{
  "markdown": "# Hello Skills\n\nA curated collection of reusable agent skills for the [Agent Skills ecosystem](https://agentskills.io).\n\n## 1. About Agent Skills (`agentskills.io`)\n\n[Agent Skills](https://agentskills.io) defines an open format for packaging and sharing agent capabilities as portable skills.\n\nEach skill is usually organized as a folder with a `SKILL.md` file, and can include:\n- clear usage instructions\n- references and templates\n- helper scripts\n\nThis makes skills easy to discover, reuse, and version across different agent runtimes.\n\n## 2. Skills in This Repository\n\nThis repository currently includes the following skills (34):\n\n- `agent-first-product-strategy`: Reframe AI product strategy from human-first assumptions to agent-first positioning, metrics, and execution.\n- `agent-teams-guide`: Guide for orchestrating and controlling Claude Code agent teams.\n- `analogy-commentary`: Turn source content into a familiar analogy framework, then produce concise commentary angles and a short take.\n- `bento-slides`: Create, edit, and validate self-contained Bento HTML presentations with charts, tables, morph transitions, interactive states, motion, media, and speaker notes.\n- `china-model-selection-guide`: Compare China LLMs with practical, scenario-based model selection guidance.\n- `claim-ledger`: Turn research claims into a verifiable Claim-Evidence-Boundary ledger.\n- `codex-deep-research`: Run web-first deep research for comparisons, evaluations, market scans, and citation-heavy recommendations.\n- `cross-domain-thinking-toolbox`: 25 professional mental models for complex problem solving.\n- `debog-yourself`: Diagnose and escape psychological traps that block progress.\n- `deep-productivity`: Deep-work productivity framework (Building, Maintenance, Recovery).\n- `defrag`: Analyze code for refactoring opportunities and suggest the top 10 highest-value improvements.\n- `doko-page-reader`: Read and extract content from web pages via a locally connected Chrome browser and Dokobot bridge.\n- `ears-requirements`: Rewrite and validate requirements using EARS syntax.\n- `fastnote-cli-operator`: Operate the FastNote local notebook through natural language by mapping requests to note CRUD, search, pin, and tag commands.\n- `fix-orbstack-docker-pull`: Diagnose and fix Docker image pull failures on macOS with OrbStack (proxy, TUN, fake-ip, registry issues).\n- `follow-builders-lite`: Lightweight AI builders digest from the upstream zarazhangrui/follow-builders GitHub Actions feeds.\n- `hn-to-x-poster`: Review the current top Hacker News stories, select software or AI items, and publish a Chinese thread of at least 3 posts to X from an already logged-in browser session.\n- `hn-top10`: Fetch the current top Hacker News stories as structured agent-friendly output.\n- `instreet-operator`: Operate InStreet forum and Playground workflows through a bundled Python client with restored local account state.\n- `learning-first-principles`: Diagnose and optimize learning methods with first-principles thinking.\n- `longitudinal-cross-sectional-research`: Write deep research reports that combine longitudinal history with cross-sectional comparison.\n- `m365-oauth-mail`: Read Microsoft 365 / Office 365 school or corporate mail with OAuth2 device-code flow when password IMAP is disabled by the tenant.\n- `multi-agent-systems`: Design orchestrator-subagent LLM architectures.\n- `mungers-lattice`: Multidisciplinary decision analysis with Munger-style mental models.\n- `optimize-gpt-5-6-prompts`: Review, simplify, migrate, and create prompts for GPT-5.6 and the GPT-5.6 family.\n- `qm-reader-data`: Read articles, sources, and translations from the QMReader backend (rss.qiaomu.ai) via a bundled Python script with zero dependencies. Flags disabled feed sources in listings and explains 404s instead of failing silently.\n- `research-content-router`: Route research-to-content workflows from research through synthesis to publishable output.\n- `resume-builder`: Generate and revise job resumes from raw notes, existing resumes, career histories, or profile snippets.\n- `retrospective-master`: Structured retrospective coaching using the GRAI method.\n- `saas-agent-toolkit`: Turn SaaS capabilities into agent-usable tool contracts with guardrails, approvals, and auditability.\n- `url-to-markdown`: Convert a public webpage URL into a reusable Markdown file with a bundled script and agent-friendly execution flow.\n- `vibe-design`: Design, specify, implement, or review AI-native and Agent product interfaces with product intent, domain semantics, GenUI/A2UI controls, and evidence-based evaluation.\n- `x-thread-poster`: Post multi-part X/Twitter threads through Chrome DevTools MCP using the user's logged-in browser session.\n- `x-tweet-ego`: Post single tweets to X (Twitter) with ego-browser, with a battle-tested flow and known pitfalls (contenteditable composer, dual composer selectors, background-tab rAF freeze, React state sync).\n\n## 3. Quick Start\n\nInstall this skill pack:\n\n```bash\nnpx skills add https://github.com/hexbee/hello-skills\n```\n\n## 4. Related Links\n\n- [Agent Skills Doc](https://agentskills.io)\n- [Anthropic Skills](https://github.com/anthropics/skills)\n- [Skills Specification](https://agentskills.io/specification)\n- [Skills NPM](https://www.npmjs.com/package/skills)\n- [Vercel Agent Skills](https://github.com/vercel-labs/agent-skills)\n",
  "bytes": 5367,
  "sha": "4f0c56e386e1b98eb9d58db5b4cd3f60513ce6329457f9416153dd99202f58ac",
  "repo_slug": "hexbee/hello-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/skl_hexbee_hello_skills_deep_productivity_048ee85f/readme"
}