Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 437 files from 1 744 authors, of which 61 785 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
| 雅思阅读精读教练 v3.0。同义替换提取 + T/F/NG 逻辑拆解 + 段落结构分析 + 错题诊断 + 数据持久化。 触发方式：/ielts-reading、「分析阅读」「这道为什么错」「同义替换」「阅读训练」
| 雅思数据驱动诊断 v3.0。读取所有历史数据，生成诊断报告 + 个性化备考计划。 触发方式：/ielts-diagnosis、「诊断」「备考计划」「我现在的水平」「给我制定计划」
| 雅思词汇训练 v3.0。间隔重复 + 同义替换专项 + 写作高频词 + 数据持久化。 触发方式：/ielts-vocab、「背单词」「同义替换」「词汇练习」「写作词汇」
| 启动本地 IELTS Dashboard。React + Vite，浏览器查看备考数据可视化。 触发方式：/ielts-dashboard、「打开仪表盘」「看看进度」「dashboard」
| 雅思写作批改教练 v3.0。四维评分 + 句子级标注 + 改写对比 + 审题检查 + 数据持久化。 触发方式：/ielts-writing、「批改作文」「帮我看看这篇」「审题」「写作练习」
| Track and surface the estimated water cost of Claude interactions. Every query has a physical footprint - data centers need cooling, electricity needs generation. This skill adds environmental accountability by estimating water consumption per session and surfacing it at meaningful moments. Not to induce guilt, but to create awareness of the physical cost of intelligence.
| Before any destructive or irreversible operation (rm -rf, DROP TABLE, DELETE, blast radius → confirm explicitly → document what happened. Chains pre-mortem and you-sure with built-in documentation. No dangerous operation executes without ceremony.
| When a user asks how long a task will take, requests a time estimate, or before starting any non-trivial coding task, immediately run scripts/estimate_task.py to analyze the codebase scope and provide a data-driven time estimate. Show the estimate breakdown, risk factors, and checkpoint recommendations without asking.
| When a user uploads or references a data file (CSV, JSON, XLSX, TXT, LOG) or any file larger than 100KB, immediately estimate token cost using scripts/estimate_size.py. If >30k tokens, chunk the file and summarize each chunk. If smaller, run quick inspection. Return a safe preview and summary without asking the user what to do.
| Before ANY significant development task (new feature, refactor, integration, migration), run a complete planning ritual by orchestrating other skills in (estimate time) -> final confirmation. Do not start coding until the battle plan is approved.
| When debugging frustration appears ("why isn't this working?", "it should work", fix → verify. Prevents the common failure of jumping to fixes before understanding the problem. An elixir that chains rubber-duck and prove-it with investigation.
| Leaves notes for future Claude sessions in .claude/breadcrumbs.md. At session end or after significant work, records what was tried, what worked, what failed, and context for next time. On session start, reads breadcrumbs to understand history. Session-to-session memory without manual updates.
| Orchestration pattern for parallelizable tasks. When facing work that can be split into independent subtasks (research multiple topics, analyze multiple files, test multiple scenarios), spawn parallel agents and aggregate results. Use when subtasks have no dependencies on each other.
| Syncs Granola meeting notes to Obsidian vault. Reads from Granola's local cache to extract meeting metadata and notes, then creates properly formatted markdown files with frontmatter. Also handles manual transcript formatting when cache doesn't have content.
| comments created, missing tests, stale references, incomplete error handling. Activates after implementing features or fixes. The cleanup that always gets skipped.
| When a session contains a significant failure, misunderstanding, or repeated mistake, analyse the root cause and draft a new skill that would have prevented it. The skill library should grow from real failures, not hypothetical improvements. Every painful debugging session is a skill waiting to be written.
| Before adding abstraction, asks "do we need this now?" Activates when proposing factories, abstract classes, config-driven behavior, or "for future extensibility." Resists over-engineering. Three similar lines are better than a premature abstraction.
