AI & ML

wxy Skill

Core skill manager for evoskills. Handles skill lifecycle (init, install, remove, update) and skill contributions.

wxy Skill

Complete release workflow for project versioning. Covers branch creation, testing validation, documentation updates, PR creation via skills, and GitHub Release creation. Emphasizes stability through branch isolation strategy.

wxy Skill

Perform code quality checks before commit. Validates code standards, security, architectural consistency. Runs TypeScript compilation, linting, test coverage verification.

wxy Skill

创建/输出文件的安全约束。禁止 HERE 文档创建文件；大文件输出需分段写入同一文件，避免会话超限。

wxy Skill

强制在每次回复前读取项目指令文件，避免遗漏规范。与 _context-ack 配合，仅负责“读取约束”，不负责输出格式。

wxy Skill

Enforce TypeScript type safety guidelines. Ensures proper typing, prevents type-related runtime errors. Focuses on mock data creation, enum handling, and complex type initialization.

brorlandi Bundle

Establish and then run a repository's release convention: semantic version bump, changelog and release notes written from the commits since the last release, git tag, GitHub release with versioned assets, in-app or public changelog screens, and app store notes. The first time it runs in a repo it detects the stack (web app, Android, iOS, macOS/desktop binary, library/CLI, or a monorepo holding several apps), agrees the convention with the user, and records it in `.claude/release.json` plus a short CLAUDE.md section — so every later run, and any agent working without this skill, knows where the version lives, which changelog to update, and how the release is published. Use this skill whenever the user mentions release notes, changelog, novidades, semantic versioning, "fechar uma versão", "nova versão", "subir a versão", "bump", tags, GitHub releases, publishing a build to a store, or asks what changed since the last release. Also offer it proactively right after a PR is created or merged and after finishing a

barateza Bundle

Apply when writing, modifying, or reviewing code. Behavioral guidelines to reduce common LLM coding mistakes. Triggers on implementation tasks, code changes, refactoring, bug fixes, or feature development.

medride Skill

Automates plan review with a staff engineer agent. Spawns reviewer, presents feedback, handles iterations - all through guided prompts.

campbellmcgregor Skill

Conversational guidance for building software with AI agents, covering workflows, tool selection, prompt strategies, parallel agent management, and best practices based on real-world high-volume agentic development experience. Use this skill when users ask about setting up agentic workflows, choosing models, optimizing prompts, managing parallel agents, or improving agent output quality.

amiable-dev Bundle

Multi-model code review with structured feedback using LLM Council peer evaluation. Use for PR reviews, code quality checks, or implementation review. Keywords: code review, PR, pull request, quality check, peer review, feedback

apappascs Skill

Shows token usage, model distribution, turn count, duration, and tool usage for a Claude Code session. Use when the user asks about token usage, session cost, model breakdown, or says "session stats" or "how much did this session use".

apappascs Skill

Generates a context recovery prompt from a past Claude Code session so a new session can pick up where it left off. Use when the user says "resume from", "pick up where I left off", "continue that session", "context recovery", or wants to start a new session with context from an old one.

belumume Bundle

Implement RLM-style (Recursive Language Model) orchestration for complex tasks. This skill should be used when facing large context requirements, multi-part tasks that would benefit from parallel execution, or when context rot is a concern. Automatically decomposes tasks, spawns parallel subagents, aggregates results, and iterates until completion. Inspired by the RLM research paper (arXiv:2512.24601).

watzon Bundle

Load this before writing any code to prevent vibe rot and ensure high-quality, durable output. Standing baseline for every coding session under AI-assisted development: proof before done, small bisectable changes, reuse over clones, honest tests, architecture boundaries, and human accountability. Also use for "make this last", "stop vibe rot", "quality harness", "code health audit", "laws for agents", "fitness functions", "review agent PRs", and harness setup. Progressive docs live beside this file; load them when the task needs depth.

getterdoneinc Bundle

Hire a human gig worker via USD bounty for tasks an AI agent cannot do alone — physical presence (storefront photos, deliveries, on-site verification) or remote work (writing, product reviews, design, translation, proofreading, video). Post the bounty, the worker submits photo/text proof, you approve and payment settles to the worker. Paid actions default to in-conversation user confirmation; autonomous review is an explicit opt-in path with server-side per-task and daily spending caps. One-time agent setup at https://getterdone.ai/register-agent.

nijingzhe Bundle

Use SimpleLLMFunc to build typed async LLM functions, chat agents, tools, event-stream consumers, and PyRepl/selfref workflows. Use when writing or editing app code that imports SimpleLLMFunc, configures provider.json, adds @llm_function/@llm_chat/@tool, chooses OpenAICompatible or OpenAIResponsesCompatible, or mounts PyRepl/FileToolset.

amiable-dev Bundle

Verify code, documents, or implementation against requirements using LLM Council multi-model deliberation. Use when you need multi-model consensus on correctness, completeness, or quality. Keywords: verify, check, validate, review, approve, pass/fail, consensus, multi-model

nitzan94 Skill

Audit Agent/Task model routing — reads the dispatch log written by the model-routing PreToolUse hook and breaks down spend by model, subagent type, and project. Use when the user asks 'how's the model routing', 'audit my model usage', 'check the dispatch log', 'is the routing hook working', '/model-audit', or before drafting any public-facing post about Claude Code usage. Requires the model-routing hook to be installed first (see hooks/model-routing in this repo).

