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. 79 551 files from 1 750 authors, of which 61 898 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.
Implement, write code, add a new screen, create a feature, new view, new processor, or wire up a new service in Bitwarden iOS. Use when asked to "implement", "write code", "add screen", "create feature", "new view", "new processor", "add service", or when translating a design doc into actual Swift code.
Write tests, add test coverage, unit test, or add missing tests for Bitwarden iOS. Use when asked to "write tests", "add test coverage", "test this", "unit test", "add tests for", "missing tests", or when creating test files for new implementations.
> Process raw source documents into wiki pages. Use when the user adds files to raw/ and wants them ingested, says "process this source", "ingest this article", "I added something to raw/", or wants to incorporate new material into their knowledge base.
> Health-check the wiki for contradictions, orphan pages, stale claims, and missing cross-references. Use when the user says "audit", "health check", "lint", "find problems", or wants to improve wiki quality.
> Answer questions against the knowledge base wiki. Use when the user asks a question about their collected knowledge, wants to explore connections between topics, says "what do I know about X", or wants to search their wiki.
> Set up a new Obsidian knowledge base with the LLM Wiki pattern. Use when the user wants to create a second brain, initialize a vault, set up a personal knowledge base, or says "onboard". Guides through an interactive wizard to configure vault name, location, domain, agent support, and tooling.
Use when checking skills for security or quality issues, reviewing audit results from skills.sh or Tessl, or remediating findings across published skills.
Generates a Mermaid flowchart diagram of dbt model lineage using MCP tools, manifest.json, or direct code parsing as fallbacks. Use when visualizing dbt model lineage and dependencies as a Mermaid diagram in markdown format.
Use when a user needs help triaging dbt-core to Fusion migration errors. Runs dbt-autofix first, then classifies remaining errors into actionable categories (auto-fixable, guided fixes, needs input, blocked).
Use when migrating a dbt project from one data platform or data warehouse to another (e.g., Snowflake to Databricks, Databricks to Snowflake) using dbt Fusion's real-time compilation to identify and fix SQL dialect differences.
Creates unit test YAML definitions that mock upstream model inputs and validate expected outputs. Use when adding unit tests for a dbt model or practicing test-driven development (TDD) in dbt.
Writes and executes SQL queries against the data warehouse using dbt's Semantic Layer or ad-hoc SQL to answer business questions. Use when a user asks about analytics, metrics, KPIs, or data (e.g., "What were total sales last quarter?", "Show me top customers by revenue"). NOT for validating, testing, or building dbt models during development.
Use when creating or modifying dbt Semantic Layer components — semantic models, metrics, dimensions, entities, measures, or time spines. Covers MetricFlow configuration, metric types (simple, derived, cumulative, ratio, conversion), and validation for both latest and legacy YAML specs.
Generates MCP server configuration JSON, resolves authentication setup, and validates server connectivity for dbt. Use when setting up, configuring, or troubleshooting the dbt MCP server for AI tools like Claude Desktop, Claude Code, Cursor, or VS Code.
Retrieves and searches dbt documentation pages in LLM-friendly markdown format. Use when fetching dbt documentation, looking up dbt features, or answering questions about dbt Cloud, dbt Core, or the dbt Semantic Layer.
Formats and executes dbt CLI commands, selects the correct dbt executable, and structures command parameters. Use when running models, tests, builds, compiles, or show queries via dbt CLI. Use when unsure which dbt executable to use or how to format command parameters.
Diagnoses dbt Cloud/platform job failures by analyzing run logs, querying the Admin API, reviewing git history, and investigating data issues. Use when a dbt Cloud/platform job fails and you need to diagnose the root cause, especially when error messages are unclear or when intermittent failures occur. Do not use for local dbt development errors.
Builds and modifies dbt models, writes SQL transformations using ref() and source(), creates tests, and validates results with dbt show. Use when doing any dbt work - building or modifying models, debugging errors, exploring unfamiliar data sources, writing tests, or evaluating impact of changes.
Use when a user is enabling, configuring, optimizing, or debugging dbt State (the server-backed reuse mechanism that clones or skips nodes instead of rebuilding them). Use when they conflate dbt State with the `state:modified` selector or `--state` deferral. Use when asked about models rebuilding unexpectedly, views with `select *` rebuilding, volatile SQL (`current_timestamp()`, `random()`) rebuilding or not, cross-developer cloning, lag_tolerance.
Use when changing a dbt model in a way that could break its consumers — renaming, removing, or retyping a column, or changing a model that downstream models, exposures, dashboards, or BI tools depend on — to judge whether the change is breaking and who it affects. Also use when versioning a model (model versions, latest_version, latest_version_pointer, deprecation_date, migration windows), enforcing contracts, setting access or groups, or doing multi-project dbt Mesh work (cross-project refs via dependencies.yml, disambiguating similarly-named models, splitting a monolith). Covers single- and multi-project, and planning or advising as well as implementing.
