A minimal catalog of my favourite skills for working with claude
This repository also configures its own agents. See what claudefiles tells them →
Plugin Claude Code
Bundles 13 commands, 9 agents · 936 tokens together
Lean sprint workflow for Claude Code. Twelve commands (init/research/plan/execute/review/retro/flow/advisor/triage/serve/paper/comment), nine agents, .jira/ state with Gherkin acceptance predicates per sprint, GitHub issue + PR integration, Nyquist validation by default.
Plugin Claude Code
Bundles 4 commands · 108 tokens together
Per-project workflow workspace. Hosts .project/.jira/.warden state in a private /.studio/ git repo and symlinks each project root into its workspace slug. No tool/skill modifications — consuming plugins see expected paths.
Plugin Claude Code
Bundles 1 skill, 6 commands · 287 tokens together
Frontend design skill with 17 steering commands for impeccable UI/UX. Based on Impeccable (https://impeccable.style).
Plugin Claude Code
Bundles 5 commands · 199 tokens together
Acceptance test playbook. Three runtimes (bash, hurl, agent-browser), three modes (design, run, triage). Project-coupled, sprint-agnostic. Composes with jira sprint features/ and /jira:flow.
Plugin Claude Code
Bundles 50 skills, 2 agents · 2,562 tokens together
Rigorous agent workflows from Lauren Tan's pstack, ported to Claude Code. /pstack:poteto-mode matches a task to a playbook and routes through how, why, architect, arena, swarm, interrogate, unslop and 24 principle skills; subagents run as pstack:poteto-agent.
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: