agentleFS

Find the best CLAUDE.md, AGENTS.md and Claude skills

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.

Worked for most · soon
Blockllms.txt

goose / static

block/goose/documentation/static/llms.txt

This site covers using goose, the open-source agent application, and building applications with the goose Development Kit (GDK). Read the relevant documentation before writing commands, configuration, or code. Guides and Python/Kotlin references below are Markdown; native Rust APIs link to docs.rs. Use GDK's Rust crates to assemble an agent or call models directly. Python and Kotlin bindings expose providers and conversation compaction, not the full agent runtime. Use ACP to make the pre-built goose agent the backend for your application.

No other project uses it yet

57k4mo agoReviewMountCreate a free account to mount
BlockSkill

compare-tasks

block/goose/evals/harbor/.agents/skills/compare-tasks/SKILL.md

Compare how two harbor benchmark runs performed on a single shared task

No other project uses it yet

57k4mo agoReviewMountCreate a free account to mount
BlockCopilot instructions

goose

block/goose/.github/copilot-instructions.md

Important: You review PRs immediately, before CI completes. Do not flag issues that CI will catch. Rust checks: - cargo fmt --check - Code formatting (rustfmt) - cargo test --jobs 2 - All tests - cargo clippy --all-targets -- -D warnings - Linting (clippy) Desktop app checks: - pnpm install --frozen-lockfile - Fresh dependency install (in ui/desktop/) - pnpm run lint:check - ESLint + Prettier - pnpm run test:run - Vitest tests Setup steps CI performs: - Installs system dependencies…

1 project uses a version of this

57k4mo agoReviewMountCreate a free account to mount
AnthropicCLAUDE.md

claude-cookbooks / chief_of_staff_agent

anthropics/claude-cookbooks/claude_agent_sdk/chief_of_staff_agent/CLAUDE.md

Output: JSON with monthly_burn, runway_months, total_runway_dollars, quarterly_burn, and burn_rate_daily Remember: As Chief of Staff, you have access to financial data in the financial_data/ directory and can delegate specialized analysis to your subagents (financial-analyst and recruiter).

Steady4 mentions in 2 weeks

No other project uses it yet

54k22d agoReviewMountCreate a free account to mount
AnthropicSkill

analyzing-financial-statements

anthropics/claude-cookbooks/skills/custom_skills/analyzing-financial-statements/SKILL.md

This skill calculates key financial ratios and metrics from financial statement data for investment analysis

Steady4 mentions in 2 weeks

8 projects use a version of this

54k22d agoReviewMountCreate a free account to mount
AnthropicSkill

applying-brand-guidelines

anthropics/claude-cookbooks/skills/custom_skills/applying-brand-guidelines/SKILL.md

This skill applies consistent corporate branding and styling to all generated documents including colors, fonts, layouts, and messaging

Steady4 mentions in 2 weeks

3 projects use a version of this

54k22d agoReviewMountCreate a free account to mount
AnthropicSkill

creating-financial-models

anthropics/claude-cookbooks/skills/custom_skills/creating-financial-models/SKILL.md

This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions

Steady4 mentions in 2 weeks

10 projects use a version of this

54k22d agoReviewMountCreate a free account to mount
JetBrainsAGENTS.md

kotlin

JetBrains/kotlin/AGENTS.md

CRITICAL: guidelines.md MUST be followed at all times.

No other project uses it yet

54k10d agoReviewMountCreate a free account to mount
JetBrainsAGENTS.md

kotlin / analysis

JetBrains/kotlin/analysis/AGENTS.md

A library for analyzing Kotlin code at the semantic level, providing structured access to symbols, types, and semantic relationships. Entry point: Use analyze() to start an analysis session. See Analysis…

54k10d agoReviewMountCreate a free account to mount
JetBrainsCLAUDE.md

kotlin

JetBrains/kotlin/CLAUDE.md

CRITICAL: @./.ai/guidelines.md guidelines MUST be followed at all times. Local Preferences: @./.claude/local.md When asked to update memory, you must update ./.claude/CLAUDE.md if it is not specified that another file should…

No other project uses it yet

54k10d agoReviewMountCreate a free account to mount
JetBrainsSkill

analysis-api-create-cherry-pick-issue

JetBrains/kotlin/.claude/skills/analysis-api-create-cherry-pick-issue/SKILL.md

Create a KTIJ cherry-pick tracking issue for a KT fix that needs to be cherry-picked to an IntelliJ branch. Use when cherry-picking Analysis API fixes.

