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. 86 696 files from 2 113 authors, of which 68 413 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.
Use this skill when a Power Automate flow triggers the agent with a payload describing an unknown source column from a lab results file that broke an Azure Data Factory ingestion pipeline. The skill semantically matches the source column against the canonical clinical schema indexed in Azure AI Search, scoped first by the sending lab and then by clinical domain, and writes a suggested destination-column mapping to the Dataverse review queue for a clinical informatics steward to approve. Also activates on manual invocations like "map this lab column", "the ADF pipeline failed on column X, what should it map to", or "suggest a canonical column for this lab feed field".
Extract and preserve a departing senior leader's institutional knowledge — projects, decisions, rationale, relationships, tribal knowledge — into a structured, multi-phase archive built from M365 signals (emails, Teams, meetings, SharePoint/OneDrive). Resumable across multiple sessions. Use when the user asks to "build an institutional knowledge archive", "preserve institutional knowledge", "capture a departing leader's knowledge", "run a knowledge extraction for an executive handoff", "document a leadership transition before someone retires", or otherwise to capture/preserve a specific leader's decision history and expertise before they leave. Do not trigger on incidental mentions of someone retiring, leaving, or being out of office.
>- Use this skill whenever a user asks to audit, curate, clean up, deduplicate, rationalize, or assess files used by an AI knowledge source. Require the user to upload copies of the source files, analyze those complete files locally, and use configured knowledge sources only to validate findings.
>- Determines which region-specific knowledge source(s) to search based on the user's location. You MUST invoke this skill BEFORE calling the KnowledgeSearch tool, and pass the chosen source(s) as its `sources` parameter.
Use this skill when the user asks to create LinkedIn posts, promotional posts, thought-leadership posts, newsletter introductions, article intros, or long-form LinkedIn content from source notes, facts, or drafts.
Create, polish, rewrite, review, repurpose, brainstorm, or configure evidence-led LinkedIn posts, captions, comments, hooks, ideas, and conversation-scoped writing profiles from facts, notes, drafts, research, announcements, or lived experience. Use for the initial LinkedIn request and every follow-up clarification, revision, correction, constraint, or preference in the active task.
> Analyzes meetings from pasted text, transcripts, or audio/video recordings and turns them into a structured intelligence report. Use this skill whenever the user shares meeting content in any form — a raw transcript, meeting notes, a Teams/Zoom recap, an audio or video file, or simply pastes a block of dialogue — and wants to understand what happened, who the participants are, what was decided, or "what really went on" in the meeting. meeting", "what did we agree on", "read this transcript", "insights from this call", or "what am I missing from this conversation" all indicate this skill. It surfaces explicit outcomes (decisions, action items, deadlines), builds persona profiles of the topics, and signals that were never made explicit but matter deeply to the context.
>- Use this skill whenever the user wants to search, browse, or look up records in a Microsoft Dataverse table — for example "look up accounts", "find opportunities for Contoso", "show me contact details", or "search cases by status". Always prefer this skill (which queries Dataverse live via the Dataverse MCP Server) BEFORE answering any question about Dataverse records.
Use this skill whenever the user asks to design, prepare, deliver, evaluate, improve, localize, or modernize Microsoft technical learning experiences, instructor-led training, workshops, demonstrations, hands-on labs, certification preparation, assessments, surveys, or learning enablement initiatives. Apply an instructional intelligence assessment before generating training assets or recommendations.
Use this skill when the user needs to choose the right Microsoft AI platform for a project, is comparing Microsoft 365 Copilot, Agent Builder, Copilot Studio, Microsoft Foundry, Foundry Agent Service, Windows AI Foundry, or Agent 365, needs to gather requirements for an AI or agent build, needs a solution architecture recommendation, needs to estimate effort as technical complexity and risk, or asks any variant of "which platform should I use", "how do I choose", "help me scope this AI project", or "what's the right tool for this AI use case".
Scan the user's recent Microsoft 365 signals (emails, active chats/channels, calendar subjects) to surface recurring patterns worth productizing — either as a blog post (the user explains the same thing repeatedly) or as an automation (the user does the same multi-step task repeatedly). Use when the user asks "what should I write about?", "what could I automate?", "find patterns in my work", or invokes "/pattern-radar".
Analyze the user's own sent emails to build a personal writing-voice profile and generate a reusable personal voice skill from it. Use this skill whenever the user asks to analyze their writing style, learn their tone of voice, create/build/update a personal voice skill or "own voice" profile, make drafts "sound like me", or makes an equivalent request in any other language. Also use it when the user complains that generated emails or Teams messages don't sound like them and no personal voice skill exists yet.
