Agents
AI agents and automation
tracepact
by dcdeve
Behavioral testing and static analysis framework for AI agents with tool use. Tests that agents call the right tools, in the right order, with the right arguments. Audits SKILL.md files for security risks without executing the agent. Records and replays agent behavior via cassettes for deterministic CI testing.
@tank/skill-creator
by tankpkg
Create skills that extend AI agent capabilities with synthesized domain expertise. Covers skill anatomy, progressive disclosure, research workflow (books + web), writing conventions, and ecosystem patterns. Trigger phrases: "create a skill", "new skill", "build a skill", "skill about", "make a skill for", "update skill", "improve skill", "write a skill"
SKILL_NAME
by famaoai-creator
Extracts and processes data for {{SKILL_NAME}} purposes.
template-skill
by yonderlab
Replace with description of the skill and when the agent should use it.
uiux-excellence-guide
by Jpkovas
Create and refine visually strong interfaces with excellent UX, accessibility, and measurable performance. Use when requests involve designing new screens, redesigning existing UI, defining or evolving design systems/tokens, improving hierarchy/microcopy/motion, raising WCAG 2.2 compliance, improving touch ergonomics, or optimizing Web Vitals (LCP, INP, CLS) in web and app products.
recursive-language-model
by viktor-ferenczi
Recursive Language Model workflow for processing documents that exceed context window limits. Uses a persistent Python REPL and subordinate agents to chunk, search, and analyze large context files.
agent-activity-monitor
by famaoai-creator
Collects and visualizes statistics regarding the agent's activities, including skill usage, execution success rates, and task duration. Provides a data-driven dashboard for ecosystem health.
1ai-reach Agent Control Skill
by oyi77
If you need browser-based dashboards, there is no dedicated web UI yet
optimize-skill
by hyf0
Analyzes and optimizes an existing agent skill for conciseness, discoverability, and adherence to best practices. Use when a skill needs improvement, is too verbose, has poor activation rates, or fails to follow progressive disclosure patterns. Do NOT use for creating a new skill from scratch — use create-skill instead.
talent-requirement-generator
by famaoai-creator
New autonomous skill discovery.
raison-sdk
by aksuharun
"Raison JavaScript/TypeScript prompt management SDK. Use when working with the raison npm package to render templates or query prompt data."
@tank/llm-app-patterns
by tankpkg
Build production-grade LLM-powered applications — RAG systems, tool-using agents, structured output extraction, streaming responses, and cost optimization. Covers the full engineering stack for apps built on top of foundation models, not model training. Synthesizes Huyen (AI Engineering), Brousseau & Sharp (LLMs in Production), Bouchard & Peters (Building LLMs for Production), Lanham (AI Agents in Action), Arsanjani & Bustos (Agentic Architectural Patterns), Rothman (RAG-Driven Generative AI). Trigger phrases: "RAG", "retrieval-augmented generation", "vector search", "chunking strategy", "embedding", "reranking", "hybrid search", "tool use", "function calling", "tool calling", "agent", "agentic", "multi-agent", "orchestrator", "structured output", "JSON mode", "Instructor", "Pydantic", "streaming", "server-sent events", "SSE", "token streaming", "LLM cost", "model routing", "semantic cache", "prompt caching", "LLM evaluation", "LLM-as-judge", "RAGAS", "hallucination", "faithfulness", "golden dataset", "LLM in production", "LLMOps", "build with LLMs", "LLM application"
ralph-wiggum-loop
by xpepper
Use when context window exhaustion is a concern or when addressing a large volume of PR comments — spawns a fresh agent session per comment via an external shell loop. For an in-session approach, use pr-review-loop or copilot-review-loop instead.
seo-roast
by younesbenallal
Roast a landing page or article from an SEO perspective (technical + on-page + content/intent). Optionally generate a screenshot-rich HTML report.
agentic-flow-builder
by P47Phoenix
Guide for building dynamic agentic flows using ReAcTree hierarchical decomposition and Anthropic's workflow patterns. This skill should be used when users want to create complex multi-step agent workflows with deterministic gates, business rules, and comprehensive audit trails.
euler-advanced
by euler-xyz
Advanced features guide for Euler Finance V2 protocol. This skill should be used when implementing vault hooks, flash loans, debt transfer, fee flow mechanics, or EUL rewards. Triggers on tasks involving hooks, pause guardians, access control, flash loans, pullDebt, FeeFlowController, or RewardToken.
create-skill
by hyf0
Creates a new agent skill following best practices for structure, description writing, and progressive disclosure. Use when the user wants to author a new SKILL.md, scaffold a skill directory, or build a reusable skill. Do NOT use for improving an existing skill — use optimize-skill instead.
agent-browser
by linuxlewis
Browser automation using the agent-browser CLI. Use when user asks to browse websites, open webpages, interact with page elements, take screenshots, fill forms, click buttons, scrape content, or automate browser tasks.
retrospect
by cyberelf
This skill reviews the current chat session and GitHub Copilot instructions to identify user-reported issues that should become new lessons, detect violations of existing instructions, and update instructions accordingly to prevent future mistakes.
safe-update
by web3blind
Stateful and low-risk OpenClaw update workflow with precheck, backup, release-impact analysis, postcheck, auto-rollback, and cleanup. Use when user asks to safely update OpenClaw with rollback-ready backups and minimal manual steps.
search-intent-coverage
by younesbenallal
Determine what to cover to satisfy search intent by analyzing SERPs (preferred) or extracting competitor pages to Markdown.
ip-profitability-architect
by famaoai-creator
New autonomous skill discovery.
feature-dev
by huminglong
一个全面、结构化的特性开发工作流程，包含代码库探索、架构设计、质量审查和实现等专门阶段。在构建需要以下条件的新特性时使用：（1）在做出更改之前了解现有代码库，（2）通过系统性的提问澄清模糊的需求，（3）在实现之前设计周到的架构，（4）通过多维度的代码审查确保质量。非常适合涉及多个文件、需要架构决策、包含复杂集成或需求有些不明确的功能特性。
spec-implement
by anyoneanderson
Specification-driven implementation — Execute implementation from specs to PR. Reads issue-to-pr-workflow.md as playbook, enforces coding-rules.md as quality gates, tracks progress via tasks.md checkboxes with resume capability. English triggers: "Implement from spec", "Start implementation", "Execute spec tasks" 日本語トリガー: 「仕様書から実装」「実装を開始」「specタスクを実行」