- 📁 references/
- 📁 updates/
- 📄 LICENSE
- 📄 SKILL.md
Analyze repository structure and generate or update standardized AGENTS.md files that serve as contributor guides for AI agents. Supports both single-repo and monorepo structures. Measures LOC to determine character limits and produces structured documents covering overview, folder structure, patterns, conventions, and working agreements. Update mode refreshes only the standard sections while preserving user-defined custom sections. Use when setting up a new repository, onboarding AI agents to an existing codebase, updating an existing AGENTS.md, or when the user mentions AGENTS.md.
Conception pipeline. Détecte le mode (epic/task/bug) selon le type d'issue ou le prompt et invoque les agents appropriés. Usage: /analyse [<issue#>] [<description>]
用于查询某地的今天天气
AI-augmented development controls, GitHub Copilot governance, LLM security, AI-generated code review per Hack23 Secure Development Policy
Deploy frontend assets to the IC. Covers certified assets, SPA routing with .ic-assets.json5, content encoding, and programmatic uploads. Use when hosting a frontend, deploying static files, or setting up SPA routing on IC. Do NOT use for canister-level code patterns or custom domain setup — use custom-domains instead.
Claude Code Manager — manage accounts, sessions, environments, and optimize token usage. Use when the user mentions switching Claude accounts, cleaning up sessions, environment snapshots, disk usage, token optimization, Claude Code health check, orphaned sessions, orphaned processes, tmp files, MCP audit, project bindings, session search, token usage history, account reorder, profiles, isolated, concurrent sessions, watch, rate limit, auto-switch, dashboard, session archive, setup wizard, recover, usage dashboard, usage compare, claudeignore, permission rules, statusline, status bar, or says "ccm", "doctor", "clean cache", "clean tmp", "session list", "session search", "env snapshot", "bind", "unbind", "reorder", "usage history", "init", "permissions audit", "statusline", "ccm watch", "ccm profiles", "ccm setup", "ccm recover".
iOS 26 / iPadOS 26 Liquid Glass design system for web and app development. Exact design tokens, component specs, layout patterns, and animation parameters from Apple's official Figma Community Kit.
语音领域每日论文速递。搜索最新语音大模型(Speech LLM、TTS、ASR、codec、speech generation)和语音前端(speech enhancement、noise suppression、beamforming、source separation、dereverberation)预印本论文,以毒舌但判断极准的 senior reviewer 口吻精读每篇论文,重点服务语音大模型和语音前端研究者;输出技术方案、实验结果、简介摘要和10分制评分,并将结果写入腾讯文档「每日论文速递」文件夹。触发场景:用户说"帮我找最新语音论文"、"搜语音预印本"、"语音论文速递"、"今天有什么语音论文"、"看看最新的 TTS/ASR/语音增强论文"等。
Advanced block functionality, event handlers (dig, tap, step-on, interact), extended data (simple_data, inventories, custom protobuf data), client extended data, and block mutation APIs. Use alongside define_new_block. Does not cover timers or circuits.
Add a new property to the AI agents database. Use when the user wants to add, create, or introduce a new column, property, field, or feature to track across all agents in the comparison matrix. Handles all four required steps - database updates, groups.json, table display, and GitHub issue templates.
Query Z.ai GLM Coding Plan usage statistics including quota limits, model usage, and MCP tool usage
- 📁 references/
- 📄 README.md
- 📄 SKILL.md
Strategic research framework that compresses months of market/competitive research into hours through structured power questions. Extracts unspoken industry insights, fragile market assumptions, and strategic attack surfaces from competitor data, reviews, and industry sources using parallel Exa-powered intelligence gathering. Use when user says "attack surface", "research the market", "competitive analysis", "analyze competitors", "find market opportunity", "stress-test this idea", "market research", "evaluate opportunity", "find blind spots", "market entry", or when they want to deeply understand a market, evaluate a new direction, find industry blind spots, assess a partnership, or analyze opportunities. Do NOT use for code review, testing, deployment, bug fixing, or implementation tasks. --- # Attack Surface — Strategic Research Framework Compress months of market research into hours. The difference between 3 hours and 3 months isn't the amount of information — it's knowing which questions actually matter. Instead of "summarize these" or "analyze the competition", this framework extracts: - **UNSPOKEN INSIGHTS** — what successful players understand that customers never say out loud - **FRAGILE ASSUMPTIONS** — beliefs the entire market is built on, and how they break - **ATTACK SURFACES** — the blind spots, the fragile consensus, the opening nobody is talking about ## When to Use - Entering a new market or vertical - Evaluating a new feature direction for an existing project - Assessing a partnership or platform opportunity - Stress-testing a business idea before committing - Finding competitive blind spots and underserved niches - Any strategic question that benefits from deep evidence-based analysis ## Workflow Overview 7 phases, alternating between automated intelligence gathering and user-guided analysis: | Phase | Name | Mode | Output | |-------|------|------|--------| | 1 | Briefing | Interactive | Research brief | | 2 | Source Collection | Automated (parall
