Your AI agents deserve better than unverified skills!
Built on trust, grown by the community.
Trust Layer for AI Agent Skills
Scanned & Verified by
mcp-scan
SemgrepTrivyOSV-ScannerOWASPSnykSocket.devVirusTotalCrowdStrikemcp-scanSemgrepTrivyOSV-ScannerOWASPSnykSocket.devVirusTotalCrowdStrikeFor Product Managers — Skills that make AI actually useful for your daily work. No code required.
tools
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
tools
tools
development
testing
development
From frontend to embedded systems — skills for every engineering specialisation.
Data pipelines, ML models, BI dashboards, and analytics workflows.
PRDs, roadmaps, OKRs, user stories, and stakeholder communication.
SEO, content strategy, growth, brand, analytics, and campaign automation.
Process automation, supply chain, IT ops, and business process analysis.
Agile, Scrum, program delivery, stakeholder management, and reporting.
UI/UX, graphic design, motion, design systems, and user research.
Outreach, deal qualification, CRM automation, and revenue operations.
Job descriptions, HR policies, onboarding, people analytics, and compliance.
Contract drafting, GDPR, IP, legal operations, and regulatory analysis.
Ticket automation, knowledge base, escalation workflows, and CX management.
Copywriting, technical writing, video scripting, journalism, and translation.
Financial modelling, FP&A, accounting automation, audit, and treasury.
Academic writing, curriculum design, research synthesis, and instructional content.
Medical writing, health informatics, clinical research, and regulatory submissions.
Property listings, market analysis, lease documents, and client communication.
Agent Skills are modular capabilities that extend AI coding assistants. Each skill consists of a SKILL.md file with instructions, plus optional scripts and templates. They work with Claude Code, OpenAI Codex CLI, and ChatGPT.
Download the SKILL.md file and place it in your skills directory. For Claude Code: ~/.claude/skills/ (personal) or .claude/skills/ (project). For OpenAI Codex CLI: ~/.codex/skills/. The AI automatically discovers and loads skills from these locations.
The gold shield badge indicates that the skill comes from a verified publisher — a trusted, public GitHub repository. We vet sources and display repository metadata so you can make informed decisions.
All skills are sourced from public GitHub repositories with verified publishers. We display star counts, repository info, and publisher details. As with any open-source software, we recommend reviewing the content before installing.
Yes! Skills are modular and designed to work together. You can combine skills for different tasks — for example, a code reviewer skill with a git automation skill.
Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting state, revision-checked mutations, and user-facing emergence.
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Use when you have a spec or requirements for a multi-step task, before touching code
