New Checked the same way as MCP servers
Agent Skills, and what they let an agent do
Read straight from each publisher's repository. For every skill: what it allows the agent to do, the scripts it ships, and what fixed checks matched. Nothing is run.
Skills from GitHub17
Clear filters- acquire-codebase-knowledgeGitHub · 1 scriptUse this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine fe…OfficialRuns commands1 finding
- agent-skill-stackGitHub · 5 scriptsFind, evaluate, and assemble the smallest compatible set of AI Agent Skills for an end-to-end natural-language goal. Use when a user wants Skills for a multi-step workflow, asks which Skills fit a project, needs an installed-Skill audit or conflict check, has …OfficialDestructive commandsReaches the network1 high finding
- appinsights-instrumentationGitHub · 1 scriptInstrument a webapp to send useful telemetry data to Azure App InsightsOfficialRuns commands
- azure-architecture-autopilotGitHub · 3 scriptsDesign Azure infrastructure using natural language, or analyze existing Azure resources to auto-generate architecture diagrams, refine them through conversation, and deploy with Bicep. When to use this skill: - "Create X on Azure", "Set up a RAG architecture" …OfficialRuns commands1 high finding
- batch-script-progressGitHub · 4 scriptsDesign and verify runtime output when creating or modifying Python, PowerShell, or Node.js scripts that process multiple files, records, or API requests. Use for batch scripts, bulk operations, silent long-running loops, progress reporting, per-item failures, …OfficialRuns commands1 finding
- bug-receiptGitHub · 1 scriptClose defects and incidents with a BUG RECEIPT and VERIFIED, PARTIAL, or BLOCKED status after diagnosis, repair, or recovery.OfficialRuns commands
- build-evidence-mapGitHub · 2 scriptsBuild an auditable evidence map for a contested technical choice, research synthesis, proposal review, or consequential decision. Use when Copilot must preserve supporting, contradicting, qualifying, and missing evidence with exact source regions instead of co…OfficialRuns commands
- code-tourGitHub · 2 scriptsUse this skill to create CodeTour .tour files — persona-targeted, step-by-step walkthroughs that link to real files and line numbers. Trigger for: "create a tour", "make a code tour", "generate a tour", "onboarding tour", "tour for this PR", "tour for this bug…OfficialReaches the networkRuns commands
- convert-excel-to-mdGitHub · 1 scriptConverts Excel (.xlsx) workbooks into Markdown so their contents can be accurately analyzed, summarized, searched, or extracted from. Use this skill whenever the user shares, references, or asks about a .xlsx file — even if they don''t say "convert" or "markdo…OfficialDestructive commandsReaches the network1 high finding
- convert-pdf-to-mdGitHub · 1 scriptConverts PDF (.pdf) documents into Markdown so their contents can be accurately analyzed, summarized, searched, or extracted from. Use this skill whenever the user shares, references, or asks about a .pdf file — even if they don''t say "convert" or "markdown" …OfficialDestructive commandsRuns commands1 high finding
- convert-word-to-mdGitHub · 1 scriptConverts Word (.docx) documents into Markdown so their contents can be accurately analyzed, summarized, searched, or extracted from. Use this skill whenever the user shares, references, or asks about a .docx file — even if they don''t say "convert" or "markdow…OfficialDestructive commandsReaches the network1 high finding
- copilot-pr-autopilotGitHub · 7 scriptsCopilot left 14 review comments on your PR — half are nits. Hours of fix → reply → resolve → re-request, and each round lands MORE comments. This skill runs loop engineering: auto-triggers Copilot Code Review via GraphQL (no @copilot mention), triages every op…OfficialReaches the networkRuns commands
- copilot-usage-metricsGitHub · 4 scriptsRetrieve and display GitHub Copilot usage metrics for organizations and enterprises using the GitHub CLI and REST API.OfficialRuns commands
- cypress-flake-fixerGitHub · 1 scriptFind and fix flake-prone anti-patterns in an existing Cypress suite, and APIs removed in Cypress 12 to 16. Bundles a zero-dependency scanner for fixed cy.wait() delays, assigned command return values, async/await, force: true, chaining after actions, one-shot …OfficialRuns commands1 finding
- daily-focus-boardGitHub · 1 scriptSpin up a personal, motivating daily focus board that renders in a browser canvas and that the user drives by talking to their AI partner. Tasks track status (to-do → in progress → done) with timestamped progress notes and roll up into a "today''s momentum" fe…OfficialReaches the networkRuns commands1 high finding
- datanalysis-credit-riskGitHub · 3 scriptsCredit risk data cleaning and variable screening pipeline for pre-loan modeling. Use when working with raw credit data that needs quality assessment, missing value analysis, or variable selection before modeling. it covers data loading and formatting, abnormal…OfficialRuns commands
- docs-sync-auditGitHub · 1 scriptRun a read-only documentation drift audit for a feature, PR, branch, release, API, configuration change, workflow, CLI, package, or repository area. Use when the user asks whether docs are stale, missing, inconsistent with code, or need updates after code chan…OfficialRuns commands1 finding
Labels come from the skill's own files, read on the date shown: the tools its frontmatter allows and the scripts it ships. They are not a safety rating, and no finding is not a safety guarantee. How skills are checked.