copilot-skills

AI Engineering Coach - opens a private local dashboard that analyzes AI coding sessions, practice patterns, output, and context health. Say "AI engineering coach" to start.

📡 AI-First Drops — researches frontier model releases from the past week, stack-ranks new capabilities by power/impact, and generates ready-to-use prompts for each. Outputs both a markdown report and a CSV on your Desktop. Say "weekly ai report" to start.

🏟️ Havoc Hackathon — a multi-model orchestration skill that turns your terminal into a competitive arena. Dispatches up to 13 current full-size AI models in tournament elimination heats, scores them with sealed judge panels and Shadow Spec hidden quality gates, evolves the best ideas between rounds via Convergence Broadcasts, and synthesizes the final output from collective intelligence. Say "run hackathon" to start. Say "run kiloagent" for 1,000-agent deep mode. Say "run hackathon metaswarm" for commander contestants backed by full SS-250 swarms.

Multi-agent fleet conductor for the GitHub Copilot CLI. Launches exactly five visible Terminal Stampede commander groups, coordinates them through live collaboration ledgers, watches them with Agent Pulse, and applies sealed Shadow Score evaluation. Say "agent orchestra" to start.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Generate Excalidraw diagrams from descriptions. Creates .excalidraw JSON files that can be opened in https://aka.ms/excalidraw or embedded in documentation. Use when creating architecture diagrams, flowcharts, data flow visualizations, or illustrations for proposals and design documents.

Create and fill out Microsoft Dynamics 365 MyExpense expense reports from receipts using visible browser automation. Handles travel expenses, recurring monthly expenses (internet, phone), hotel itemization, and corporate AMEX matching. Produces a complete, review-ready draft; the user always submits themselves. Triggers include: 'expense report', 'submit expense', 'file an expense', 'internet expense', 'monthly expense', 'travel expense', or any request to log a reimbursable cost.

Edit Microsoft Loop documents in the browser using Playwright automation. Use when the user wants to create, edit, or update a Loop document, mentions 'Loop', 'Loop page', or 'Loop workspace', or wants to add content to a shared document in Loop.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments; working with SharePoint-hosted or OneDrive-hosted presentations (even when no local file is involved). Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename or a SharePoint/OneDrive URL pointing to a presentation, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill. IMPORTANT: If the input is a SharePoint or OneDrive URL, read ~/.copilot/skills/pptx/sharepoint.md before doing anything else.

Create interactive HTML artifacts (dashboards, visualizations, org charts, network maps, trackers, comparisons) as self-contained HTML files. Use whenever the user requests a web application, data visualization, interactive tool, or any HTML artifact. All output MUST use the Clawpilot theme variables defined in this skill.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Fully interactive tutor for non-technical first-time users of the GitHub Copilot app. Starts from install/open, then guides users through the app, project sessions, approvals, issues, PRs, and first useful workflows.

Context Compass — your guide to bringing GitHub, Slack, and WorkIQ context into Copilot CLI. Runs beginner onboarding, daily briefings, safety checks, diagnostics, and role-based prompt recipes. Say "context compass" to start.

Multi-agent fleet conductor with real-time TUI observability. Launches multiple Terminal Stampede commander groups, keeps them coordinated through live collaboration ledgers, and applies sealed Shadow Score evaluation. Say "agent conductor" to start.

Fleet Scorecard — turns any multi-agent CLI run into a clear outcome decision. Scores what changed, what won, what failed, and whether to run it again. Say "fleet scorecard" to start.

🐝 Swarm Command — multi-model consensus swarm orchestrator. Launches 50-250+ AI agents across 15 models with hierarchical fan-out, cross-family review, Shadow Score Spec L2 conformance, and quality-gated synthesis. Say "swarm command", "swarmcommand", or "swarm250" to start.

Suggests GitHub Universe talk submissions based on your GitHub activity. Pulls your repos, PRs, issues, and contributions, identifies themes in your work, and generates complete CFS-ready proposals with titles, abstracts, and session details that match the Universe submission form.

🐝 Hive1K — recursive multi-model swarm orchestrator. Launches 250-1,000+ AI agents across 16 models with Division Commanders, hierarchical fan-out, Shadow Score Spec L2 conformance, and quality-gated synthesis. Say "hive1k" or "swarm1k" to start.

Helps any Hubber write their FY26 performance reflection. Pulls GitHub activity for the review period, reads the org chart, accepts supplementary context (team docs, Slack pastes, peer feedback), and generates an editable draft structured around the three FY26 reflection questions.

Interactive training for the GitHub Copilot CLI. Guided lessons, quizzes, scenario challenges, and a full reference covering slash commands, shortcuts, modes, agents, skills, MCP, and configuration. Say "cliexpert" to start.

🛡️ CodeQL Mastery — SOSS Fund expert on GitHub CodeQL and code scanning. Ask any question about CodeQL, code scanning, QL queries, vulnerability detection, community packs, or database internals. Validates security features via GitHub API and tracks call-to-action completion for dashboard reporting. Say "codeql" to start.

Use this skill when someone wants to learn GitHub Copilot CLI from scratch. Offers interactive step-by-step tutorials with separate Developer and Non-Developer tracks, plus on-demand Q&A. Just say "start tutorial" or ask a question!

🏭 Dark Factory — agentic build system with sealed-envelope testing. Orchestrates 6 specialist agents through a checkpoint-gated pipeline. Say "dark factory" to build something, "dark factory express" for quick tasks.

Cross-terminal multi-agent orchestration. Splits complex tasks into parallel work units dispatched to independent Copilot CLI workers via tmux panes with filesystem IPC, atomic operations, dead worker recovery, and conflict-aware synthesis.

🧬 Evo Forge — breeds better agents through evolutionary selection. Mutates agent prompts, tournaments them, selects survivors, tracks lineage. Say "evo forge" to evolve an agent, "evo forge status" to see the leaderboard.

🎓 First Agent — live training skill that guides non-developers from zero to building their first AI agent in three sessions. Run It → Remix It → Build It. Designed for instructor-led sessions. Say "first-agent" to start.

Converts Google Docs, Slides, and Sheets to Microsoft Office formats (Word, PowerPoint, Excel). Paste a Google URL and get the Office file. Say "convert" with a Google Doc link to start.

🐙 OctoFund — data-driven funding allocator for underfunded open source projects. Takes a budget, scores critical projects on dependency impact and funding gaps, and produces a stack-ranked funding report. Say "octofund" to start.

🎤 Pitch Master — transforms ANY concept, repo README, or about section into a world-class Y Combinator / TechStars 60-second quick pitch. Hook → Problem → Solution → Why Now → Traction → Ask. Technical, non-technical, boring infrastructure — everything becomes compelling. Say "pitch me" to start.

Use when the user asks to "fetch context from Slack", "read this Slack thread", "get requirements from Slack", "extract Slack conversation", or provides a Slack permalink. Uses `gh slack read` — no background scraping, no MCP server. Always warn about security and request confirmation before using Slack data.

🛡️ SOSS Fund Training — MODULE_TITLE. Interactive trainer with CTA tracking, security validation, and dashboard-ready data export. Say "MODULE_TRIGGER" to start.

🔍 Design Auditor — paste a URL, get 5 ranked fixes to improve conversions. Analyzes layout, performance, accessibility, and CTA effectiveness. Say "audit <url>" to start, or "audit local" for a local dev server.

Translate Google Workspace habits into Microsoft 365 steps, app mappings, troubleshooting, and power-user guidance.