发现 Skills

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to 'open a website', 'fill out a form', 'click a button', 'take a screenshot', 'scrape data from a page', 'test this web app', 'login to a site', 'automate browser actions', or any task requiring programmatic web interaction.

Build RESTful APIs, GraphQL endpoints, and database-driven backend services. Use when designing APIs, implementing CRUD operations, handling authentication, or working with backend logic.

Expert at handling file uploads and cloud storage. Covers S3, Cloudflare R2, presigned URLs, multipart uploads, and image optimization. Knows how to handle large files without blocking. Use when: file upload, S3, R2, presigned URL, multipart.

Use this skill when building applications with Gemini models, the Gemini API, working with multimodal content (text, images, audio, video), implementing function calling, using structured outputs, or needing current model specifications. Covers SDK usage (google-genai for Python, @google/genai for JavaScript/TypeScript), model selection, and API capabilities.

Use when conducting performance-testing reviews with a multi-agent review workflow.

This file is the role-skill entry point for Claude Code.

Use this skill when the user asks to extend the requirements framework, add a new requirement type, create a custom strategy, add a custom calculator, modify framework architecture, create a requirement plugin, or otherwise build new requirement strategies. It also triggers on questions about strategy registration, calculator implementation, or auto-satisfaction mappings.

ROS2 Managed (Lifecycle) Node implementation with Clean Architecture (Python & C++)

Use Kimi for Chinese reading, long-context summaries, and structured extraction.

Guide for creating effective 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. Covers skill structure, YAML frontmatter, trigger configuration, and the 500-line rule.

Generate domain-specific Claude skills through a guided multi-agent workflow. Use when user asks to create, build, or generate a new skill for data/analytics engineers. Orchestrates research, clarification, decision-making, skill generation, and validation phases with human review gates. Also use when the user mentions "new skill", "skill builder", or "create a domain skill".

Triage a bug or issue by exploring the codebase to find the root cause, then create a GitHub issue with a TDD-based fix plan. Use when a user reports a bug, wants to file an issue, mentions "triage", or wants to investigate and plan a fix for a problem.

Implement authentication and authorization in Go Gin APIs. Covers JWT middleware, login/register handlers, role-based access control (RBAC), token refresh, and protected routes. Use when adding auth, login, signup, JWT tokens, user sessions, permissions, or role checks to a Gin application.

Search and retrieve knowledge from ingested sources, skill catalogs, git history, and consensus ledger. Use when the collective needs to query knowledge entries, browse skills, audit git commits, search deliberation history, or retrieve cataloged information.

Build elegant node sync/communication beyond Discord. Use when Tabula Myriad needs to establish direct HTTP-based inter-node communication, sync git states across nodes, broadcast consensus decisions, or verify node health without relying on Discord.

Writes and maintains technical documentation including API docs, README files, and Architecture Decision Records. Use when the user asks to document an API, write a README, create documentation, update docs, write an ADR, or document a design decision. Triggers on phrases like "write the README", "document this", "API documentation", "update the docs", "write an ADR", "create a changelog". Not for code comments (use code-review skill to flag missing comments).

Build AI agents with the OpenAI Agents SDK + Model Context Protocol (MCP) for tool orchestration. Supports multi-provider backends (OpenAI, Gemini, Groq, OpenRouter) with MCPServerStdio. Use this skill for conversational AI features with external tool access via the MCP protocol.

Git branch management, commit conventions, and PR creation workflow. Use for all tasks that require code changes, regardless of language or scope.

Transform requirements into software architecture documentation. Use when a user has requirements specs, user stories, or business cases and needs design documents, architecture documentation, or Architecture Decision Records (ADRs). Use when the user mentions "design doc", "architecture doc", "system design", or "technical design".

Autonomous daily digest of relevant arXiv papers in physics and machine learning based on your interests

Agency dashboard — shows agency-wide status, pipeline metrics, installed tools, and recent activity

Generates a complete, customized Non-Disclosure Agreement with plain English annotations, tailored to the specific parties and situation

Pack repositories into AI-friendly files with Repomix (XML, Markdown, plain text). Use for codebase snapshots, LLM context preparation, security audits, third-party library analysis.

Use when a task fails, a user corrects the assistant, a capability is missing, or a recurring better pattern should be logged for future improvement in Codex.