google-adk-python_mrgoonie
Build AI agents with Google's Agent Development Kit (ADK) for Python. Use when creating tool-using or multi-agent systems, wiring sequential, parallel or loop workflow agents, integrating Google Search or code execution, evaluating agent performance, or deploying to Vertex AI Agent Engine or Cloud Run.
motion
>-
proxmox-auth
Authenticate to and manage a Proxmox VE cluster over SSH and the pvesh API. Use when querying cluster nodes, listing or controlling LXC containers and VMs, checking cluster and node status, or automating Proxmox administration.
analogy-commentary
Turn source content into a familiar analogy framework, then produce concise commentary angles and a short take. Use when the user asks whether a post, article, speech, or idea is “like” a known story, theory, faction, historical pattern, or strategic lens.
china-model-selection-guide
China model selection and task-routing guide for Doubao-Seed-2.0-Code, GLM-5, MiniMax-M2.5, and Kimi-K2.5. Use when users need to choose the best-fit model by input type, task complexity, engineering constraints, and delivery goals, including staged multi-model workflows.
claim-ledger
将研究与写作中的主张转成“Claim-Evidence-Boundary”可核验账本。用于在产出前强制补齐证据、反证、边界与可发布性判断，防止无依据断言并提升复用性。
codex-deep-research
Run web-first deep research in the current Codex session for comparisons, evaluations, market scans, recommendations, and other citation-heavy questions that need current information. Escalate to multi-agent work only when task complexity justifies it.
cross-domain-thinking-toolbox
Apply 25 professional mental models to solve complex problems. Use when: (1) facing multi-faceted challenges that require diverse perspectives, (2) stuck in single-minded approaches, (3) need innovative solutions, (4) making major decisions with multiple stakeholders, (5) understanding complex human behavior, or (6) seeking to break cognitive biases and adopt alternative viewpoints.
debog-yourself
Help users identify and escape psychological traps that are holding them back. Use when user feels stuck, unable to progress, facing a deadlock, or experiencing decision paralysis. Provide diagnostic frameworks and specific strategies to help users understand which trap pattern they're in and find a path forward.
deep-productivity
Master deep work productivity through the three types of work framework (Building, Maintenance, Recovery). Use when user needs to: (1) Build a sustainable deep work routine with just 1 hour/day, (2) Create vision/anti-vision for life direction, (3) Structure goals using the 10-year → 1-year → 1-month → 1-week hierarchy, (4) Apply project-based learning to bridge skill gaps, (5) Identify lever-moving tasks that actually progress goals, (6) Balance focus work with necessary recovery for creativity.
defrag
Analyze code for refactoring opportunities and suggest the top 10 highest-value improvements. Use this whenever the user says `/defrag`, asks to refactor, clean up code, improve code quality, identify code smells, or wants a ranked list of code improvements. This skill is for analysis only unless the user explicitly asks to apply a specific suggestion.
doko-page-reader
Read and extract content from web pages through a locally connected Chrome browser using Dokobot local bridge only. Use when an agent needs JavaScript-rendered pages, logged-in browser content, or pages that block headless scrapers and should be handled entirely through the user's local browser.
ears-requirements
Write and rewrite textual system requirements using EARS (Easy Approach to Requirements Syntax). Use when converting ambiguous natural-language requirements into structured statements, classifying requirements into EARS patterns, or reviewing requirement quality for missing triggers, states, and measurable responses.
fastnote-cli-operator
Operate the FastNote local notebook through natural language by mapping requests to note CRUD, search, pin, and tag commands. Use this whenever the user wants to create, list, inspect, update, pin, unpin, delete, or review FastNote notes or tags, even if they never mention the CLI. Execute the bundled zero-dependency script directly instead of relying on the project package runtime.
fix-orbstack-docker-pull
Diagnose and fix Docker image pull failures on macOS with OrbStack, especially Docker Hub EOF/TLS/manifest errors caused by system proxies, Clash/CyberClash/Mihomo/Surge-style TUN mode, fake-ip DNS such as 198.18.0.x, or unstable registry access. Use when `docker pull` or `docker manifest inspect` fails with EOF, SSL_ERROR_SYSCALL, failed to fetch anonymous token, failed to resolve reference, failed to copy, or registry-1.docker.io/auth.docker.io connectivity confusion.
follow-builders-lite
Lightweight AI builders digest from the upstream zarazhangrui/follow-builders GitHub Actions feeds. Use when the user asks for AI builder news, AI industry updates, /ai-style digests, summaries of top AI builders, or wants a safer local skill that reads public feed JSON without API keys, cron setup, delivery integrations, or local scraping.
hn-to-x-poster
Use this when the user wants to review Hacker News top 30 stories, select software or AI related items, and automatically publish a Chinese thread of at least 3 posts to x.com or Twitter from an already logged-in browser session.