elaraai Skill

Data science and machine learning platform functions for the East language (TypeScript types). Use when writing East programs that need optimization (MADS, Optuna, SimAnneal, Scipy, Optimization, GoogleOr), machine learning (XGBoost, LightGBM, NGBoost, Torch MLP, Lightning, GP), Bayesian inference (PyMC), simulation (Simulation DES), ML utilities (Sklearn preprocessing, metrics, splits), conformal prediction (MAPIE), or model explainability (SHAP). Triggers for: (1) Writing East programs with @elaraai/east-py-datascience, (2) Derivative-free optimization with MADS, (3) Bayesian optimization with Optuna, (4) Discrete/combinatorial optimization with SimAnneal, (5) Gradient boosting with XGBoost or LightGBM, (6) Probabilistic predictions with NGBoost or GP, (7) Neural networks with Torch MLP or Lightning, (8) Data preprocessing and metrics with Sklearn, (9) Conformal prediction intervals with MAPIE, (10) Model explainability with Shap, (11) Iterative coordinate descent with Optimization, (12) Constraint programm

mvilrokx Bundle

Launch parallel specialized agents to review a codebase, then synthesize findings through adversarial debate. Use when user says "debate review", "multi-agent review", "codebase review", "full review", or asks for a comprehensive code/architecture/security audit. Also use proactively before major releases, after large refactors, or when preparing production deployments. Supports two modes: "direct" (you coordinate) and "delegated" (a single general-purpose agent coordinates everything autonomously).

adynato Skill

Configure MCP servers for Oh My Pi using repo-local `.omp/mcp.json` without polluting teammates. Covers preferred OMP config locations, adding `.omp/` to `.gitignore` when absent, and common setup patterns with an Atlassian Rovo example. Use when adding or updating MCP servers for a project in OMP.

adynato Bundle

Direct communication standards for replies, status updates, summaries, handoffs, comments, PR notes, admin messages, operational writing, and user-facing agent communication. Use when writing or editing communication that should be extremely informal, brief, and factual, especially when responding to Adar or producing concise internal updates.

ether-moon Bundle

This skill is the primary entry point for creating, modifying, evaluating, and governing the lifecycle of agent skills. Use cases include any new or existing SKILL.md work, including trigger design, structure and resources, evals, benchmarks, model-invocation budgeting, token or cost regressions, description optimization, troubleshooting, or retirement, even when skill-creator is available. It takes precedence over skill-creator for overlapping requests, delegates supported work within an explicit evaluation budget, and retains project policy, evidence requirements, and final acceptance.

umbraco Bundle

Guide for running and debugging this Umbraco MCP server via the CLI. Use when the user wants to list tools, call tools, configure filtering, dry-run, readonly mode, or debug configuration.

umbraco Skill

Guide for installing and configuring the Umbraco MCP server (@umbraco-cms/mcp-dev) as a live MCP connection in an AI client. Use when the user wants to set up, connect, install, or troubleshoot the MCP server itself (as opposed to running it standalone via the CLI).

cmer81 Skill

Use when the user wants a specific weather model, needs ensemble uncertainty ranges, requests seasonal outlooks, or asks for long-term climate projections.

wojisama Bundle

This skill should be used when the user asks to "organize the project rules", "clean up scattered documentation", "把规则迁移到 skills 目录", "优化 skill 路由", "提高 description 命中率", or "减少薄壳重复维护". Activate when a SKILL.md is too large, rules are duplicated across agent entry files, task routing or trigger_examples miss natural user language, or templates / thin shells / validation scripts need drift-resistant maintenance.

timothywarner-org Bundle

Scaffold production-ready Python MCP servers using FastMCP. Use when creating new MCP servers, initializing MCP projects, generating server boilerplate, or setting up MCP development environments. Supports all MCP primitives (tools, resources, prompts) with Pydantic validation, async patterns, and proper project structure.

timothywarner-org Bundle

Audit the CLAUDE.md hierarchy in a repo for drift between what each CLAUDE.md claims and what's actually on disk. Validates that referenced file paths still exist, flags voice violations (em dashes, "ask" as a noun), and checks the ground-truth facts block for stale tokens (MCP spec date, transports, model lineup). Use when the user asks to audit, validate, check, or verify CLAUDE.md files, says "is my CLAUDE.md still accurate", flags possible doc drift, or wants to sanity-check the docs before a course recording or release.

wasp-lang Skill

Start the Wasp dev server and set up full debugging visibility. This includes running the server (with access to logs), and connecting browser console access so the agent can see client-side errors. Essential for any development or debugging work.

wasp-lang Bundle

Adds Wasp knowledge, LLM-friendly documentation fetching instructions, and best practices to your project's CLAUDE.md or AGENTS.md file

weaverse Skill

Capture current work context for handoff to another agent/developer. Gathers git state, todos, and modified files into a structured handoff document saved to the related spec folder.

antoinebou12 Skill

Create and extend MCP (Model Context Protocol) servers in Python using FastMCP and the official SDK. Covers tools, resources, prompts, STDIO vs HTTP transports, logging rules for STDIO, and production best practices. Use when building or modifying MCP servers in Python, adding tools/resources/prompts, debugging MCP servers, or choosing transport and client config.

antoinebou12 Bundle

Produces Mermaid or PlantUML diagram code from user specifications for UML, architecture, and flow diagrams. Use when the user asks for diagram code or output for the generate_uml / generate_uml_image MCP tools. Supports Kroki-renderable output.

antoinebou12 Skill

Creates diagrams via the uml-mcp MCP server (generate_uml, generate_uml_image, validate_uml, list_diagram_types, generate_uml_batch) and returns shareable Kroki URLs or inline chat images. Use when the user wants diagrams, PlantUML/Mermaid/D2/UML, URLs, Kroki, goat/umlet, or diagram_type.