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.
MicrosoftSkillmicrosoft/vscode/.github/skills/context-menus/SKILL.md
Use when adding, changing, or reviewing context menus or menu contributions, including Action2 `menu` entries and MenuRegistry items with `group`/`order`, hand-built `showContextMenu` action lists, submenus, and separators. Covers group order, destructive-action placement, consistency across surfaces, and labels.
Steady+17 stars this week
No other project uses it yet
MicrosoftSkillmicrosoft/vscode/.github/skills/cpu-profile-analysis/SKILL.md
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-*.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating user timing marks.
Steady+17 stars this week
5 projects use a version of this
MicrosoftDeletes or force-pushesSkillmicrosoft/vscode/.github/skills/customizations-in-the-agent-host/SKILL.md
Architecture and hard-won debugging lessons for customization enablement (plugins, MCP servers, agents, skills, instructions) in the agent host. Use when changing how customizations are discovered, published, enabled/disabled, or handed to a provider SDK; when a customization shows the wrong enabled state in the UI; or when a disabled MCP server or plugin is still reaching the model.
Steady+17 stars this week
1 project uses a version of this
MicrosoftSkillmicrosoft/vscode/.github/skills/design-philosophy/SKILL.md
The VS Code design philosophy — a shared Values→Principles→Moves vocabulary for reasoning about UI in design terms instead of raw pixels. Use when designing, building, reviewing, or giving feedback on any visual surface; when deciding a radius, spacing, type role, icon size, border, color, or motion; or when translating a "this feels off" observation into a concrete, principled fix.
MicrosoftSkillmicrosoft/vscode/.github/skills/doc-comments/SKILL.md
Update doc comments
Steady+17 stars this week
1 project uses a version of this
MicrosoftSkillmicrosoft/vscode/.github/skills/experiments/SKILL.md
Use when adding, changing, or reviewing a VS Code A/B experiment, either an experiment-controlled setting or a treatment read with the assignment service, and when deciding whether and where to log an `experimentTrigger` event for a triggered ExP scorecard.
Steady+17 stars this week
6 projects use a version of this
MicrosoftSkillmicrosoft/vscode/.github/skills/feature-tryouts/SKILL.md
Use when adding, reviewing, or troubleshooting an interactive release-note Try This experience, including commands, views, editor samples, Chat drafts, guided spotlights, prerequisites, scoped targets, or Agents-window handoff.
Steady+17 stars this week
No other project uses it yet
MicrosoftSkillmicrosoft/vscode/.github/skills/feedback-learning/SKILL.md
Classify and record explicit corrective feedback without turning skills or instructions into append-only knowledge dumps.
Steady+17 stars this week
1 project uses a version of this
MicrosoftSkillmicrosoft/vscode/.github/skills/fix-ci-failures/SKILL.md
Investigate and fix CI failures on a pull request. Use when CI checks fail on a PR branch — covers finding the PR, identifying failed checks, downloading logs and artifacts, extracting the failure cause, and iterating on a fix. Requires the `gh` CLI.
Steady+17 stars this week
7 projects use a version of this
MicrosoftSkillmicrosoft/vscode/.github/skills/fixissueno/SKILL.md
fixIssueNo
Steady+17 stars this week
No other project uses it yet
MicrosoftSkillmicrosoft/vscode/.github/skills/flaky-smoke-tests/SKILL.md
Diagnose intermittent VS Code Electron smoke-test failures from the Azure DevOps Flaky Smoke Tests pipeline (definition 700). Covers finding failed iterations, downloading task logs and platform artifacts with Azure CLI, correlating cumulative runner logs, tracing the introducing commit, and queueing focused validation runs.
Steady+17 stars this week
1 project uses a version of this
MicrosoftSkillmicrosoft/vscode/.github/skills/heap-snapshot-analysis/SKILL.md
Analyze V8 heap snapshots to investigate memory leaks and retention issues. Use when given .heapsnapshot files, asked to compare before/after snapshots, asked to find what retains objects, or investigating why objects survive GC. Provides snapshot parsing, comparison, retainer-path helpers, and scratchpad scripts.
Steady+17 stars this week
5 projects use a version of this
MicrosoftSkillmicrosoft/vscode/.github/skills/hover/SKILL.md
Use when adding, changing, or reviewing hovers or tooltips on VS Code widgets and UI elements, including buttons, actions, toolbars, lists, and trees. Covers custom versus native tooltips, hoverDelegate placement, HoverStyle, pointers, IHoverService delayed hovers, groupId, and shared instant-hover behavior across adjacent widgets.
Steady+17 stars this week
No other project uses it yet
MicrosoftSkillmicrosoft/vscode/.github/skills/integrated-browser/SKILL.md
Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under `src/vs/platform/browserView` and `src/vs/workbench/contrib/browserView`.
Steady+17 stars this week
1 project uses a version of this
MicrosoftSkillmicrosoft/vscode/.github/skills/integration-tests/SKILL.md
Use when running integration tests in the VS Code repo. Covers scripts/test-integration.sh (macOS/Linux) and scripts/test-integration.bat (Windows), their supported arguments for filtering, and the difference between node.js integration tests and extension host tests.
Steady+17 stars this week
15 projects use a version of this
MicrosoftSkillmicrosoft/vscode/.github/skills/issue-grouping/SKILL.md
Group similar issues.
Steady+17 stars this week
No other project uses it yet
MicrosoftSkillmicrosoft/vscode/.github/skills/memory-leak-audit/SKILL.md
Audit code for memory leaks and disposable issues. Use when reviewing event listeners, DOM handlers, lifecycle callbacks, or fixing leak reports. Covers addDisposableListener, Event.once, MutableDisposable, DisposableStore, and onWillDispose patterns.
Steady+17 stars this week
8 projects use a version of this
MicrosoftSkillmicrosoft/vscode/.github/skills/migrate-issues/SKILL.md
migrate GitHub issues from one repository to another
Steady+17 stars this week
No other project uses it yet
MicrosoftSkillmicrosoft/vscode/.github/skills/otel/SKILL.md
OpenTelemetry guidance for VS Code agent experiences. Use when changing Agent Host telemetry, local Copilot Chat telemetry, provider-native spans or metrics, OTel settings and managed policy, trace persistence/export, or monitoring documentation.
MicrosoftSkillmicrosoft/vscode/.github/skills/policy-and-managed-settings/SKILL.md
Use whenever adding, modifying, or reviewing any Copilot, agent, LLM, AI, tool, permission, sandbox, MCP, model, telemetry, feature-gate, setting, configuration, or enterprise control—especially anything an organization or administrator may need to manage. Start here to decide whether it belongs in runtime managed settings, a typed SDK contract, VS Code configuration policy, extension policy, or a split implementation. Run on every new Copilot/agent/LLM control and ANY change that adds a `policy:` field.
Steady+17 stars this week
1 project uses a version of this
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.
