spec
garrytan/gstack/spec/SKILL.md
Turn vague intent into a precise, executable spec in five phases. (gstack)
Steady12 mentions in 2 weeks
168 projects use a version of this
One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
garrytan/gstack/spec/SKILL.md
Turn vague intent into a precise, executable spec in five phases. (gstack)
Steady12 mentions in 2 weeks
168 projects use a version of this
microsoft/PowerToys/AGENTS.md
Top-level AI contributor guidance for developing PowerToys - a collection of Windows productivity utilities
No other project uses it yet
microsoft/PowerToys/.github/copilot-instructions.md
PowerToys AI contributor guidance
No other project uses it yet
microsoft/PowerToys/.github/skills/powertoys-verification/SKILL.md
Verify PowerToys behavior end-to-end with the winapp CLI across two scenarios: (A) a module's release checklist against the installed build; (B) PR validation — derive each PR's checklist from its description + diff, then drive it against the installed build (a merged/shipped PR, or a whole release/hotfix set) or by building + sideloading the module when the PR isn't in the build yet (unmerged or not-yet-released). Drive each item via UIA invoke / Named Events / settings.json edits / clipboard / GPO / SendInput, and emit a structured PASS / FAIL / BLOCKED verdict per item with evidence (FAIL distinguishes product defects from stale/ambiguous checklist items). Use when asked to verify a module checklist, validate a PR, sign off a release/hotfix's PRs, or QA installed/sideloaded PowerToys bits. Combines generic winapp ui mechanics (references/winapp-ui-testing.md) with PT-specific recipes, per-scenario playbooks (references/scenarios/), and the helper .ps1 files shipped with this skill.
No other project uses it yet
microsoft/PowerToys/.github/skills/ui-tests-migration/SKILL.md
Create, migrate, and stabilize PowerToys UI tests with Microsoft.PowerToys.UITest.Next and winappcli, through local VM success, commit/push, and CI validation. Use for ports, new UITest projects, flaky CI tests, persistent Hyper-V validation, Settings IPC authentication/test signing, Explorer/Shell selection, preview handlers, thumbnail providers, hotkey activation, stateful process lifecycle, composed WinUI/WebView visual baselines, or foreground failures. Covers APIs, scaffolding, test design, diagnostics, and the required handoff to ui-tests-pipeline-ci. Keywords: UI test, UITests, UITestAutomation.Next, winappcli, WinAppDriver, Selenium, Settings IPC, not-microsoft-signed, Authenticode, local VM, Hyper-V, checkpoint, migrate, flaky, CI stability, Explorer, Shell extension, WebView2.
microsoft/PowerToys/.github/skills/ui-tests-pipeline-ci/SKILL.md
Microsoft FTE-only completion workflow for PowerToys UI-test implementation: automatically continue after successful local VM suites, commit and push scoped changes, queue CI, wait synchronously, and stabilize through Azure CLI and Azure DevOps REST APIs. No separate push/run-CI request is needed for create, migrate, or stabilize tasks unless the user limited scope. Also use for explicit UITests CI, setup preflight, 401/403 diagnosis, build reuse, recordings/artifacts, and the three-run limit. Keywords: FTE, az, Azure CLI, Azure DevOps, pipeline, UI Test Automation, UITests CI, commit, push, local-to-CI handoff, buildNow, specificBuildId, uiTestModules, CI flake.
microsoft/PowerToys/.github/skills/winmd-api-search/SKILL.md
Find and explore Windows desktop APIs. Use when building features that need platform capabilities — camera, file access, notifications, UI controls, AI/ML, sensors, networking, etc. Discovers the right API for a task and retrieves full type details (methods, properties, events, enumeration values).
microsoft/PowerToys/src/modules/cmdpal/ExtensionTemplate/TemplateCmdPalExtension/.github/copilot-instructions.md
commands** — Add catch-all search commands - **publish-extension** — Publish to Microsoft Store or WinGet ## Documentation - [Creating an extension](https://learn.microsoft.com/windows/powertoys/command-palette/creating-an-extension) - [Extension samples](https://learn.microsoft.com/windows/powertoys/command-palette/samples) - [Extensibility overview](https://learn.microsoft.com
No other project uses it yet
microsoft/PowerToys/src/modules/cmdpal/ExtensionTemplate/TemplateCmdPalExtension/.github/skills/add-adaptive-card-form/SKILL.md
Create form-based UI for your Command Palette extension using Adaptive Cards. Use when asked to add forms, user input fields, toggle switches, text inputs, dropdown menus, data entry, surveys, configuration dialogs, or interactive content pages. Supports the Adaptive Cards Designer for visual form building.