> Run circular import detection against ddtrace and propose architectural fixes for any cycles found. Use this when adding or refactoring modules, or when the detect_circular_imports CI job reports new cycles on a PR.
> Diagnose and fix slow base venv build times caused by unnecessary recompilation of native extensions (CMake, Cython, Rust) across riot generate runs. Use when CI base venv builds are slow, when ext_cache isn't saving time, or when investigating warm build regressions.
| dd-trace-py integration development guide. Use when creating, modifying, or debugging contrib integrations in the Python tracer. Covers the patch module system, context_with_data, context_with_event (new), registration, testing with riot, and common anti-patterns. LLM/AI integrations should use this skill for APM-side workflow only; use llmobs-integrations for LLMObs-specific lifecycle, extraction, streaming, and VCR guidance. Pin is DEPRECATED. "trace_handlers", "PATCH_MODULES", "context_with_data", "context_with_event", "TracingEvent", "VCR", "cassette", "generative-ai", "LLM integration", "riot", "riotfile", "suitespec", "new integration", "wrap", "unwrap".
> Find all CPython internal headers and structs used in the codebase, particularly for profiling functionality. Use this when adding support for a new Python version to identify what CPython internals we depend on.
> Run targeted linting, formatting, and code quality checks on modified files. Use this to validate code style, type safety, security, and other quality metrics before committing. Supports running all checks or targeting specific checks on specific files for efficient validation.
> Register a new environment variable / configuration option in dd-trace-py. Use whenever you add (or rename) a DD_*/_DD_*/OTEL_*/DATADOG_* environment variable so it is documented, validated, and tracked for cross-language feature parity. Covers supported-configurations.json, the generated _supported_configurations.py module, docs/configuration.rst, and the feature-parity registry hand-off.
> Compare CPython source code between two Python versions to identify changes in headers and structs. Use this when adding support for a new Python version to understand what changed between versions.
| dd-trace-py LLMObs integration development guide. Use when creating, modifying, or debugging LLMObs integrations for LLM/AI libraries in the Python tracer. Covers BaseLLMIntegration, stream handling, message extraction, token counting, tool call parsing, and VCR-based testing patterns. "_llmobs_set_tags", "BaseStreamHandler", "submit_to_llmobs", "integration.trace", "LLM span", "VCR", "cassette", "anthropic", "openai", "google_genai", "claude_agent_sdk", "generative-ai", "LLM integration", "llmobs_enabled".
> Review CI results for the current branch, commit, or PR using the Datadog MCP. Use this when CI is failing, to understand what's blocking a PR, or to get actionable fix instructions for failed jobs and tests.
> Decide whether a release note is needed, and if so create or update a Reno fragment, following dd-trace-py's conventions (docs/releasenotes.rst).
> Run performance benchmarks to measure the impact of code changes. Discovers relevant benchmark scenarios based on changed files, executes them comparing a baseline version against local changes, and summarizes performance results. Use this when touching performance-sensitive code paths or when asked about performance impact.
> Validate code changes by intelligently selecting and running the appropriate test suites. Use this when editing code to verify changes work correctly, run tests, validate functionality, or check for regressions. Automatically discovers affected test suites, selects the minimal set of venvs needed for validation, and handles test execution with Docker services as needed.
| Creates a professional PowerPoint presentation about a Copilot Dev Camp lab or topic. Researches Microsoft Learn documentation, organizes content into a slide structure, and generates a polished deck with speaker notes. Use when user asks to "create a presentation on", "make a deck about", "build a slideshow for", "present on Dev Camp topic", or "generate slides about" any Copilot Dev Camp lab or Microsoft technology topic.
| Researches and compiles comprehensive information about Microsoft Foundry, including documentation, architecture, models, and deployment options. Use when user asks to "research Microsoft Foundry", "learn about Foundry", "Foundry documentation", "Foundry architecture", "Foundry models", "how to deploy with Foundry", "Foundry features", or "Foundry capabilities".
| Creates new Copilot Dev Camp lab markdown files under docs/pages/<subfolder>/ with a consistent structure, concise exercises, and required custom components. Use when asked to author a new lab, scaffold a lab file, or draft a Copilot Dev Camp lab page.
| Drafts a concise weekly status-update email to the user's team, covering open tasks, upcoming meetings, and action items, with light emoji formatting in the body. Use when the user asks to "draft my weekly status email", "write my weekly team update", "send my team the weekly status", "create my Monday status mail", "weekly status update for the team", or "recap this week for the team". Do NOT use for leadership or executive updates and cross-functional stakeholder communications — use stakeholder-comms instead. Do NOT use for one-off announcements or non-status emails — use the Outlook tools directly.
| Authors a professional Word document about a Copilot Dev Camp lab or Microsoft technology topic. Researches Microsoft Learn documentation, organizes content into a document structure, and generates a polished one-pager or detailed guide with formatting and citations. Use when user asks to "write a document about", "create a guide for", "author a one-pager on", "write a technical brief on", or "create documentation for" any Copilot Dev Camp lab or Microsoft technology topic.