Use this skill whenever the user asks to run a Monte Carlo simulation, model risk or uncertainty with random sampling, estimate P5/P50/P95 outcomes, or produce a probability distribution for project timelines, portfolio returns, downtime, costs, or similar uncertain variables. Trigger on phrases like 'run a Monte Carlo', 'simulate outcomes', 'probability chart for best and worst case', or when they give min/most-likely/max (or mean/std) and want thousands of iterations. Do NOT trigger for deterministic forecasts with no uncertainty, or for generic charts unrelated to simulation.
>- Use this skill whenever the user wants tabular data from a PDF document AS A FILE — to extract, pull out, export, convert, or "put into a spreadsheet/Excel/CSV" (e.g. "pull out the rebates from the Contoso contract", "extract this pricing table", "get this into a spreadsheet"). This INCLUDES follow-up requests after you have already answered or summarized the data in chat — e.g. "now give me that as a file/spreadsheet", "export what you just showed me", "download that as Excel". In those follow-ups you MUST still invoke this skill and extract from the source document; never hand-build a spreadsheet from the chat summary. Do NOT use this skill for answer-in-line questions such as "what are the rebates in the Contoso contract?" — those are grounded Q&A.
Pre-simulate how a defined set of role-based personas will react to an internal comms, launch, or enablement artefact before it ships. Use when the user asks to "run the persona panel", "pressure-test this comms against our personas", "QA this launch email/deck before it goes out", "how will each team react to this", or wants persona- and domain-level feedback on a broad internal artefact. Requires a personas file — bring your own (see references/personas.template.md). Do NOT use for 1:1 private comms, HR/performance matters, or legal/contractual language.
Use this skill when the user asks for a point of view, punchy line, positioning sentence, provocative statement, headline angle, opinion line, or concise strategic stance.
| Writes natural, first-person spoken presenter scripts (talk tracks) for the slides in a PowerPoint deck, from slide images, or from pasted slide text. Treats existing speaker notes as AUTHORITATIVE when they contradict slide text. Produces one spoken script per slide with delivery cues, calibrated to a target duration and speaking pace, plus a timing table. Use when the user says "write a script for these slides", "I'm presenting slides X-Y, what should I say", "create a presenter script", "turn my speaker notes into a talk track", or "make a 6-minute script for these slides". Do NOT use to create or edit the visible content of slides, to summarize a recorded meeting or transcript, or for general document writing.
>- Use this skill whenever the user shares a Power BI or Analysis Services semantic model (a TMDL export, a BIM/JSON model definition, or a pasted list of tables, relationships, and measures) and asks for a model review, a performance check, or help fixing DAX, before writing or correcting any DAX measure for that model.
Assess Power Automate Desktop and hybrid cloud/desktop automation projects for maintainability, reliability, security, performance, troubleshooting readiness, scaling, and governance using current Microsoft guidance and evidence-based review practices.
> Trigger whenever the user uploads or references a Power Automate solution `.zip` and asks about references, dependencies on other flows, or related questions — phrasing like "document this flow", "what does this flow read/write/touch", "map the connection references", "audit this solution", or "which flows call which".
Use this skill whenever the user asks to document, map, standardize, redesign, or improve a business process from notes, transcripts, interviews, or requirements, especially when they need an editable SOP, process map, RACI, controls, improvement backlog, or polished PowerPoint briefing.
Use when the user asks to redline, track changes, or compare differences in a file. Compares an uploaded .docx or .pdf against a provided .dotx/.docx template and returns a redlined .docx where every textual difference is a Word tracked change (insertion/deletion) authored by "Copilot Studio AI". No visual conversion — built directly on the template.
Use this skill whenever the user asks for an insights/reporting analysis of a SharePoint list from a connected SharePoint knowledge source; first validate the list exists, then generate and save a single-file interactive HTML report to a pre-approved SharePoint destination whose audience is no broader than the source list and items, and return its SharePoint URL.
>- Use this skill whenever the user asks to create, build, or revise a self-contained HTML or web slide presentation, browser slideshow, keynote-style deck, arrow-key-navigable presentation, or a deck matching a previous HTML presentation. Use it before authoring the HTML so the shared design system, channel-specific delivery, and verification steps are applied. Do not use it for PowerPoint (.pptx), static documents, or data dashboards.
