Agent Skills

OpenProse

prose

Run, lint, and manage OpenProse contract-markdown workflows and ProseScript; interpret `prose` commands and execute or validate multi-step agent orchestrations.

Alef Polyglot Binding Generator

alef

Generates fully-typed language bindings and scaffolding for Rust libraries across 16 target languages, and provides CLI workflows for generate, build, test, ver

TypeClaw Plugins Guide

typeclaw

Comprehensive authoring and operational guide for writing and operating TypeClaw plugins: defining plugins, tools, subagents, cron jobs, skills, and hooks.

Writing Plans

SuperAntigravity

Create precise, bite-sized implementation plans from a spec so engineers can implement features reliably using TDD and exact file/command instructions.

clj-surgeon — Structural Clojure Refactoring

clj-surgeon

A babashka CLI toolbox for structural edits on Clojure/ClojureScript: extract forms, reorder, rename namespaces, merge/split CLJC, and analyze deps and extracts

Bug Review

capsem

Structured, per-bug review workflow: confirm, validate or push back, get agreement, implement TDD fixes, and commit with changelog — one bug per commit.

Golang Code Style

cc-skills-golang

Human-coded Go style guidelines for clarity, function design, control flow, and idiomatic practices — use when writing or reviewing Go code, creating linters, o

Code Spec Backfill

liza

Identify missing function-level contracts and backfill docstrings and type annotations; report ambiguous gaps with misuse scenarios. Incremental, state-driven w

Goal Forge

goal-forge

Convert a rough coding idea into a verified SPEC.md and an executable Codex /goal (GOAL.md) with measurable acceptance criteria.

Language‑Agnostic Coding Principles

claude-code-workflows

Opinionated, language-agnostic principles for writing maintainable, readable, and secure code — use when implementing features, refactoring, or reviewing code q

Multi-perspective Code Review

claude-code-blueprint

Run a comprehensive, multi-agent code review that covers quality, security, and database concerns and synthesises a severity-ranked findings table.

Fresh Eyes Review

agent-skills

Quickly re-read recently changed code to catch obvious bugs, typos, and edge cases before committing.

spec-gen: Execute Refactor

spec-gen

Apply a confirmed refactoring plan safely: reads a refactor plan, applies changes as small, test-gated mini-developments, and stops on failures to avoid lost co

Finishing a Development Branch

code-virtuoso

A step-by-step playbook to verify, review, choose an integration strategy, write PR messages, push, and clean up when finishing a development branch.

Skill Structure (naming & layout)

majestic-marketplace

Guidelines for SKILL.md structure: naming conventions, frontmatter fields, directory layout, invocation control, and validation rules to author correct skills a

Agent Creator

code-virtuoso

Interactive guided tool that helps design focused sub-agents (specialist, role, or team-lead) with correct frontmatter, tool permissions, and system prompts.

Prompt Caching Patterns

ai-toolkit

Guidelines and patterns for implementing prompt caching with Anthropic APIs to reduce input-token costs and latency, including TTLs, breakpoints, and hit-rate m

Pair Programming

vexjoy-agent

Interactive micro-step pair-programming protocol: announce changes, show diffs, wait for user approval, apply, and verify (lint/tests).

Incur CLI Framework

incur

TypeScript framework to build CLIs that work for both AI agents and humans, with typed schemas, structured outputs, and MCP/skill generation.

Code Graph

claude-bootstrap

Sub-millisecond AST-based code graph for symbol lookup, dependency analysis, call tracing, and blast-radius detection to speed code navigation and impact analys

Codemap

codemap

Provide instant architectural context for a codebase: structure, dependencies, diffs, and cross-agent handoffs to guide safe editing and analysis.

Building Agents

claude-skill-registry

Guidelines and templates for designing, validating, and maintaining Claude Code agents (subagents), including schema, naming conventions, tooling and security b

Vet — proactive code vetting

vet

Run a vet-style review immediately after each logical code change to detect issues in diffs and conversation history; complements tests but focuses on human/age

UXC — Unified eXecution CLI

uxc

Discover, inspect, and invoke schema-exposed remote interfaces (OpenAPI, GraphQL, gRPC, MCP, JSON-RPC) via a single CLI contract with deterministic JSON envelop

Zylos Shell Channel

zylos-core

Channel skill that connects a CLI REPL to a Claude-like backend via a Unix socket, routing user input to the agent and delivering responses back to the REPL.

/verify — Verification Before Completion

specialist-agent

Run fresh verification commands (tests, build, lint, types) and require full output evidence before claiming work is complete or merging changes.

Drizzle ORM Knowledge Patch

nevaberry-plugins

Add knowledge about Drizzle ORM changes (v1.0.0-beta.x) — validator import consolidation, Effect Schema support, node-sqlite driver, and .comment() query taggin

Skillshare Devcontainer (devcontainer CLI runner)

skills

Run CLI commands, tests, and debugging reliably inside the project's Linux devcontainer to avoid host-architecture mismatches and preserve isolated test state.

Ralph PRD Converter

claude-build-workflow

Convert product requirement documents (PRDs) or Markdown specs into Ralph's prd.json format, producing small verifiable user stories for autonomous execution.

Manten — Lightweight Async Testing Patterns

manten

Compact Node.js testing patterns with standalone imports, AsyncLocalStorage-based context, concurrency controls, hooks, snapshot testing, and simple timeouts/re