Converts a raw claims export workbook (one claim per row) into a polished, formatted Excel report with a Dashboard (KPIs, breakdowns by status, damage type, severity, and location, plus charts) and a clean Claims Detail table. The report layout is a built-in reference template, so every run looks consistent. Use when the user asks to "turn this claims export into a report", "build a claims report", "format the claims data", "make a claims dashboard", "summarize these claims", "claims summary report", or drops a claims_export spreadsheet and wants it turned into a nice report. Also use for similar flat claim/loss/incident exports that share the columns Claim Number, Claimant, Location, Damage Type, Status, Date Filed, and Estimated Cost. Do NOT use for writing a prose narrative document (use docx), building slides (use pptx), ad-hoc one-off spreadsheet edits unrelated to claims (use xlsx), or interactive dashboards the user clicks through (use canvas).
Use Rozenite for Agents through CLI-driven `rozenite agent` commands to inspect React Native DevTools data and Rozenite plugins on a live app target. Trigger this skill for shell-based debugging and live session work. For Node.js or TypeScript scripts, wrappers, automations, or other programmatic SDK usage, use `rozenite-agent-sdk` instead.
Use Rozenite for Agents through `@rozenite/agent-sdk` in Node.js or TypeScript code. Trigger this skill when Codex needs to write or run scripts, wrappers, automations, benchmarks, or agent runtimes that call Rozenite programmatically instead of driving the `rozenite agent` CLI directly.
Drive Browser Use Desktop's assigned Chromium target via the DevTools Protocol from JavaScript. Run snippets through the bundled `browser-harness-js` CLI; it auto-spawns a long-lived Bun HTTP server holding a CDP `Session`, and every call executes against the same persistent connection.
紫微斗数命盘解读 V2：输入生辰信息，精确排盘并生成可视化命盘解读报告（HTML）。支持格局量化仪表盘、空宫借星标记、流年时空压力热力表，双主题（典藏/赛博）可切换。融合紫微三合派、中州派和手相互证的方法论。当用户提到算命、命盘、紫微斗数、排盘、命理、八字、运势、看命、生辰分析时触发。也适用于用户说「帮我看看命盘」「算一下」「排个盘」「看看运势」的场景。即使用户只是说「帮我分析一下我的性格/事业/感情」，只要上下文暗示需要命理分析，也应该触发。
| Gets secure, one-time-use payment credentials (cards, tokens) from a Link wallet so agents can complete purchases on behalf of users. Use when the user says "get me a card", "buy something", "pay for X", "make a purchase", "I need to pay", "complete checkout", or asks to transact on any merchant site. Use when the user asks to connect or log in to or sign up for their Link account.
Embody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.
导演并制作多类型视频，从创意、研究、剧本、视觉开发、人物与声音设计、分镜和生成 Prompt，一直推进到素材生成、任务追踪与交付。适用于 Storytime Animation、Animated Explainer 与 Cinematic Drama，三个 Mode 均已完成实际作品验证。尚未建立专属 Mode 的类型不得冒充已支持流程。
TrailSnap CLI 命令行工具，用于查询照片、相册、标签、位置和人物等信息。当用户需要查看照片、相册数据时调用此技能。
Pre-pipeline aggregator that scans AI agent cache directories (.claude, .cursor, .antigravity, .openclaw) or any user-specified directory for experimentation logs, extracts insights and numeric results, and formats them as PaperOrchestra-ready inputs (idea.md + experimental_log.md). TRIGGER when the user says "aggregate my agent logs for paper writing", "extract experiments from my coding agent history", "prepare PaperOrchestra inputs from my cache", "turn my agent logs into a paper", mentions a folder or directory they want to use as the basis for a paper, or wants to run PaperOrchestra but only has scattered agent experiment histories rather than structured inputs. Run this BEFORE paper-orchestra. Also called automatically by paper-orchestra when workspace/inputs/idea.md or workspace/inputs/experimental_log.md are missing.
Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules, deterministic 0-100 decision bands (Accept/Minor/Major/Reject) that drive a target-met early stop, and a Devil's Advocate concession-threshold guard that blocks acceptance on unresolved critical findings. Maintains a worklog and snapshots each iteration so revert is real, not symbolic. TRIGGER when the orchestrator delegates Step 5 or when the user asks to "refine the draft", "iterate on the paper", or "run peer review on this paper".
Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover candidate papers via web search, verify them through Semantic Scholar (Levenshtein > 70 fuzzy title match, temporal cutoff, dedup by paperId), cross-corroborate against Crossref + OpenAlex to flag hallucinated citations, build a BibTeX file, and draft Introduction + Related Work using ≥90% of the verified pool. Runs in parallel with the plotting-agent. TRIGGER when the orchestrator delegates Step 3 or when the user asks to "find citations for my paper", "draft the related work", or "build the bibliography".
Step 1 of the PaperOrchestra pipeline (arXiv:2604.05018). Convert (idea.md, experimental_log.md, template.tex, conference_guidelines.md) into a strict JSON outline containing a plotting plan, literature search plan (Intro + Related Work), and section-level writing plan with citation hints. TRIGGER when the orchestrator delegates Step 1 or when the user asks to "outline a paper from raw materials" or "generate the paper structure".
Run the four paper-quality autoraters from PaperOrchestra (arXiv:2604.05018, App. F.3) — Citation F1 (P0/P1 partition + Precision/Recall/F1), Literature Review Quality (6-axis 0-100 with anti-inflation rules), SxS Overall Paper Quality (side-by-side), and SxS Literature Review Quality (side-by-side). TRIGGER when the user asks to "score this paper draft", "evaluate against the benchmark", "compare two papers", or "run the autoraters".
Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured research materials (idea, experimental log, LaTeX template, conference guidelines, optional figures) into a submission-ready LaTeX manuscript and compiled PDF. TRIGGER when the user asks to "write a paper from my experiments", "turn this idea and these results into a paper", "generate a conference submission", "run paper-orchestra on X", or otherwise wants the end-to-end paper-writing pipeline. Coordinates the outline-agent, plotting-agent, literature-review-agent, section-writing-agent, and content-refinement-agent skills.
Reverse-engineer raw materials (Sparse idea, Dense idea, experimental log) from an existing AI research paper to build a benchmark case for evaluating paper-writing pipelines. Replicates the PaperWritingBench dataset construction procedure from arXiv:2604.05018 §3 / App. C. TRIGGER when the user asks to "build a benchmark case from this paper", "reverse-engineer raw materials", or "evaluate my pipeline against PaperWritingBench".
Step 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimental_log.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER when the orchestrator delegates Step 2 or when the user asks to "generate the figures for my paper" or "render the plots from this experiment log".
Step 4 of the PaperOrchestra pipeline (arXiv:2604.05018). ONE single multimodal LLM call that drafts the remaining paper sections (Abstract, Methodology, Experiments, Conclusion), extracts numeric values from experimental_log.md into LaTeX booktabs tables, splices the generated figures from Step 2, and merges everything into the template that already contains Intro + Related Work from Step 3. TRIGGER when the orchestrator delegates Step 4 or when the user asks to "write the methodology and experiments sections" or "fill in the rest of the paper".
Use when the user asks for an AWS architecture diagram — VPC/networking, event-driven, landing zone, multi-AZ, serverless pipeline, or any diagram built with AWS service icons. Builds with the declarative layout engine using ground-truth mxgraph.aws4 stencils, validates (stencils/colors/nesting/geometry), runs a render-based vision self-check. Default output is .drawio; PNG/SVG only on request.
Use when the user asks for an Azure architecture diagram — VNet/networking, App Service, AKS, landing zone, multi-region, or any diagram built with Azure service icons. Builds with the declarative layout engine using ground-truth Azure stencils, validates (stencils/colors/nesting/geometry), runs a render-based vision self-check. Default output is .drawio; PNG/SVG only on request.
Use when the user asks for a BPMN diagram, swimlane diagram, business process map, or workflow diagram with roles/lanes and phases. Builds with the declarative layout engine using canonical mxgraph.bpmn stencils (events, gateways, typed tasks) in horizontal swimlanes (pool → lanes × phases), validates (BPMN semantic rules plus geometry), runs a render-based vision self-check. Default output is .drawio; PNG/SVG only on request.
Use when the user asks for a Databricks lakehouse architecture diagram — medallion architecture (Bronze/Silver/Gold), Delta Lake, Unity Catalog, workspace deployment, data-plane/control-plane, or any diagram built with Databricks icons. Builds with the declarative layout engine using ground-truth stencils, validates (stencils/colors/nesting/geometry), runs a render-based vision self-check. Default output is .drawio; PNG/SVG only on request.
Use when the user asks for a GCP or Google Cloud architecture diagram — VPC/networking, GKE, Cloud Run, landing zone, multi-region, or any diagram built with GCP service icons. Builds with the declarative layout engine using ground-truth GCP stencils, validates (stencils/colors/nesting/geometry), runs a render-based vision self-check. Default output is .drawio; PNG/SVG only on request.
Claude Skills — questions
Answers built from the skills we actually parsed.