Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 404 files from 1 741 authors, of which 61 763 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
>- load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying / repairing services (use rag-blueprint).
Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing, comparing, or discussing skill capabilities.
Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with image-evidence-driven investigation. Use when analyzing ChangeNet model failures, investigating poor recall / FAR / PASS-NO_PASS metrics, auditing visual inspection pipeline quality, or running an RCA report for an AOI defect-detection model. Trigger phrases include "RCA on my ChangeNet model", "why is my AOI model failing", "audit ChangeNet predictions", "investigate FAR regressions", "root cause analysis on visual-changenet".
Performs gap analysis on NVIDIA TAO VCN Classify (Visual Component Net) experiments by invoking the data-services container (`tao_toolkit.data_services` from `versions.yaml`) directly via `docker run … gap_analysis vcn_aoi …` — picks the optimal decision threshold, ranks per-sample weakness, and emits a top-K weakest parquet expanded per-lighting for downstream augmentation. Use when analyzing VCN classification failures, picking SDA augmentation targets, or auditing PASS/NO_PASS boundary cases.
Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions. Use when the user asks to "analyze VLM BCQ gaps", "extract VLM false positives and false negatives", or identify failure cases from a predictions JSON for DEFT root-cause analysis on a binary-classification VLM workflow.
Contains well-defined rules for creating natural, accurate, and readable writing. Use whenever authoring longer text, like analysis documents, PR or CL descriptions, or documentation.
Performs a comprehensive, multi-step code review of pull requests or local code changes, using iterative refinement (generation, critique, synthesis) to ensure high-quality, actionable feedback. Use when you need to review code changes thoroughly.
Guide for writing effective code documentation, including docstrings, JSDoc, dartdoc, and implementation comments. Use this skill when writing new code, adding features, or improving existing documentation in Dart, Python, or TypeScript to ensure clarity and maintainability.
Safe, portable, and efficient command-line patterns for macOS/BSD Unix tools (grep, find, sed, awk, xargs, mdfind, pbcopy, open) and modern alternatives (ripgrep, fd). Covers common shell scripting and one-liner use cases including fast searching, text processing, codebase navigation, and parallel execution.
Reviews the specified code against the canonical API Design guidelines. Use this skill when the user asks for an API review or to check code against API design principles.
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Uses get_runtime_errors and lsp to fetch an active stack trace, locate the failing line, apply a fix, and verify resolution via hot_reload.
Guides agents in compiling and packaging C/C++ source code into dynamic or static libraries (Code Assets) using Dart's Native Assets hook system (via hook/build.dart and hook/link.dart utilizing package:hooks and package:native_toolchain_c). Use when a user asks to: 'setup native assets', 'compile C/C++ source code', 'bundle dynamic libraries', 'build native C code', 'link native assets', 'implement build.dart or link.dart hooks', or 'integrate C/C++ interop in Dart/Flutter'. Helps agents avoid manual toolchain orchestration and configures secure hash-validated binary downloads or advanced linker tree-shaking with package:record_use mapping.
Workflow for fixing package version conflicts. Use this when `pub get` fails due to incompatible package versions.
Guide agents to use `package:ffigen` to automatically generate FFI bindings instead of writing them manually. Use this skill when a task involves writing new FFI bindings, extending C/Objective-C/Swift integrations, or replacing hand-crafted `dart:ffi` setups.
Architects a Flutter application using the recommended layered approach (UI, Logic, Data). Use when structuring a new project or refactoring for scalability.
Adds interactive widget previews to the project using the previews.dart system. Use when creating new UI components or updating existing screens to ensure consistent design and interactive testing.
> Help users write syntactically and semantically correct primary constructors in Dart, and migrate/use the new constructor syntax, empty-body semicolon syntax, in-body initializer list syntax, and abbreviated concise constructor syntax.
Configures Flutter Driver for app interaction and converts MCP actions into permanent integration tests. Use when adding integration testing to a project, exploring UI components via MCP, or automating user flows with the integration_test package.
Fixes Flutter layout errors (overflows, unbounded constraints) using Dart and Flutter MCP tools. Use when addressing "RenderFlex overflowed", "Vertical viewport was given unbounded height", or similar layout issues.
Implement a component-level test using `WidgetTester` to verify UI rendering and user interactions (tapping, scrolling, entering text). Use when validating that a specific widget displays correct data and responds to events as expected.
Use `LayoutBuilder`, `MediaQuery`, or `Expanded/Flexible` to create a layout that adapts to different screen sizes. Use when you need the UI to look good on both mobile and tablet/desktop form factors.
Create model classes with `fromJson` and `toJson` methods using `dart:convert`. Use when manually mapping JSON keys to class properties for simple data structures.
Add `flutter_localizations` and `intl` dependencies, enable "generate true" in `pubspec.yaml`, and create an `l10n.yaml` configuration file. Use when initializing localization support for a new Flutter project.
Configure `MaterialApp.router` using a package like `go_router` for advanced URL-based navigation. Use when developing web applications or mobile apps that require specific deep linking and browser history support.