Use when the user asks to set up, run, or check a scheduled regulation, law, or regulatory-guidance monitor or tracker — triggers include "set up a regulation tracker for X", "monitor [regulation] for me", "run my regulation monitor", "what changed on [regulation] this week", or an unattended scheduler invoking a saved profile. On first invocation walk interactive setup (topics, jurisdictions, cadence, delivery), auto-discover the top authoritative sources per topic, and STOP for user confirmation before any monitoring. On subsequent runs visit only the locked source list plus user seeds, classify items, flag team-relevant ones via a WorkIQ-derived keyword match, and render a self-contained HTML dashboard with client-side sortable columns. Do NOT use for one-off legal research, reading a single document, computing compliance liability or filing position, or non-regulatory news monitoring.
Use this skill any time SharePoint list is being fetched, searched, or shown to the user — whether it comes from a SharePoint/Microsoft 365 connector, a search result, a pasted export, or a fetched SharePoint URL. Apply it instead of dumping raw JSON or an ad hoc table whenever the user asks to "pull," "check," "look up," "find," or "show" anything from a SharePoint list, even if they never say the word "format.".
Turns an uploaded dataset (.xlsx, .csv, .json, or PDF tables) into a self-contained, scroll-driven HTML data story with animated Plotly charts, counting stat cards, and narrative chapters. Use when the user asks for a data story, scrollytelling report, or an interactive narrative write-up of a dataset. If the user asks for a demo or example with no dataset of their own, build the story from the bundled sample workbook at assets/Basketball_Demo_Data.xlsx.
Analyze the user's communication style across their Teams chats and emails to build a reusable mimicry profile — greetings, tone, length, punctuation, sign-offs, common phrases, and quirks. Use this skill when the user asks to capture or analyze their writing style, or before configuring an assistant (e.g. an OOO auto-responder) that should write in their voice.
Use this skill when the user asks to create, improve, review, package, genericise, or submit an Agent Skill, SKILL.md file, skill metadata, or reusable agent instruction bundle.
Use ONLY when the user's message contains the exact command `/special-debug tool-trace` (optionally with `--full`); run the task normally, then write `tool_trace.json` summarizing tool/action/connector calls in order. Sensitive values (secrets, tokens, PII/PHI) are redacted by default; `--full` keeps them verbatim for an authorized admin.
>- Use this skill whenever a user shares a vendor contract, SOW, or supplier agreement draft and wants a first-pass risk review before it goes to legal, before recommending any change to contract terms.
Build a prioritised morning work brief for Microsoft Scout from Outlook mail, calendar, and Teams chats - what the user owes people, what is blocked on others, what is coming up, and what to do first. Use this skill whenever the user asks for a morning brief, a Monday or weekly brief, a daily digest, a "what is waiting on me" or "what did I miss" summary, a catch-up after time off, a review of unresolved team threads or pending actions, a look at the week ahead, or wants to know who is blocking them - even if they never use the word "brief". Also use it when setting any of this up as a recurring Scout automation.
Use this skill whenever the user asks to write, rewrite, humanise, de-AI, or polish prose so it doesn't read as AI-generated — or to review a draft for signs of AI writing. Apply it before returning any substantial prose the user will publish.
>- Convert a hand-drawn whiteboard photo (or sketched process/diagram) from a discovery or working session into a polished, client-ready infographic as an editable PowerPoint slide (.pptx). Use this whenever someone uploads or references a photo of a whiteboard, a hand sketch of a process or system, or session-capture notes and wants it "cleaned up", "made presentable", "turned into a diagram/infographic", "converted for the client", or similar — even if they don't say the word "infographic". Covers two layout archetypes — linear process flows (left-to-right step rails) and network/topology maps (locations, systems, or actors connected by labeled flows). Built for consulting/ERP discovery capture but works for any whiteboard-to-deliverable conversion. Do NOT use for charts/graphs from numeric data, for editing an existing polished design, or for generating diagrams with no source sketch.
Textum PRD→Scaffold→Story workflow for Codex with low-noise outputs and gate checks.
Textum PRD→Scaffold→Story workflow for Codex with low-noise outputs and gate checks.
Manage Backblaze B2 cloud storage. List files, audit usage, estimate cost, clean up stale data, review security posture, and manage lifecycle rules. Use when the user mentions B2, Backblaze, object storage buckets, or storage cleanup.
Updates a project changelog with entries for changes since the branch diverged from main. Use when about to open a PR, cutting a release, or when the user asks about changelog, release notes, or migration notes.
Guides developers through a human-supervised PDCA framework for AI code generation. Applies analysis, TDD, validation, and retrospection. Activates for sessions requiring systematic quality control.
