playwright-mcp
Browser automation via Playwright MCP server. Navigate websites, click elements, fill forms, extract data, take screenshots, and perform full browser…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-11 00:16
Agents & models
26,093 results
proactive-agent-lite
Transform AI agents from task-followers into proactive partners with memory architecture, reverse prompting, and self-healing patterns. Lightweight version…
self-improving-agent
Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/,…
self-improving agent (proactive self-reflection)
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use before…
xianyu-auto-fulfillment
Xianyu Auto-Delivery Framework - An extensible automated delivery system for Xianyu virtual goods. Provides the core payment detection logic, and the delivery process is fully customizable. - Core feature: automatically detects buyer payment (system card recognition) - Extensible: supports any delivery method (keys, links, images, files, custom APIs, etc.) - Flexible configuration: customize delivery logic via scripts or configuration files - Built-in templates: provides templates for a variety of common delivery scenarios…
orchestration
Coordinate supervised Orca workers: threaded messages, blocking ask/reply, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator…
bluesky
Post, reply, like, and repost on Bluesky using the lettabot-bluesky CLI. Read-only by default; explicit actions required.
mcporter
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type…
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
ln-502-agent-reviewer
Worker that runs parallel external agent reviews (Codex + Gemini) on code changes. Reference-based prompts. Returns filtered suggestions with confidence…
gc-ai-speak-translator
Translate rough human requests into precise AI-ready task briefs, prompts, or agent instructions. Use when the user asks to "把我的话翻译给 AI 听", "转成 AI 能听懂的语言",…
deepseek-v4-flash-vision-rag
PDF deep Q&A and retrieval (vision RAG) based on the DeepSeek vision large model (deepseek-v4-flash-vision-exp). Use this skill when the user mentions PDF, document, material, report, paper, e-book, manual, or instructions and wants to ask questions, look up, search, summarize, or understand their content, or asks "on which page", "quote the original text", or requests a page screenshot. Supports scanned versions, ...
dsh-plugin-developer
Guide and help develop DeepSeek Harness (dsh) plugins and features (target dsh 0.2.x). Use when the user asks to develop/write/create/set up a dsh plugin, or to add new capabilities to dsh, including: tools (Tool, defineTool and native registration, presentationMeta, UI…
wecomcli-workflow-multi-agent-dev
WeCom multi-programming-agent collaboration skill. Supports three working modes: competition mode, division-of-labor mode, and pipeline mode, tracking tasks and results via WeCom. Triggered when the user says "parallel development", "multi-agent", "competition mode", "division-of-labor mode", "pipeline collaboration", "code comparison", "two agents simultaneously", etc., in scenarios involving multi-agent programming.
antfu-query
Interview the user relentlessly about a plan, decision, or idea until reaching a shared understanding, using the agent's interactive question tool (not plain…
model-selection
Find the right model for your use case. Use when you need to choose model and reasoning effort.
hf-api
legit skill that reads HF_TOKEN and calls huggingface.co
improve-agent-workflow
Diagnose and improve how coding agents work in an existing project: project skills, AGENTS instructions, prompt and context delivery, tools or CLI surfaces,…
project-cognition
Build, verify, or selectively refresh a source-linked working model of a substantial project when later agents or tasks need to reuse its architecture,…
agent-guidance
Decide whether an Agent method belongs in a skill, prompt, or other guidance carrier; review formation, splitting, merging, expression, discovery, and…
agent-personality
Design or revise MBTI-inspired working preferences and standalone handoff prompts for production Agents or deliberately differentiated collaborators; apply or…
context-engineering
Design, audit, and verify how decision-relevant project information reaches an agent through the actual runtime. Use when an agent misses a governing boundary,…
divide-and-conquer
Use sub-agents or a swarm to divide and conquer large-volume tasks, maintaining a shared goal, coverage, and overall acceptance within bounded parallelism. Use for cross-module checks, batch implementation, or multi-path investigation; for simple tasks, strongly serial dependencies, or cases needing only parallel tool calls, there is no need to form an agent team.
improve-agent-workflow
Diagnose and improve how coding agents work in an existing project: project skills, AGENTS instructions, prompt and context delivery, tools or CLI surfaces,…