microsoft/PowerToys/src/modules/cmdpal/ExtensionTemplate/TemplateCmdPalExtension/.github/skills/add-dock-band/SKILL.md
Add dock band support to your Command Palette extension for persistent toolbar widgets. Use when asked to add dock support, toolbar buttons, persistent UI widgets, taskbar integration, live-updating status displays, quick-access buttons, or always-visible controls. Supports single buttons, multi-button strips, and live-updating content.
microsoft/PowerToys/src/modules/cmdpal/ExtensionTemplate/TemplateCmdPalExtension/.github/skills/add-extension-settings/SKILL.md
Add a settings page to your Command Palette extension. Use when asked to add settings, preferences, configuration options, toggles, text inputs, dropdowns, or user-customizable behavior. Covers ToggleSetting, TextSetting, ChoiceSetSetting, and persistence.
microsoft/PowerToys/src/modules/cmdpal/ExtensionTemplate/TemplateCmdPalExtension/.github/skills/add-fallback-commands/SKILL.md
Add fallback commands to your Command Palette extension for catch-all search behavior. Use when asked to add search functionality, query matching, direct input handling, calculator-style evaluation, URL opening, command execution, or results that appear when no other extension matches. Used by 14 of 20 built-in extensions.
ggml-org/llama.cpp/AGENTS.md
human-written code - Mechanical tasks: formatting, repetitive patterns, completing code from established designs - Documentation drafts for components the contributor already understands - Writing code from a design the contributor owns Agents
Steady14 mentions in 2 weeks
No other project uses it yet
openai/codex/codex-rs/skills/src/assets/samples/openai-docs/SKILL.md
API first-timers, Codex/Work Q&A. If the user already has an OpenAI API integration, skip this skill for API questions and use the developer docs. Read this skill before answering how Codex or ChatGPT Work behaves, where to find a feature, or how to configure or troubleshoot this app or coding agent. This includes conversation history, model and cache behavior, instruction precedence, permissions, and tool availability. Use for API onboarding only when the user is connecting to the OpenAI API for the first time. Skip action requests, such as scheduling an automation, and tasks fully answered by supplied text or data.
Steady14 mentions in 2 weeks
31 projects use a version of this
openai/codex/codex-rs/skills/src/assets/samples/skill-creator/SKILL.md
Create or update a Codex skill with appropriately scoped instructions and any needed supporting resources.
Steady14 mentions in 2 weeks
189 projects use a version of this
Often used withtaskflow-inbox-triagemermaid-diagram-generatorecosystem-reference
openai/codex/codex-rs/tui/src/bottom_pane/AGENTS.md
explanation of the current behavior. - Keep implementations/docstrings aligned unless a divergence is intentional and documented. Practical check: - After edits, sanity-check that docs mention only APIs/behavior that exist in code
Steady14 mentions in 2 weeks
No other project uses it yet
rustdesk/rustdesk/AGENTS.md
restructure, and the code already fails cleanly there or behaves as master does, document it as a known limit in the PR instead. Anything beyond the easy fix needs
Steady6 mentions in 2 weeks
No other project uses it yet
shadcn-ui/ui/skills/shadcn/SKILL.md
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.
Cooling2 mentions in 2 weeks
189 projects use a version of this
react/react-native/AGENTS.md
declare export`. Declare only the surface the repo calls, typed as the package documents it, never `any`. - Check with `yarn flow-check`, and drop the libdef with the last
Steady2 mentions in 2 weeks
2 projects use a version of this
electron/electron/CLAUDE.md
Other targets (v8, boringssl, etc.) ├── spec/ # Test suite (1189+ TypeScript test files) ├── docs/ # API documentation and guides ├── build/ # Build configuration ├── script/ # Build and automation scripts └── chromium_src/ # Chromium source overrides
No other project uses it yet
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.