Multi-backend database security auditor. Audits Supabase, Firebase (Firestore/RTDB/Storage/Functions/Remote Config), MongoDB (self-hosted + Atlas), self-hosted PostgreSQL, and self-hosted MySQL for RLS/rules misconfigurations, exposed credentials, auth bypasses, MongoBleed (CVE-2025-14847), pgBouncer CVE-2025-12819, mysql_native_password drift, ghost auth, and storage exposures. Use this skill whenever the user mentions database security, RLS or rule audits, security review, penetration testing a vibe-coded app, checking if their DB is exposed, hardening a backend, fixing security rules, or auditing apps built with Lovable/Bolt/Replit/Cursor/Claude Code on any of these backends. Trigger on phrases like 'is my app secure', 'check my database', 'audit my Firebase', 'audit my MongoDB', 'audit my Postgres', 'audit my Supabase', 'is my DB exposed', or any cross-backend variant ('audit my full stack').
Audit any Supabase project for security vulnerabilities, RLS misconfigurations, exposed API keys, auth bypasses, and storage issues. Use this skill whenever the user mentions Supabase security, RLS policies, database security audit, security review, penetration testing a Supabase app, checking if their database is exposed, hardening their Supabase project, fixing RLS, or anything related to securing a Supabase or vibe-coded application. Also trigger when the user asks about securing apps built with Lovable, Bolt, Replit, Cursor, or any AI coding tool that uses Supabase as a backend. Even if the user just says 'is my app secure' or 'check my database' and their project uses Supabase, use this skill. (DEPRECATED: this skill is a backwards-compat shim. Prefer the multi-backend `database-sentinel` skill, which covers Supabase plus Firebase, MongoDB, self-hosted Postgres, and self-hosted MySQL.)
Reference — rules for safely executing write/destructive operations against ad accounts. Always loaded into the performance-marketer agent.
Reference — what Markifact is, what the MCP server exposes, and the discover→inspect→run pattern. Always loaded into the performance-marketer agent.
Convert any HTML/CSS/JavaScript project into a production-ready WordPress Block Theme (Full Site Editing) with Interactivity API, Block Bindings, per-block CSS, and WordPress 6.5+ best practices. Use this skill whenever the user wants to convert, port, transform, migrate, or rebuild static HTML/CSS/JS into a WordPress block theme, FSE theme, or Gutenberg-compatible theme. Also triggers for scaffolding themes from scratch, generating theme.json from design tokens, creating block patterns from HTML snippets, or building WooCommerce-compatible block themes. Trigger on phrases like "convert to WordPress", "make this a WP theme", "block theme from HTML", "FSE theme", "Gutenberg theme", "WordPress theme from scratch", "port my landing page to WordPress", "WooCommerce theme from HTML", "create a block pattern", "generate theme.json", or any request involving WordPress block theme development. Also use this skill when the user invokes the slash commands /convert-to-wp-theme, /scaffold-wp-theme, /wp-pattern, /wp-theme-json, /wp-template, /wp-block, /wp-migrate, /wp-plugin-theme, /wp-variation, or /wp-classic-to-fse. Even if the user just says "WordPress theme" or "WP theme", this skill is likely relevant.
RouterOS v7 domain knowledge for AI agents. Use when: working with MikroTik RouterOS, writing RouterOS CLI/script commands, calling RouterOS REST API, debugging why a Linux command fails on RouterOS, or when the user mentions MikroTik, RouterOS, CHR, or /ip /system /interface paths. Scope: RouterOS 7.x (long-term and newer) only — v6 is NOT covered and accuracy for v6 problems will be low.
RouterOS hotspot captive portal for wired/wireless access control. Use when: configuring hotspot on RouterOS, setting up captive portal, writing hotspot profiles or instances, configuring walled garden, setting DHCP option 114 (RFC 8910 captive portal URI), integrating RADIUS with hotspot, or when the user mentions /ip/hotspot, walled-garden, hotspot profile, or captive portal on MikroTik.
MNDP (MikroTik Neighbor Discovery Protocol) wire format, behavior, and RouterOS /ip/neighbor integration. Use when: implementing MNDP discovery, parsing MNDP packets, working with /ip/neighbor, understanding WinBox device discovery, debugging why a router doesn't appear in neighbor lists, or when the user mentions MNDP, neighbor discovery, WinBox discovery, or /ip/neighbor.
MAC-Telnet protocol (MikroTik Layer-2 terminal/exec over UDP 20561) wire format, session handshake, and MD5 + MTWEI (EC-SRP) authentication. Use when: implementing or debugging a MAC-Telnet client/server, reaching a RouterOS device by MAC address without IP, parsing MAC-Telnet packets, understanding the WinBox-style L2 terminal, deciding between classic MD5 and modern MTWEI auth, or when the user mentions MAC-Telnet, mactelnet, mactelnetd, port 20561, or MTWEI/EC-SRP RouterOS login.
