external tool", "export ready-for-dev stories", or "create the handoff package". Also trigger when the user asks "what stories are ready for dev?" and wants an exportable artifact rather than a status report. path, status, owned file/module scope, wave/parallel_set, dependencies, acceptance-criteria summary, locked-sections note, and a schemaVersion field. See REFERENCE.md (bundled) for the full manifest schema and adapter notes for git-worktree parallel development and autonomous dependency-graph orchestrators.
Automated LinkedIn engagement workflow. The agent finds a relevant post on your chosen topic, drafts a comment with a genuine insight, gets your approval in chat, and posts it — all in one loop. You approve once before anything is posted. Use when asked to "engage on LinkedIn", "find a post to comment on", "post a LinkedIn comment", or "engage on [topic]". Requires LinkedIn session credentials in .env. Everything runs locally — credentials never leave your machine.
Automated LinkedIn engagement workflow. The agent finds a relevant post on your chosen topic, drafts a comment with a genuine insight, gets your approval in chat, and posts it — all in one loop. You approve once before anything is posted. Use when asked to "engage on LinkedIn", "find a post to comment on", "post a LinkedIn comment", or "engage on [topic]". Requires LinkedIn session credentials in .env. Everything runs locally — credentials never leave your machine.
Install, observe, tune, and enforce Sponsio: a runtime contract layer for LLM agents that blocks unsafe tool calls and scores output quality against declared rules. Use when the user wants to set up / add / install Sponsio, add guardrails or runtime safety to an LLM agent, generate or refine a sponsio.yaml, audit tool configurations for risks (data leaks, unguarded writes, missing confirmations), explain or review existing contracts, check what Sponsio would have blocked (`sponsio report`), move from observe to enforce mode, or debug why a contract is (or isn't) firing. Triggers on phrases like "set up sponsio", "add sponsio", "install sponsio", "add guardrails", "monitor my agent", "harden my agent", "audit my agent", "generate contracts", "explain my sponsio.yaml", "sponsio report", "flip to enforce", "false positive", "why is this rule firing".
Use after installing the sponsio-openclaw plugin to wire the runtime end-to-end. The plugin install only registers hooks + skills; the contract library and per-environment overrides are configured here. Bootstraps the per-plugin contract library tree at ~/.sponsio/plugins/, generates fresh starter libraries for OpenClaw plugins / MCP servers via `sponsio plugin scan` (with `--introspect` to auto-discover tool inventory; the agent then applies the prompt from `sponsio plugin prompt openclaw` to extract semantic contracts using its own LLM context — no separate API call), tunes the shipped rules to the user's actual environment, and verifies with a smoke test. Use when the user says any of "configure sponsio-openclaw", "set up sponsio-openclaw", "first-time setup of sponsio for OpenClaw", "wire up sponsio in this OpenClaw session", "add Sponsio guardrails for my OpenClaw plugins", "tune the plugin for my environment", "the plugin is too strict / too loose", "calibrate sponsio rules", "scan this OpenClaw plugin", "generate sponsio rules for my OpenClaw plugin", "I just installed Y plugin / MCP server in OpenClaw, what should sponsio block", or asks how to make sponsio-openclaw actually block things.
Use after `/plugin install sponsio-claude-code` to wire the runtime end-to-end. The plugin install only registers hooks + skills; the contract library and per-environment overrides are configured here. Bootstraps the per-plugin contract library tree at ~/.sponsio/plugins/, installs bundled starter libraries for popular MCP servers (github, filesystem, playwright), generates fresh starter libraries for plugins / MCP servers that don't ship one (via `sponsio plugin scan`), tunes the shipped rules to the user's actual environment (workspace path, expected call volume, dev/CI/prod profile), and verifies with a smoke test. Use when the user says any of "configure sponsio-claude-code", "set up sponsio-claude-code", "first-time setup of sponsio", "wire up sponsio in this Claude Code session", "add Sponsio guardrails for my MCP tools", "tune the plugin for my environment", "the plugin is too strict / too loose", "calibrate sponsio rules", "scan this plugin", "generate sponsio rules for X", "create a contract library for my plugin", "I just installed Y plugin / MCP server, what should sponsio block", or asks how to make sponsio-claude-code actually block things.
Install, observe, tune, and enforce Sponsio: a runtime contract layer for LLM agents that blocks unsafe tool calls and scores output quality against declared rules. Use when the user wants to set up / add / install Sponsio, add guardrails or runtime safety to an LLM agent, generate or refine a sponsio.yaml, audit tool configurations for risks (data leaks, unguarded writes, missing confirmations), explain or review existing contracts, check what Sponsio would have blocked (`sponsio report`), move from observe to enforce mode, or debug why a contract is (or isn't) firing. Triggers on phrases like "set up sponsio", "add sponsio", "install sponsio", "add guardrails", "monitor my agent", "harden my agent", "audit my agent", "generate contracts", "explain my sponsio.yaml", "sponsio report", "flip to enforce", "false positive", "why is this rule firing".