| Orchestration pattern for large-scale processing where work is distributed, processed independently, then combined. Map phase splits and processes, Reduce phase aggregates results. Use for codebase-wide analysis, bulk transformations, or any task where "do X to everything, then summarize."
| Generates Obsidian .base files from natural language descriptions. Translates requests like "show me all active project notes sorted by date" into valid .base YAML with filters, formulas, views, and summaries. Activates on "create base", "make a view", "show me all notes where", "dashboard", or when user wants structured views of their vault.
| When activated, respond entirely in Geordie dialect from Newcastle upon Tyne. Use proper Geordie words, phrases, and grammar. Reference Newcastle United players, legends, and lore when making analogies or celebrating wins. Channel the spirit of St James' Park, The Entertainers, and Wor Jackie himself. Howay the lads!
| Generates Obsidian .canvas files from intent. Takes a description of what you want to visualise and produces valid JSON Canvas — mind maps, flowcharts, kanban boards, research canvases, project overviews. Activates on "create canvas", "make a board", "visualise", "map out", "mind map", or when spatial organisation of ideas is needed.
| Initialises an Obsidian vault for Claude Code workflows. Sets up folder structure, frontmatter conventions, templates, starter .base views, and a CLAUDE.md that describes the vault so future sessions understand it instantly. Activates on "set up obsidian", "init vault", "new vault", or first contact with an Obsidian project that has no CLAUDE.md.
| Creates well-structured Obsidian notes with proper frontmatter, wikilinks, and template adherence. Detects available CLI (official, Yakitrak, or direct file write) and uses the best option. Reads vault conventions from CLAUDE.md before creating. Activates on "create note", "new note", "add to obsidian", or when creating markdown files in an Obsidian vault.
| Manages daily notes workflow in Obsidian. Appends tasks, session logs, and learnings to today's daily note. Creates the daily note if it doesn't exist. Bridges Claude Code sessions to your daily note so nothing gets lost. Activates on "add to daily", "log this", "daily note", or end of session when daily notes are enabled.
| Searches an Obsidian vault intelligently — combines CLI search, frontmatter filtering, content grep, and wikilink traversal. Goes beyond keyword search to find notes by property, by link, by folder, and by content. Activates on "find in vault", "search vault", "which note has", "where did I write about", or when looking for specific notes in Obsidian.
| End-of-session ritual that syncs Claude Code session artifacts to an Obsidian vault. Chains breadcrumbs, retrospective, note creation, and daily driver into a single flow. Creates session notes, updates daily note, and leaves breadcrumbs. Activates on "sync to obsidian", "save session", "end session", or when user wraps up significant work in a vault-connected project.
| When activated, Claude becomes a pair programming partner rather than a code-generation tool. Explains reasoning, teaches patterns, asks questions that build understanding, and adjusts depth based on the person's goals. Balances getting work done with building lasting knowledge. Activate with "let's pair on this" or by setting a learning focus at session start.
| Orchestration pattern for sequential, dependent tasks. When work must flow through stages where each stage depends on the previous (design → implement → test → review), structure as a pipeline with explicit handoffs. Each stage completes before the next begins.
| Before declaring any task complete, actually verify the outcome. Run the code. Test the fix. Check the output. Claude's training optimizes for plausible-looking output, not verified-correct output. This skill forces the verification step that doesn't come naturally. No victory laps without proof.
| Before starting ANY significant task (feature build, refactor, integration, migration, or architectural change), first imagine the project has failed. Generate 3-5 specific failure scenarios, assess risk levels, identify mitigations, then adjust the implementation plan to address high-risk items FIRST. Do not start coding until the pre-mortem is acknowledged.
| When refactoring, rewriting, or migrating critical code paths, orchestrate a and prove-it with built-in implementation phase. Prevents "refactor broke production" disasters. Activates on "refactor", "rewrite", "migrate", or "clean up" for non-trivial code.
| When a user is stuck, frustrated, or describing a problem vaguely, do NOT immediately suggest solutions. First, force structured problem articulation have you tried? Only after the problem is clearly defined, propose solutions.
| After completing a significant task or experiment, documents what worked, what failed, and key learnings. Activates when a multi-step task finishes or when user says "done", "finished", "that worked", or asks for a summary. Failed attempts get documented first - they're read more than successes.
| Meta-skill for creating well-structured skills with proper progressive disclosure. When user wants to create a new skill, guide them through Ensures skills follow the repository conventions and are immediately usable.
| Before building on assumptions, validates them first. Activates when making claims about how code works, what exists, or why something happens. Prevents assumption cascades where one wrong guess leads to a completely wrong solution.
| When Claude discovers a non-obvious solution, unusual pattern, or hard-won insight during a session, automatically forge it into a new skill. Don't just note the learning - create the actual skill file so future sessions future sessions → repeat.
| When facing architectural decisions, technology choices, or strategic trade-offs, present options as a structured comparison and require explicit trade-off acknowledgment before proceeding. Triggers on words like "should we", "which approach", "what's the best way", or when Claude is about to recommend one approach over alternatives. Never present a single recommendation without showing viable alternatives first.
| Before starting any significant task, force explicit evaluation of available skills. For each potentially relevant skill, state YES/NO with reasoning. Only proceed to implementation after skills have been consciously evaluated and activated. Prevents the ~50% "coin flip" activation rate that occurs when skills are passively available but not deliberately considered.
| Before making changes, verifies they match what was actually requested. Activates when about to modify files, add features, or refactor code. Catches scope creep before it happens - no "while I'm here" improvements.
| Before modifying shared code (utilities, types, configs, base classes), traces all callers and dependents first. Activates when editing files in shared/, utils/, lib/, or anything imported by 3+ files. Prevents "fixed one thing, broke three others."
| Before ANY destructive, irreversible, or high-impact action, pause and surface database changes, production deployments, mass updates, permission changes, or anything that can't easily be undone. Require explicit confirmation before proceeding. Never auto-execute dangerous operations.
| are you looking for, what would it look like, where would it live, what else might it be called. Activates on "find", "where is", "search for", or when exploration begins. Prevents grep-and-pray.
| Extracts YouTube video transcripts and saves them as structured markdown files with metadata and timestamped content. When a user shares a YouTube URL, IMMEDIATELY runs the extraction script, creates a local folder, and saves the transcript. Handles both manual and auto-generated captions.
>- This skill is specifically for the Clawpatch CLI (openclaw/clawpatch, says "review with clawpatch", "run clawpatch", "clawpatch fix", "find bugs with clawpatch", "clawpatch report/findings", "clawpatch open-pr", wants to dispatch subagents to fix Clawpatch findings in parallel, or otherwise names Clawpatch or one of its commands. Do NOT use it for generic "review this code", "find bugs", or "code review" requests that don't involve Clawpatch — those belong to a different tool.
>- This skill should be used when the user names chrome-devtools-axi, asks to "execute npx -y chrome-devtools-axi", wants Chrome DevTools Protocol browser automation through the AXI CLI, or needs token-efficient accessibility snapshots, stale-ref-safe clicks/fills, console/network inspection, screenshots, Lighthouse, or performance traces from a Chrome session. Do NOT use for simple web search/static extraction, stealth/anti-detection browsing, or non-Chrome browser targets.
>- Use Camofox/Camoufox as an opt-in anti-detection browser server for agent workflows that need cloaked browsing. Covers npm/npx startup, OpenClaw plugin tools, REST API commands, session/tab workflow, environment variables, process-scoped CAMOFOX_URL for Hermes, and hard rules such as always sending userId and re-snapshotting after state-changing actions. Do not use for normal web search, text extraction, curl fetches, or ordinary browser automation.
>- This skill should be used when the user names Charmbracelet VHS, asks to use the `vhs` CLI, wants a terminal recording, terminal GIF, terminal MP4/WebM, `.tape` file, scripted terminal demo, or a reproducible command-line screencast. Do NOT use for generic browser recording, full desktop screen capture, or unscripted secret-bearing interactive sessions.