RouterOS /container subsystem for running OCI containers on MikroTik devices. Use when: enabling containers on RouterOS, setting up VETH/bridge networking for containers, managing container lifecycle via CLI or REST API, building OCI images for RouterOS, configuring container environment variables, troubleshooting container issues, or when the user mentions RouterOS container, /container, VETH, device-mode container, or MikroTik Docker.
RouterOS firewall filter, NAT, mangle, and address-list configuration. Use when: writing firewall rules in RouterOS, configuring NAT, setting up address-lists or interface-lists, writing idempotent firewall scripts, configuring DNS redirect or port forwarding, or when the user mentions /ip/firewall, chain=forward, chain=input, connection-state, address-list, interface-list, or layer7-protocol on MikroTik.
RouterOS command tree introspection via /console/inspect API. Use when: building tools that parse RouterOS commands, generating API schemas from RouterOS, working with /console/inspect, mapping CLI commands to REST verbs, traversing the RouterOS command hierarchy, or when the user mentions inspect, command tree, RAML, or OpenAPI generation for RouterOS.
RouterOS /app YAML format for container applications (7.21+ builtin app, 7.22+ custom YAML creation). Use when: writing or validating RouterOS /app YAML files, working with MikroTik container apps, building docker-compose-like definitions for RouterOS, creating /app store schemas, debugging /app validation errors, or when the user mentions /app, tikapp, or RouterOS container YAML.
RouterOS scripting language and CLI configuration idioms for .rsc files and interactive commands. Use when: writing or reviewing RouterOS scripts, scheduler/netwatch/on-event snippets, idempotent CLI config, :local/:global/:foreach/:do syntax, [find] selectors, print as-value handling, script permissions, or when the user mentions .rsc, RouterOS script, scripting tips, or CLI config automation.
Ground RouterOS config/scripts/API code against a REAL router using quickchr (@tikoci/quickchr) — a CLI + Bun/TS library that downloads, boots, and manages MikroTik CHR VMs on QEMU. Use when: validating generated RouterOS config or scripts against real RouterOS before trusting them; spinning up a disposable CHR for REST/CLI/API iteration; writing integration/lab tests against CHR; needing host↔guest networking for a CHR (port-forward, L2/MNDP capture, guest→host UDP); driving an external RouterOS tool against a live CHR. For raw QEMU/CHR boot mechanics (VirtIO, UEFI vs SeaBIOS, acceleration) without quickchr, use routeros-qemu-chr instead.
Inspecting and validating RouterOS command/script syntax against a live device via /console/inspect (highlight, completion, syntax, child) and :parse IL. Use when: validating RouterOS commands before execution, explaining or linting RouterOS scripts, building syntax-aware tooling (LSP servers, validators, agent explain/check commands), interpreting highlight token streams or :parse intermediate language, discovering enum values or argument schemas, or when the user mentions console/inspect, highlight tokens, parseIL, or RouterOS script validation.
MikroTik RouterOS CHR (Cloud Hosted Router) with QEMU. Use when: running RouterOS in QEMU, booting CHR images, debugging CHR boot failures, setting up VirtIO devices for RouterOS, choosing between SeaBIOS and UEFI boot, configuring QEMU port forwarding for RouterOS REST API, setting up inter-VM socket networking or host-side L2 capture of guest broadcasts (e.g. MNDP), or selecting QEMU acceleration (KVM/HVF/TCG).
RouterOS packet capture and TZSP streaming for protocol debugging. Use when: capturing packets on RouterOS, setting up /tool/sniffer, streaming live traffic via TZSP, using firewall mangle action=sniff-tzsp, debugging network protocols on MikroTik, receiving TZSP with Wireshark or tshark, saving pcap files from RouterOS, or when the user mentions packet sniffer, TZSP, sniff-tzsp, /tool/sniffer, or packet capture on RouterOS.
管理基于 Markdown 实体的本地知识库。提供库观察、实体检索、按需加载章节、精确编辑及显式关系管理能力。支持长期记忆与持续学习。
Guides discovery and application of project-specific conventions including code patterns, naming, structure, and team practices. Use when exploring a codebase or implementing features to match existing patterns.
>- Provides Mermaid diagram syntax, best practices, and styling rules for technical visualizations. Use when creating diagrams, flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, architecture diagrams, C4 diagrams, visualizations, or any visual documentation in markdown. Always use this skill when generating or updating Mermaid code blocks.
Claude Skills — questions
Answers built from the skills we actually parsed.