> Instructions for adding a new validation rule and CLI flag to dart_skills_lint. Use this skill when asked to create a new rule that validates aspects of skills (like frontmatter metadata).
> Validates an in-progress PR or feature branch of dart_skills_lint against known downstream ecosystem consumers. Use when assessing breaking changes across external repositories during PR evaluation, testing migrations against the changelog, or determining necessary backwards compatibility shims.
Use the `http` package to execute GET, POST, PUT, or DELETE requests. Use when you need to fetch from or send data to a REST API.
> How to integrate, update, and configure the dart_skills_lint validation tool within a repository. Make sure to use this skill whenever the user asks to update dart_skills_lint, configure skills validation tests, fix skills linter dependency drifts, verify repository state before editing, optimize lint rules execution, or draft pull request submission commands.
Mandatory checks to run before completing any task that touches md files or dart code in this repository.
|- Use this skill when you need to set up validation for AI agent skills in a Dart project for the first time. Adds the linter as a dev_dependency, creates a configuration file, and generates a baseline for legacy repos.
|- Use this skill when you need to validate AI agent skills with dart_skills_lint — running the linter, interpreting failures, fixing violations, and authoring custom rules.
Team code quality checklist - use for checking Python code quality, bugs, security issues, and best practices
Generate comprehensive pytest tests - use when generating tests, creating test suites, or testing Python code
Generate conventional commit messages - use when creating commits, writing commit messages, or asking for git commit help
A minimal skill example - use when learning the skill format
Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.
Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.
Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.
Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never leaks file paths or line numbers into the issue. Use when the user reports a bug conversationally, runs a QA pass, or says "file an issue", "log this as a bug", "capture this".
Smart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after. Use before manual compact or when auto-compact triggers.
Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.
Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.
Track session costs, set budget alerts, and optimize token spend. Use to check costs mid-session or set spending limits.
Apply interface craft when building or reviewing UI - motion, easing, timing, springs, component feel, and visual foundations. Use when building a component, animation, transition, hover or press state, modal, drawer, toast, or when polishing an interface so it feels right. Says "make this feel better", "add an animation", "polish the UI", "review this component".
Remove AI-generated code slop, unnecessary comments, and over-engineering from the current branch diff. Cleans up boilerplate, simplifies abstractions, strips defensive code, and in skill-file mode lints SKILL.md files for quality. Use when cleaning up code, simplifying, removing boilerplate, before committing, or when reviewing a skill before promoting it.
Build the project's shared language and bounded contexts before writing code, so names stay consistent and the agent stops paraphrasing domain concepts. Produces a CONTEXT.md glossary and decision records. Use at the start of a project or feature, or when the codebase and the people describing it speak different languages.
Configure file watching hooks to auto-react to config changes, env file updates, and dependency modifications. Use to set up reactive workflows.
Audit an area of the codebase and propose the smallest structural moves that improve it - untangle boundaries, kill duplication, fix seams, break cycles. Produces a prioritized plan and decision records, not a rewrite. Use when a codebase feels tangled, hard to change, or is becoming a ball of mud, or when asked to improve or refactor architecture.
Show session analytics, learning patterns, correction trends, heatmaps, and productivity metrics. Computes stats from project memory and session history. Use when asking for stats, statistics, progress, how am I doing, coding history, or dashboard.
Capture a correction or lesson as a persistent learning rule with category, mistake, and correction. Stores, categorises, and retrieves rules for future sessions. Use after mistakes or when the user says "remember this", "don't forget", "note this", or "learn from this".
Provider-agnostic multi-LLM deliberation. Three phases — independent responses, cross-model anonymized ranking, chairman synthesis. Provider config from env (OPENAI/ANTHROPIC/FIREWORKS/OPENROUTER/custom OpenAI-compatible base URL). Persists transcript to a wiki page when --wiki <slug> is passed. Use when the user wants multiple AI perspectives, consensus-building, or the "LLM Council" approach for high-stakes reviews, plan critique, or contested learning rules.
LLM-powered quality verification using prompt hooks. Validates commit messages, code patterns, and conventions using AI before allowing operations. Use to set up intelligent guardrails.
Audit connected MCP servers for token overhead, redundancy, and security. Use when sessions feel slow or before adding new MCPs.
Produce a one-screen map of an unfamiliar area of the codebase: entry points, modules, data flow, callers. Designed to be read in fifteen seconds. Use when the user says "I do not know this area", "give me the map", "zoom out", "orient me".
Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.
Create and manage git worktrees for parallel coding sessions with zero dead time. Use when blocked on tests, builds, wanting to work on multiple branches, context switching, or exploring multiple approaches simultaneously.
Analyze permission denial patterns and generate optimized alwaysAllow and alwaysDeny rules. Use when permission prompts are slowing you down or after sessions with many denials.
Stress-test a plan by walking its decision tree one question at a time. Use when the user wants to pressure-test a design before implementation.
Complete AI coding workflow system. Orchestration patterns, 18 hook events, 8 agents, cross-agent support, reference guides, and searchable learnings. Works with Claude Code, Cursor, and 32+ agents.
Claude Skills — questions
Answers built from the skills we actually parsed.