Complete DataForSEO API integration for SEO data and analysis. Use when the user asks for keyword research, search volume, SERP analysis, backlink audits, competitor analysis, rank tracking, domain authority, technical SEO audits, content monitoring, Google Trends, or any SEO-related data queries. Covers all DataForSEO APIs including SERP, Keywords Data, DataForSEO Labs, Backlinks, OnPage, Domain Analytics, Content Analysis, Business Data, Merchant, App Data, and AI Optimization APIs. Outputs CSV files.
Devicetree management for Zephyr RTOS. Covers syntax, bindings, overlays, Hardware Model v2 (HWMv2), and advanced node/property deletion patterns. Trigger when defining hardware topology, creating overlays, or mapping pins and peripherals.
USB and CAN connectivity for Zephyr RTOS. Covers USB device stack configuration (CDC ACM, HID, MSC), CAN controller integration, and professional USB-to-CAN adapter patterns including buffering and protocol packetization. Trigger when adding USB interfaces, implementing CAN bus communication, or building hardware diagnostic tools.
Bluetooth Low Energy (BLE) integration for Zephyr RTOS. Covers GATT Services/Characteristics, GAP advertising, connection parameters, power optimization strategies, and the professional Send-When-Idle design pattern. Trigger when adding BLE connectivity, optimizing battery life for wireless devices, or implementing custom GATT profiles.
IP networking fundamentals for Zephyr RTOS. Covers IoT protocol selection (LwM2M, CoAP, MQTT), IP stack configuration and trimming (IPv4/IPv6, UDP/TCP), and professional SDK integration as Zephyr modules using West manifests. Trigger when building cloud-connected applications, optimizing network memory usage, or integrating external cloud SDKs.
Custom board bringup for Zephyr RTOS using Hardware Model v2 (HWMv2). Covers directory structure, board.yml metadata, core configuration files (Kconfig, defconfig, CMake), and revision management. Trigger when creating new board definitions or porting Zephyr to custom hardware.
Build system management for Zephyr RTOS. Covers West workspace initialization, manifest management, Sysbuild multi-image builds, Kconfig symbols, and CMake integration. Trigger when setting up workspaces, configuring builds, or troubleshooting build-time errors.
Zephyr RTOS development — boards and devicetree, the build system (west, Kconfig, CMake, sysbuild), drivers and peripherals, BLE and networking, the kernel, storage, power, testing and debugging, security and OTA. Use this for ANY Zephyr RTOS or embedded-firmware task on a Zephyr project; it routes you to the right specialized skill via the zephyr-cli registry.
Industrial communication protocols for Zephyr RTOS. Covers Modbus RTU (serial), Modbus TCP (Ethernet/Wi-Fi), and CANopen basics. Trigger when building factory automation controllers, industrial sensors, or medical equipment interfaces.
Integration of advanced IoT protocols for Zephyr RTOS. Covers OpenThread mesh networking, Matter-over-Thread device development, Golioth Cloud SDK patterns, and LoRaWAN basics. Trigger when building smart home devices, wide-area sensor networks, or cloud-integrated hardware fleets.
Hardware interfacing and peripheral management for Zephyr RTOS. Covers the sensor subsystem (channels, triggers, fetch/get), pin control (Pinctrl) and multiplexing, GPIO management using Devicetree specs, and SoC-level hardware configurations. Trigger when adding new hardware components, configuring pinmux, or developing sensor-based applications.
Essential Zephyr RTOS kernel services. Covers thread lifecycle and priority, the logging subsystem for diagnostics, and the interactive shell for real-time hardware inspection and debugging. Trigger when writing application flows, adding logging to modules, or creating interactive CLI commands.
Advanced Zephyr RTOS kernel services. Covers inter-thread communication using Zbus (pub/sub), behavioral management with the State Machine Framework (SMF), background processing via work queues, and persistent configuration with the Settings subsystem. Trigger when building modular application architectures, complex state-driven logic, or requiring persistent data storage.
Claude Skills — questions
Answers built from the skills we actually parsed.