Use this skill to drive Compose HotSwan from an AI agent (Claude Code, Cursor, any MCP client) so the agent can edit a Kotlin file, trigger a hot reload, capture a device screenshot, evaluate the result against a design intent, and iterate without a human in the loop. Covers the seven HotSwan MCP tools (hotswan_get_status, hotswan_reload, hotswan_take_screenshot, hotswan_start_snapshot, hotswan_stop_snapshot, hotswan_select_variant, hotswan_build_and_install), the canonical edit-reload-screenshot loop, snapshot-based rollback, and when to fall back to a full install for schema changes. Use when the developer says "get the AI to tune this screen until it matches a mock", asks "can the AI see what changed?" or "can the AI screenshot the device?", sets up a Claude Code or Cursor workflow that needs MCP tool access, or wants AI-driven UI iteration.
Use this skill to teach Claude exactly which Kotlin and Compose changes hot-reload under Compose HotSwan and which trigger a full incremental rebuild fallback. Root cause is Android Runtime (ART) class schema immutability; only method bodies are mutable at runtime, so any change to fields, signatures, constructors, interfaces, inline functions, or new resource ids forces a rebuild. Covers the supported-changes table, the rebuild-forcing list, the diff-then-batch workflow that keeps a hot-reload session inside the fast path, and the inline-function and new-resource-id pitfalls. Trigger when the user asks "why did this rebuild?", "why isn't this hot reloading?", wants to learn HotSwan's boundaries before adopting it, or when reviewing a refactor that risks pushing a hot-reload session into a full rebuild.
Use this skill to keep Jetpack Compose state alive across HotSwan hot reloads by understanding the three escalating tiers Compose HotSwan uses (tier 1 targeted recomposition, tier 2 composition reset, tier 3 Activity.recreate) and choosing edits and state holders that stay inside tier 1 where scroll position, lazy items, dialog state, and per-composable remember values all survive. Explains which edits force escalation, which state holders survive each tier, and how to hoist transient UI state when the iteration loop must escalate. Use when the developer says "scroll jumped to top after a hot reload", "lost dialog state", "lazy column re-fetched", "tab selection reset", asks why HotSwan reload escalated to tier 2 or 3, plans a refactor and needs to know which scope it touches, or wants to know which state holders survive composition reset.
Use this skill to instrument a Jetpack Compose composable with `@TraceRecomposition` from `skydoves/compose-stability-analyzer` so per-recomposition diffs (which state or parameter changed, what value transition) print to logcat under the `Recomposition` tag. Works in release-with-debug-symbols builds where Android Studio Layout Inspector cannot reach, and feeds the IntelliJ / Android Studio plugin's live recomposition heatmap (green under 10, yellow 10–50, red 50+). Covers the Gradle plugin setup, the `ComposeStabilityAnalyzer.setEnabled(BuildConfig.DEBUG)` runtime gate that keeps the instrumentation out of production, and the handoff to debug-time Layout Inspector and CI `stabilityCheck`. Use when the user mentions `@TraceRecomposition`, "trace recomposition", "compose-stability-analyzer", "recomposition logcat", "recomposition heatmap", "release-mode recomposition counts", or needs to confirm a stability fix in a release-like build.
Create, maintain, or migrate functional skills; supports creating from a requirement brief and migrating an existing legacy skill directory into a functional skill structure.
>- This skill should be used when the user asks to "add a cask to homebrew", "create a homebrew cask", "add an app to homebrew", "new cask for", "homebrew cask for", "package an app for homebrew", "submit to homebrew-cask", "make a cask", "contribute a cask", or wants to package a macOS application for Homebrew.
>- This skill should be used when the user asks to "audit claude permissions", "audit permissions", "review local claude settings", "promote permissions to global", "clean up claude settings", "find permission patterns", or wants to identify project-local Claude Code permissions that should be added to global configuration.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
Use at the start of any OpenCLI session — this is the top-level map of what `opencli` can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".
基于 opencli 命令的智能搜索路由器。当用户想要使用 OpenCLI、CLI 或 API 搜索、查询、查找或研究信息时，尤其是涉及指定网站、社交媒体、技术资料、新闻、购物、旅游、求职、金融或中文内容时，务必使用此 skill
Orchestrates implementation of a plan file by delegating work to subagents in parallel. Verifies git branch state, tracks progress, and ensures high-quality implementation. Invoke with a plan file path and optional model override: /implement plans/my-plan.md [--model sonnet]
> Install, share, sync, and create AI agent skills across coding tools (Claude Code, Cursor, Codex, OpenCode, Copilot, Pi) using the agr CLI. Use skill ("install the pdf skill", "agr add ..."), sync agent resources across tools, share skills with their team, scaffold a new SKILL.md, run a skill ephemerally (agrx), set up a repo to manage AI agent dependencies, or configure tools/sources/instruction-syncing. Also use whenever an agr.toml or agr.lock is present in the project and the user is doing resource-management work.
