copilot-atelier
v6.0.0by raandree
Portable GitHub Copilot customization library: role-specific custom agents with handoffs and subagent allow-lists, deterministic lifecycle hooks, and on-demand Agent Skills for PowerShell/DSC engineering (Sampler, Pester, Datum, AutomatedLab, WinRM, MECM), document conversion (PDF, DOCX, XLSX, Marp, pandoc), Outlook and Microsoft To Do automation, research and citation integrity, agentic-security review, and skill/prompt/agent evaluation. Skills are portable; agents, rules, slash commands, and hooks load in GitHub Copilot clients. Keybindings are not a plugin component type; install the CopilotAtelier module from the PowerShell Gallery to get those too.
What copilot-atelier does, in the publisher's words
<source media="(prefers-color-scheme: dark)"
<img align="left" width="300" alt="Copilot Atelier logo"
Portable GitHub Copilot customization, agents, instructions, skills, prompts, and hooks, synced across machines via OneDrive and linked into the well-known ~/.copilot/ folders that VS Code and the Copilot CLI both read.
- Quick Start
- Purpose
- Folder Structure
- What Each Folder Contains
- How Much Process You Want
- Available Skills
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 50
- MCP servers
- 0
- Stars
- 17
- License
- MIT
- Repo created
- 2026-03-27
- Last pushed
- 2026-10-21
- Publisher type
- User
- Version
- 6.0.0
Links
Skills · 50
- agent-evals
- Use this skill when a Copilot skill, prompt, or agent changes and someone needs evidence that it works rather than one lucky run. Covers three stacked questions: is it discovered (trigger-rate evals), does it hold up across runs (capability and regression sets, pass@k vs pass^k, deterministic / LLM…
- agent-security-review
- Reviews AI agents, LLM-backed features, MCP servers, and prompt/skill/agent definitions for agentic-security risk. On-demand checklist: the lethal-trifecta test (private data × untrusted content × outbound channel), OWASP Top 10 for LLM Applications (2025) quick checks, a containment-first checklis…
- authenticated-web-extraction
- Extract data from sites that require login (LinkedIn, GitHub, Sessionize, Microsoft 365, X, Meetup) using a persistent Playwright + Microsoft Edge profile. Covers profile setup, interactive sign-in capture, session-cookie re-injection (Chromium drops session-only auth cookies on shutdown), cookie-b…
- automatedlab-deployment
- Build and manage Hyper-V lab environments with AutomatedLab (AL): installation, lab definitions, roles (AD, File Server, Routing, PKI, SQL), networking (incl. NAT), post-deploy configuration, VM status, snapshots, file transfer, DSC, certificates, firewall, and teardown. USE FOR: AutomatedLab, Hype…
- automatedlab-proxmox
- Diagnoses AutomatedLab Windows provisioning and remoting failures on Proxmox/QEMU from API, guest-agent, Windows Setup, and WinRM evidence. Separates deploy-time AppX cleanup from unusable generalized templates. USE FOR: AutomatedLab Proxmox, Install-Lab Proxmox hang, Windows could not start the in…
- brand-logo-system
- Designs a project's visual identity, renders SVG masters and PNG deliverables, exports the eleven-slot set a shared logo library expects, and wires the chosen variants into the project itself. Covers palette extraction, lockups, glyph marks, app icons, monochrome variants, and measured verification…
- changed-file-validation
- Runs an opt-in, bounded validation pass over the files one work batch changed. Collects project-scoped paths manually, deduplicates them per session, and checks each supported file once: PowerShell parsing and PSScriptAnalyzer in an owned, time-bounded worker process, and markdown through a real ma…
- citation-integrity
- Verify every external claim, quote, statistic, and reference in generated text against a fetched source before it ships. Prevents fabricated citations, plausible-but-wrong attributions, mis-stated quotes, broken DOIs/URLs, and "I remember reading that" hallucinations. Produces an audit trail mappin…
- code-review-and-quality
- A reusable five-axis code-review workflow for PowerShell/DSC changes: review for design, correctness, complexity, tests, and clarity/naming; size changes to stay reviewable; label findings by severity (Blocker / Major / Minor / Nit); separate must-fix from opinion; and keep review turnaround fast.…
- contributor-profile
- copilot-usage-stats
- Report how many tokens, API calls, and how much wall time a project has consumed in Copilot, and convert those tokens into GitHub AI Credits and dollars at the published per-model rates. Carries the repository-scoped join, the verified fact that `input_tokens` already contains `cache_read_tokens`,…
- create-outlook-draft
- Create Outlook email drafts from Markdown email files via COM automation in PowerShell. Parses metadata tables (To, CC, Subject) from Markdown, converts Markdown body to styled HTML (tables, bold, lists), and saves drafts to the Outlook Drafts folder. Handles COM lifecycle, locked items, duplicate…
- datum-configuration
- Reference for the Datum PowerShell DSC configuration data module: hierarchical data composition, Datum.yml, resolution precedence, merge strategies (MostSpecific, hash, deep, UniqueKeyValTuples, DeepTuple), knockout prefix, lookup_options, DatumStructure, store providers, Datum handlers (InvokeComm…
- debugging-and-error-recovery
- devils-advocate-review
- doc-coauthoring
- docx-to-markdown
- dsc-troubleshooting
- elster-form-capture
- evidence-package-assembly
- german-legal-research
- german-tax-research
- gilb-requirements-engineering
- grammar-check
- grill-me
- long-running-job-monitor
- marp-slide-overflow
- mcp-builder
- mecm-dsc-deployment
- memory-bank
- microsoft-todo-tasks
- outlook-calendar-export
- outlook-email-export
- pandoc-docx-export
- pdf-to-markdown
- pester-patterns
- pswritehtml-reporting
- reviewed-learning-inbox
- sampler-build-debug
- sampler-framework
- sampler-migration
- send-outlook-email
- skill-creator
- social-signal-sweep
- subagent-dispatch
- test-driven-development
- whisper-pyannote-transcription
- windows-gui-screenshot-capture
- winrm-troubleshooting
- xlsx-to-markdown
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
Category
Agent Tooling. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
copilot · agent-skills · custom-agents · powershell · dsc · sampler · pester
Related by publisher and keywords
Jon Gallant's collection of cross-agent skills for AI coding agents, GitHub Copilot, Claude, and Codex. Browse and install individual skills from the skills/ directory.
PSModule process guidance and reusable skills for PowerShell module repositories.
Never reconstruct where you left off. Local-first continuity for you and your coding agents, resume, decisions, and what's still in the air. CLI, MCP, and Agent Skills for Cursor, Claude Code, Copilot, and Codex.
Modernize PowerShell test suites by migrating Pester v4 tests to Pester v5.
Open-source engineering skills for repository work, Python, host-native MARGOS orchestration, ReThinking audits, and Agent Plugins authoring.
Hosted CentricMem librarian: organise and retrieve Markdown memory via host MCP.
[](https://agentpluginsdirectory.com/plugins/copilot-atelier)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.