hn-top10
Fetch the current top Hacker News stories and return agent-friendly structured results. Use this whenever the user explicitly asks about Hacker News or HN, and also when they ask for today's developer, startup, YC, or tech-community hot stories where Hacker News is a strong default source.
instreet-operator
Deprecated: this skill has been deprecated. Use this when working with InStreet forum or Playground flows. It restores account state from ~/.instreet, can auto-register when no local account exists, and routes all InStreet API requests through the bundled Python client. It has first-class commands for forum, groups, literary, arena, oracle, and games workflows, with raw api fallback for long-tail endpoints.
learning-first-principles
A cognitive framework based on learning first principles, providing learning method diagnosis, efficiency assessment, and optimization advice. Use when: (1) Diagnosing if current learning methods align with first principles, (2) Evaluating learning plan efficiency and time investment, (3) Analyzing learning behavior problems and providing improvement suggestions, (4) Determining if learning content is worth the time investment. Core principle chain: Self-learning → Induction → Self-output → Expression restructuring → Logical understanding → Practice.
longitudinal-cross-sectional-research
Write deep research reports that combine longitudinal history with cross-sectional comparison. Use when asked to analyze a company, product, technology, protocol, organization, market category, or person by tracing origins, milestones, strategy shifts, and then comparing it with current competitors, peers, substitutes, or the surrounding landscape.
multi-agent-systems
Design and implement multi-agent LLM architectures using the orchestrator-subagent pattern. Use when: (1) Deciding whether to use multi-agent vs single-agent systems, (2) Implementing context isolation for high-volume operations, (3) Parallelizing independent research tasks, (4) Creating specialized agents with focused tool sets, (5) Building verification subagents for quality assurance, or (6) Analyzing context-centric decomposition boundaries.
mungers-lattice
Multidisciplinary analytical engine using Charlie Munger's latticework of mental models. Applies cross-disciplinary thinking (math, physics, biology, psychology, economics) to dissect life and business decisions. Use when user presents a decision problem, investment question, or complex analysis request requiring deep rational analysis.
optimize-gpt-5-6-prompts
Review, simplify, migrate, and create prompts, tool descriptions, agent instructions, or prompt stacks for GPT-5.6 and the GPT-5.6 family. Use when a user provides a prompt and asks to optimize, critique, streamline, rewrite, upgrade, or adapt it for GPT-5.6, or explicitly invokes this skill to improve an existing prompt or draft one from scratch. Do not trigger merely because prompt text appears in unrelated code or documentation without an intent to create, evaluate, or change prompting behavior.
qm-reader-data
读取乔木阅读（rss.qiaomu.ai）的数据：最新文章列表、订阅源列表、单篇文章正文、中文翻译和乔木改写版。当用户想查看乔木/QMReader 上有什么新文章、想读某篇文章内容、想让 AI 总结或翻译乔木上的文章，或在 qmreader-ios 项目中调试涉及 /api/entries、/api/sources、/api/entry 的数据问题时，都应使用本 skill——即使用户没有明确提到"乔木"或"QMReader"，只要意图是获取这个 RSS 数据源的内容就适用。
research-content-router
将“研究 + 内容生产”任务按 A/B/C 分级调度，先收敛受众/目标/载体/角度，再走 Research→Synthesis→Content 流水线，输出可发布内容与证据链。适用于需要结论可信、结构稳定、可复用素材沉淀的写作任务。
resume-builder
Generate and revise job resumes from raw notes, existing resumes, career histories, or profile snippets. Use when Codex needs to create, redesign, tighten, or review a resume/CV, especially for Chinese or English A4 resumes, PDF/HTML output, first-screen hiring signal, skill ordering, pagination balance, header/contact layout, or reframing an engineering background for AI-focused roles.
retrospective-master
Professional retrospective coach based on the GRAI model (Goal-Result-Analysis-Insight) to guide users through structured retrospectives. Transform experiences into lessons, and lessons into capabilities. Use when: (1) Systematic review needed after project/event completion, (2) Learning from failures, (3) Summarizing and replicating success experiences, (4) Creating improvement action plans.
saas-agent-toolkit
Design agent-usable SaaS tool systems using six reusable tool shapes (Search, Summarize, Draft, Update, Notify, Approve) plus connectors and policy guardrails. Use when turning SaaS features into reliable agent actions with clear contracts, permissions, audit trails, and approval gates.
url-to-markdown
Convert a public webpage URL into Markdown and save it as a reusable `.md` file with the bundled script. Prefer `https://r.jina.ai/<url>` first, and only fallback to `https://markdown.new/` if `r.jina.ai` is unavailable. Use this whenever the user wants to turn a public webpage, article, documentation page, blog post, release note, or reference URL into Markdown for reading, archiving, summarizing, extraction, RAG prep, or downstream agent reuse, even if they do not explicitly mention markdown or saving a file.