No other project uses it yet

54k10d agoReviewMountCreate a free account to mount
JetBrainsSkill

analysis-api-mark-internal-apis

JetBrains/kotlin/.claude/skills/analysis-api-mark-internal-apis/SKILL.md

Drive the per-module internal-API codebase test, then refine the suggested annotations down to `internal` (or up to `@KaImplementationDetail`) based on actual external usage

54k10d agoReviewMountCreate a free account to mount
JetBrainsSkill

build-bump-gradle-version

JetBrains/kotlin/.claude/skills/build-bump-gradle-version/SKILL.md

Bumps the Gradle wrapper/distribution version that BUILDS the Kotlin project itself — the version behind `./gradlew`, defined by `gradle/wrapper/gradle-wrapper.properties`. Covers the wrapper regeneration and the version-specific fallout that follows it: removed/deprecated Gradle DSL, dependency-verification metadata, the Gradle Module Metadata fixtures, and the KGP functional tests. This is DISTINCT from the two sibling skills — it is NOT `build-tools-bump-gradle-api` (which bumps GRADLE_COMMON_COMPILE_API_VERSION, the API that plugins compile against) and NOT `build-tools-bump-gradle-in-tests` (which extends the KGP integration-test version matrix). Manual invocation only: a full run downloads a distribution, rewrites `gradle/verification-metadata.xml`, and drives `publish`, `testClasses` and `functionalTest` — hours of wall clock and a heavily mutated checkout — so it starts only when the user explicitly asks for `/build-bump-gradle-version`.

54k10d agoReviewMountCreate a free account to mount
JetBrainsSkill

build-tools-add-test-federation-annotations-to-integration-tests

JetBrains/kotlin/.claude/skills/build-tools-add-test-federation-annotations-to-integration-tests/SKILL.md

Annotate test classes in `kotlin-gradle-plugin-integration-tests` with Test Federation annotations (`@MustRunOnChangesInXYZ` / `@MustRunAlways`). Use this whenever the user asks to annotate, review, or fix Test Federation annotations on an integration test class, or to assess a test class for cross-domain dependencies under Test Federation (KT-87614).

54k10d agoReviewMountCreate a free account to mount
JetBrainsSkill

build-tools-bump-gradle-api

JetBrains/kotlin/.claude/skills/build-tools-bump-gradle-api/SKILL.md

Bumps the Gradle API version that Kotlin Gradle plugins are compiled against in the Kotlin compiler repository. Use this skill whenever the user asks to upgrade, bump, or update the Gradle compile API version, Gradle plugin API version, or GRADLE_COMMON_COMPILE_API_VERSION. Also use it when the user says something like "update KGP to compile against Gradle X.Y.Z" or "bump Gradle API to X.Y" or "we need to support Gradle X.Y in the plugin".

54k10d agoReviewMountCreate a free account to mount
JetBrainsSkill

build-tools-bump-gradle-in-tests

JetBrains/kotlin/.claude/skills/build-tools-bump-gradle-in-tests/SKILL.md

Bump the maximum supported Gradle version in the `kotlin-gradle-plugin-integration-tests` project. Use this whenever the user asks to bump Gradle in integration tests, add a new Gradle X.Y.Z to the test matrix, update `MAX_SUPPORTED` Gradle, "run tests against the new Gradle release", or anything else that sounds like extending the integration test matrix to a newer Gradle. The procedure spans four touch points across three files that must stay in lock-step (`TestVersions.kt`, `build.gradle.kts`, `GradleCompatibilityIT.kt`); reach for this skill even when the user mentions only one of those files, because editing by hand routinely desyncs them.

54k10d agoReviewMountCreate a free account to mount
JetBrainsSkill

minimize-repro-for-diagnostic-test

JetBrains/kotlin/.claude/skills/minimize-repro-for-diagnostic-test/SKILL.md

Makes a minimal reproduction of a Frontend-related bug as a diagnostic test

54k10d agoReviewMountCreate a free account to mount
JetBrainsAGENTS.md

kotlin / compiler

JetBrains/kotlin/compiler/AGENTS.md

Consider reading fir-basics.md. FIR processes code through sequential phases (see FirResolvePhase.kt). Key invariant: In phase B following phase A, all FIR elements visible in B are resolved to phase A.

No other project uses it yet

54k10d agoReviewMountCreate a free account to mount
AppleSkill

container

apple/container/skills/container/SKILL.md

Use when running, building, or managing Linux containers on macOS, or when a task involves Docker, docker compose, Lima, Colima, or Podman commands on a Mac, Dockerfiles, OCI images, image registries, or setting up a Linux development environment on Apple silicon.

Steady3 mentions in 2 weeks

2 projects use a version of this

52k3mo agoReviewMountCreate a free account to mount
VercelAGENTS.md

agent-browser

vercel-labs/agent-browser/AGENTS.md

Instructions for AI coding agents working with this codebase. This project uses pnpm. Always use pnpm instead of npm or yarn for installing dependencies, running scripts, etc. (e.g., pnpm install, pnpm run build). Do not hard-wrap prose in documentation files such as Markdown, MDX, and READMEs; let the editor or renderer wrap text naturally. Use the technical-writer skill (.agents/skills/technical-writer/SKILL.md) when you write or edit prose for this repo, including docs pages, READMEs, changelog entries, commit messages, PR descriptions, and issues.

Steady22 mentions in 2 weeks

No other project uses it yet

51k18d agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

Agent instruction files

What are agent instruction files?

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 or AGENTS.md?

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.

What is a skill?

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.

Can I search my own team's files too?

Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.