> Debrief an AI agent skill (SKILL.md) after using it — capture session feedback or a retrospective and fold it back into the skill. Use whenever X", "feedback on X skill", "improve the X skill", "update the X skill", "let's revise X based on what we just did", "the X skill should also handle Y", "X didn't trigger when it should have", or otherwise wants to capture lessons from a session back into the skill that drove it. Handles in-repo skills (under skills/) by editing the source, committing, and re-installing via `agr upgrade`. Handles remote/upstream skills by offering to fork them in-repo or to file a GitHub issue via `gh`. Do NOT use for greenfield skill authoring (a separate concern — see `anthropics/skills/skill-creator`) or for installing / syncing / removing skills (use the `agr` CLI directly).
> Map, measure and improve business processes — SIPOC and swimlane capture, cycle-time and bottleneck analysis, handoff diagnosis, and a payback-ranked improvement backlog. Use when a process is slow, error-prone, or crosses too many teams.
> Test and evaluation harness for AI agents — scenario suites, deterministic replay, regression diffing, cost and latency budgets. Use when agent quality is vibe-checked, before shipping a prompt or model change, or when evals drift.
> Designs multi-agent system architectures with orchestration patterns, tool schemas, and performance evaluation. Use when building AI agent systems, designing agent workflows, creating tool schemas, or evaluating agent performance.
> agent messaging. Use when building multi-agent systems, defining tool interfaces, or implementing agent-to-agent communication.
> Design multi-agent orchestration with workflow DAGs, routing, handoff protocols, and state management. Use when building pipelines of specialized agents, designing fan-out/fan-in patterns, or implementing fault-tolerant workflows.
> Multi-agent DAG orchestration for workflows where AI agents collaborate via dependency graphs, covering agent spawning, output merging, and quality evaluation. Use when a task needs multiple specialized agents or to parallelize AI work.
> This skill should be used when the user asks to "evaluate LLM output quality", "set up LLM-as-judge", "build an eval rubric", "compare model outputs pairwise", or "measure agent quality".
> This skill should be used when the user asks to "batch LLM requests", "should I use the batch API", "estimate batch vs realtime cost", "design a bulk LLM job", or "process thousands of prompts cheaply".
> OpenAI Codex CLI and cross-platform skill authoring. Use when setting up Codex CLI, converting or syncing skills between Claude Code and Codex, configuring agents/openai.yaml, or validating cross-platform skill compatibility.
> Context management engine for AI coding agents. Use when building agent memory systems, optimizing context windows, allocating token budgets, designing RAG pipelines for code, or managing persistent multi-session agent state.
> This skill should be used when the user asks to "build a computer-use agent", "automate a GUI with an AI agent", "when to use computer use vs an API", "make browser automation reliable", or "design screenshot-driven agent actions".
> This skill should be used when the user asks to "decide reasoning effort", "set a thinking budget", "when to use extended thinking", "tune reasoning vs cost", or "should this task use a reasoning model".
> This skill should be used when the user asks to "estimate LLM costs", "count tokens in prompts", "optimize prompt token usage", "compare model pricing", or "reduce LLM API costs".
> Build MCP (Model Context Protocol) servers with tool definitions, resource providers, prompt templates, and transports. Use when exposing APIs to AI agents, building tool servers, converting OpenAPI to MCP, or creating MCP integrations.
> This skill should be used when the user asks to "audit prompts for safety", "check prompts for injection vulnerabilities", "manage a prompt catalog", "version control prompts", or "review prompt quality and compliance".
> Patterns for AI agents that learn from their own execution, detect failure modes, and improve autonomously. Use when building agents that get better over time, managing auto- memory, or designing self-correcting feedback loops.
> Prompt engineering and LLM evaluation. Use when optimizing prompts, designing prompt templates, evaluating LLM outputs, building agentic systems, implementing RAG, creating few- shot examples, or designing structured-output workflows.
> Security audit and vulnerability scanning for AI agent skills before install. Detects prompt injection, dangerous code, exfiltration, credential harvesting, and supply chain risks. Use when evaluating untrusted skills or gating installs.
> Author, lint, and publish skill packages that satisfy the library authoring standard. Use when creating a new skill, reviewing a skill PR, or fixing one that never activates.
| Programmatic web search with context isolation. Use this skill for any research task where you need to search the web, filter results, and extract specific information — without polluting your context window with raw HTML and boilerplate. This is the default skill for web research. Triggered by "search for", "look up", "find", "research", "what's the latest on", or any query that requires current web information. Also use when asked to "search and filter", "find the important parts", or "extract the key details" — any case where the user wants curated, noise-free content.