vibe-design
Design, specify, implement, or review AI-native and Agent product interfaces with explicit product intent, domain semantics, controlled GenUI/A2UI behavior, design-system constraints, complete interaction states, and evidence-based evaluation. Use for Agent dashboards, copilots, conversational interfaces, generative reports, AI workflows, design specs, information architecture, component selection, anti-generic visual direction, UI critique, or turning an ambiguous AI product request into reusable design declarations and acceptance criteria.
x-thread-poster
Post multi-part X/Twitter threads through Chrome DevTools MCP using the user's logged-in browser session. Use when Codex is asked to open x.com, compose, publish, or automate a thread/multiple posts, especially when a source link must be included or the post style must be adapted from provided content.
x-tweet-ego
用 ego-browser 在 X (Twitter) 上发推文/发帖/引用推文。当用户要求发布推文、测试发帖、引用某条推文发自己的评论、或提到 x.com 发帖流程时使用。包含实测验证过的可靠流程和已知坑位（contenteditable composer、双 composer 选择器、后台 tab rAF 冻结、截图不可用兜底、视口外点击落空、引用入口键盘导航、标签页被替换、React 状态同步等），避免 agent 重新踩坑。
agent-first-product-strategy
Reframe AI product and SaaS strategy from human-user assumptions to agent-first execution. Use when redefining product positioning, success metrics, API/docs priorities, go-to-market, or roadmap decisions for an AI-native market where agents are primary software users.
agent-teams-guide
Guide for orchestrating and controlling Claude Code agent teams. Use when working with or managing multi-agent team coordination in Claude Code, including: (1) Creating and starting agent teams, (2) Controlling teammates (display modes, task assignment, delegation), (3) Best practices for parallel work, (4) Troubleshooting team issues. Covers concepts like team lead, teammates, shared task lists, and inter-agent messaging.
bento-slides
Create, edit, and validate self-contained Bento slide decks (`.bento.html`) by authoring the plain JSON document inside the `#bento-doc` script block. Use when Codex needs to turn source material into an interactive presentation, create a deck from the bundled Bento template, revise an existing Bento deck, or add charts, tables, morph transitions, state slides, motion, media, and speaker notes while preserving the embedded editor runtime.
goodvibes-memory
Documents the .goodvibes/memory/ cross-session memory files (decisions, patterns, failures, preferences): what's written automatically, what you should read and write, and the exact JSON shape of each file. Load at the start of a task to check prior context, and before finishing to record what you learned.
intel-mastery
Usage guide for the goodvibes intel server's 15 structure-aware tools (code_read, code_grep, code_glob, code_surface, code_safe_delete, api_routes, api_spec, api_validate, db_schema, component_tree, hook_dependencies, client_boundary, layout_analysis, scaffold, structural_edit). Load when working in a codebase and deciding between intel tools and native Read/Grep/Glob/Edit.
project-onboarding
Step-by-step approach to mapping an unfamiliar codebase's architecture using the goodvibes intel server's analyzers before making changes to it. Load when starting work in a codebase you haven't worked in before.
review-scoring
The refutation-based review rubric used by the refutation-reviewer agent and the Write-Review-Fix-Confirm (WRFC) workflow template. A defect list with severity, not a single pass/fail score. Load when reviewing a change or deciding whether a review's findings clear the bar to merge.
service-integration
How to reach authenticated APIs and project databases through the connect trust boundary. Register a service or connection, store credentials safely, then call api_request or db_query. Load when a task needs an authenticated HTTP call or a live database query (not a public URL; use native WebFetch for that).
task-orchestration
Decomposing work into parallel subagent tasks using native Workflow/Task tooling and the Write-Review-Fix-Confirm (WRFC) template. No background daemon, no runtime engine. Load when planning how to split work across multiple agents.
slidev
Use this skill when working with Slidev presentations. Helps with slide syntax, frontmatter configuration, layouts, animations, code highlighting, diagrams, themes, and exporting. Prevents common mistakes like incorrect asset paths, deprecated features, and non-existent layouts.
Subagent-Driven Development
Execute implementation plan by dispatching fresh subagent for each task, with code review between tasks
Tracing Knowledge Lineages
Understand how ideas evolved over time to find old solutions for new problems and avoid repeating past failures
Condition-Based Waiting
Replace arbitrary timeouts with condition polling for reliable async tests
Test-Driven Development (TDD)
Write the test first, watch it fail, write minimal code to pass
Testing Anti-Patterns
Never test mock behavior. Never add test-only methods to production classes. Understand dependencies before mocking.
Getting Started with Skills
Skills wiki intro - mandatory workflows, search tool, brainstorming triggers
Requesting Code Review
Dispatch code-reviewer subagent to review implementation against plan or requirements before proceeding
Page 792 of 1652 · 82593 results