yorrick/agent-skills

Claude Code plugins for automated development workflows — dev-loop, review automation, and more

This repository also configures its own agents. See what agent-skills tells them →

11Stars on the repository
33Mods indexed here, across every type
11d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

dev-loop

02

yorrick/agent-skills

Plugin Claude Code

Bundles 3 commands · 68 tokens together

Automated development loop and ad-hoc workflow generation for orchestrating AI coding agents.

not rated 11 11d ago A tokens not measured original MIT

pr-review

03

yorrick/agent-skills

Plugin Claude Code

Bundles 1 skill · 125 tokens together

Multi-provider interactive PR code review. Runs Claude Code, Gemini CLI, and Codex CLI in parallel, merges findings, then lets you vet each issue before posting to GitHub.

not rated 11 11d ago A tokens not measured original MIT

self-improve-skill

04

yorrick/agent-skills

Plugin Claude Code

Bundles 1 skill · 70 tokens together

Analyzes session transcripts and improves project documentation (CLAUDE.md, README, memory) based on learnings.

not rated 11 11d ago A tokens not measured original MIT

supabase-security

05

yorrick/agent-skills

Plugin Claude Code

Bundles 1 skill · 205 tokens together

Access-control rules for Supabase projects exposed directly to a browser via PostgREST. Covers the three enforcement layers (GRANT, RLS, triggers), the traps that cause privilege escalation, and how anon keys, JWTs and servicerole actually differ.

not rated 11 changed 21d ago A tokens not measured original MIT

task-status

06

yorrick/agent-skills

Plugin Claude Code

Bundles 1 skill · 50 tokens together

A compact, terminal-safe visual summary of task status, weighted estimated progress, next steps, deferred items, and blockers.

not rated 11 11d ago A tokens not measured original MIT

flowchart

07

yorrick/agent-skills

Plugin Claude Code

Bundles 1 skill · 49 tokens together

Create clear process flowcharts and interactive walkthroughs, with evidence-based layout guidance and keyboard checks for the actual delivery surface.

not rated 11 11d ago A tokens not measured original MIT

yorrick/agent-skills

Plugin Claude Code

Bundles 1 skill · 53 tokens together

Present system designs as visual decisions, reuse available diagram skills, and carry the user's choices back into the specification.

not rated 11 11d ago A tokens not measured original MIT

jev-router

09

yorrick/agent-skills

Plugin Claude Code

Bundles 1 skill, 4 agents · 401 tokens together

Asks Jev (via OpenRouter) how long each job will run and, in Claude Code, whether a fresh subagent would do it cheaper. Starts in shadow mode. Off until you turn it on with /jev on.

not rated 11 changed 10d ago A tokens not measured original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: