agent-skills commands

starslingdev/skills

Command Claude Code needs its repo

Check a published skill's skills.sh security audit, decide the next action, and drive a stale badge to green unattended.

eugenelim/agent-ready-repo

Command Claude Code

Check AGENTS.md, CLAUDE.md, and the projected agent artifacts (skills, subagents, commands) against the repo's conventions.

martinemde/skillet

Command Claude Code

Draw a nice ASCII art picture of "$ARGUMENTS".

oneworks-ai/app

Command Claude Code

A command system for a channel-based application, including command parsing, subcommands, translations, and permission checks. It defines commands with a chained builder style and routes them through shared middleware.

zakelfassi/skills-driven-development

Command Claude Code

Forge a new SkDD skill from a repeated pattern (shortcut for the skillforge meta-skill).

onfire7777/universal-ai-skills-library

Command Claude Code

Load a skill on demand through the universal router.

EntityProcess/agentv

Command Claude Code

Run the full deployment pipeline: plan, execute, and verify.

wonsukchoi/domain-experts

Command Claude Code

Scan a project and suggest domain-expert skills it would benefit from, then draft the ones the user picks.

qarium/goga

Command Claude Code

Command dispatcher for brainstorm.

hec-ovi/research-skill

Command Claude Code

Use the bundled Codex research skill to recall, refresh, or store project-scoped research.

voodootikigod/skills-check

Command Claude Code

Command "release" from voodootikigod/skills-check, covering arguments and steps.

lebsral/DSPy-Programming-not-prompting-LMs-skills

Command Claude Code

You are a routing assistant for DSPy AI skills. Understand the user's problem, pick the best skill, and generate a ready-to-run prompt.

EntityProcess/allagents

Command Claude Code

Extract a learning from the recent conversation and add it to the appropriate instruction file.

victorzhong0110/skill-evolution

Command Claude Code needs its repo

You are a bridge monitor for the skill-evolution framework. Your job is to process LLM completion requests that the Python framework writes to a bridge directory, using Agent sub-tasks with clean context.

HartBrook/lookagain

Command Claude Code

Run sequential code review passes with fresh contexts to catch more issues.

tonypls/agentic-product-launch

Command Claude Code

Take a shippable AI product, agent, indie SaaS, app, or devtool from ready to launched.

inetgas/arch-compiler

Command Claude Code

Compile a project spec into deterministic architecture outputs using the Architecture Compiler skill.

kensaurus/cursor-kenji

Command Claude Code

Review these files for compliance: $ARGUMENTS.

JordanGunn/nunchuck

Command Claude CodeCursor

Diagnoses software failures by combining deterministic evidence gathering with agent judgment. Models failures as medical cases. Idempotent — run repeatedly until confident diagnosis, then generate schema-based treatment.

emaraschio/cursor-commands

Command Claude CodeCursor

Turn a rough task into an agent Goal (six core sections, 3 to 5 success criteria, helper goals when parallel, two-step approval); plan-only, no execution in the same turn.

itallstartedwithaidea/MiniAgent

Command Claude Code

Analyze the Google Ads account using the google-ads-analysis skill. Pull campaign performance data, identify anomalies, and provide actionable recommendations.

nyldn/claude-dolphin

Command Claude Code

WCAG 2.2 AA accessibility compliance check.

timothywarner-org/ai901-cert-buddy-claude

Command Claude Code

Run a short AI-901 practice quiz (default 5 questions), one at a time, with progress and an end-of-quiz score. Use count=1 for a single question.

navveenb/lean-agentic-ai

Command Claude Code

Analyze LLM API usage in a codebase and recommend model right-sizing to reduce cost, carbon, and complexity.