Plugins for Anthropic's Claude Code, Codex, Cursor and more
This repository also configures its own agents. See what claude_skills tells them →
Skill Claude Code
Modern Git workflows, best practices, and commands. Use when the user asks about Git branch management (git switch vs checkout), file restoration (git restore), fixup commits, autosquash rebasing, git worktrees, rerere, force-with-lease, repository cleanup (git clean, stale branches, bloat analysis), history…
Skill Claude Code
Facade skill for multi-agent swarm orchestration in Claude Code — routes to specialist skills covering primitives, spawning, operations, and patterns. Use when coordinating multiple agents in parallel, building pipeline workflows with dependencies, running parallel code reviews, creating self-organizing task queues…
Skill Claude Code
Transforms validated /linear-walkthrough artifacts into one presentation-ready deck outline per major codebase component. Use when the user asks to create a presentation, prepare a walkthrough deck, build an onboarding deck, produce an architecture review deck, or summarize a codebase for a technical audience.…
Skill Claude Code needs its repo
Badge design and selection knowledge base for shields.io badges in README files. Use when writing or updating READMEs, choosing badge layouts, selecting badge styles, adding project health indicators, or picking Simple Icons logo slugs. Covers shields.io URL encoding rules, static vs dynamic badge selection, style…
Skill Claude Code
Strategic rebase with mandatory pre-analysis. Use when asked to rebase a branch onto main (or any target). Runs a file-level diff of both sides before touching git, produces a per-file disposition plan (KEEP/MERGE/DROP/REWRITE), and only then executes the rebase. Prevents surprise conflicts and silent data loss from…
Skill Claude Code needs its repo
Bulk-refresh research entries in ./research/ using parallel research-curator agents. Use when /refresh-research is invoked, stale research needs updating, or bulk re-verification of research entries is requested. Inventories entries by review date and age, runs RT-ICA pre-flight, spawns agents in waves of 5, updates…
Skill Codex
Use when working in a repository that uses bd or Beads for durable project task tracking, issue dependencies, blocker management, multi-session handoff, or shared work memory. Trigger when the user asks to find ready work, claim or close tasks, create follow-up work, inspect blockers, recover project context, or…
Skill Claude Code needs its repo
Orchestrate research entry lifecycle in ./research/ — create, batch-import, refresh stale entries, and validate structure. Use when asked to add a tool, research a URL, document a library, refresh research, validate entries, or given any tool or library URL. Supports --batch (parallel multi-URL), --rerun (refresh one…
Skill Claude Code
Look up prior Claude Code sessions when context is lost or forgotten. Use when asked what was done before, what happened in the last session, or any request to recall past conversation history, prior decisions, experiments, or outcomes. Indexes and searches raw JSONL transcripts from /.claude/projects/ via DuckDB.…
Skill Claude Code
Walks a user from one rough content idea to a finished post, platform-adapted variants, and repurposed follow-on assets using a 7-step sequential prompting workflow. Use when the user wants to turn a half-formed idea, frustration, story, or client situation into publishable content quickly and consistently — covering…
Skill Claude Code
Builds comprehensive Claude Code skills using parallel research agents — categorization, parallel documentation gathering, anti-hallucination checkpoints, and final validation. Use when building a skill from official docs, when "research for skill" or "create comprehensive skill" is requested, or when extensive…
Skill Claude Code needs its repo
Transitions a GitHub milestone from planning to active execution. Use when the team is ready to begin a sprint or release cycle — bulk-transitions open issue labels from status:needs-grooming to status:in-progress, updates GitHub Projects V2 Status to In Progress, and confirms before applying changes. Requires…
Skill Claude Code needs its repo
Parse a markdown file's unchecked checkbox items (- [ ]) and generate a self-organizing Claude Code swarm task pool. Use when you have a todo.md, checklist.md, or any markdown file with checkbox items and want to dispatch them as parallel swarm tasks using TeamCreate + TaskCreate + worker agents. Skips checked items…
Skill Claude Code
API reference for Claude Code multi-agent swarm tools -- TeamCreate, SendMessage, TeamDelete, TaskCreate/Update/List/Get, and Agent tool parameters. Use when looking up tool signatures, message schemas, shutdown sequences, error handling patterns, or debugging swarm operations. Covers direct messages, broadcasts, plan…
Skill Claude Code
Recipes and patterns for Claude Code multi-agent swarms. Use when building parallel specialist reviews, pipeline workflows, self-organizing swarms, research-then-implement flows, plan approval gates, coordinated multi-file refactoring, or any divide-and-conquer orchestration pattern requiring TeamCreate, TaskCreate…
Skill Claude Code
Covers how to create agents in Claude Code swarms -- subagents vs teammates, built-in agent type catalog (Bash, Explore, Plan, general-purpose, claude-code-guide), plugin agent types from compound-engineering, spawn backend selection (in-process, tmux, iterm2) with auto-detection logic, and environment variables…
Skill Claude Code
Creative reasoning framework for ill-defined problems where conventional solutions are suboptimal. Use when the problem has ambiguous goals, vast solution space, no single correct answer, or requires innovation. Implements three paradigms — combinational (novel combinations of familiar ideas), exploratory (expand…
Skill Codex
Use when the user asks what to do next, asks for a plan under uncertainty, challenges stalled or low-trust work, requests multiple possible approaches before action, or needs an evidence-first loop that uses RT-ICA-style prerequisite checks, adversarial review, subagent coordination, real validation, and durable…
Skill Claude Code needs its repo
Ensemble SOLID review — fans the ruleset across overlapping focused workers over the same code, then reduces by corroboration.
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: