Everything for Claude Code

Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 389,707 indexed, measured the same four ways as everything else here.

retro

38953

rubin-johnson/retro

Plugin Claude Code

Bundles 1 skill, 4 commands, 1 hook · 56 tokens together

Structured error and success logging for agentic coding. Log what went wrong, trace it back to your input, and generate CLAUDE.md rules from patterns.

not rated 2 6mo ago A tokens not measured original MIT

claude-harness-workflow

38954

NiroDu/claude-code-harness-kit

Skill Claude CodeCodex

Use when a repository works with claude-code-harness-kit and you want Claude to restore state, initialize or validate the harness, ignore stale session context, and continue work through the repo artifacts instead of guessing from memory.

not rated 2 5mo ago A 51 tokens original Apache-2.0

test-writer

38955

fschifone/claude-setup-wizard

Agent Claude Code

Writes unit and integration tests for new or modified code. Use this agent when the user asks to add test coverage, test-drive a feature, or when a PR lacks tests.

not rated 2 6mo ago A 39 tokens original MIT

silk

38956

hjxccc/silk-starry

Command Claude Code

A command for managing Claude Code project memory, including CLAUDE.md and related memory files.

not rated 2 5mo ago A 31 tokens original MIT

ui-ux-architect

38957

RohitBind123/claude-setup

Agent Claude Code

Use this agent when you need a comprehensive UI/UX audit, design review, or visual refinement of the app's screens and components. This agent focuses exclusively on visual design, layout, spacing, typography, color, motion, accessibility, and responsiveness — it does not touch functionality or application…

not rated 2 6mo ago A 659 tokens original MIT

digital-person

38958

justinjia0813/digital-person-skill

Skill Claude Code

A tool that studies someone’s public posts on WeChat public accounts, Weibo, and Twitter/X to extract their ideas, decision methods, and writing style.

not rated 2 6mo ago A 121 tokens

reflect

38959

rodrigo-kiko/claude-reflect-skill

Skill Claude CodeCodex

Analyzes development sessions to extract learnings from corrections, successful patterns, and revealed preferences. Use when the user wants to reflect on a coding session, extract lessons learned, or update project knowledge. Triggered by /reflect command or phrases like "reflect on this session", "what did we learn…

not rated 2 10mo ago A 68 tokens original MIT

audit-deep-logic

38960

daanvandenbergh/claudekit

Skill Claude Code

Top-down, whole-system audit of a codebase's DEEP LOGIC - the bugs that live in the SEAMS between modules, not inside any one file. Finds contracts that drift across module boundaries, invariants enforced on one path but broken on a sibling path, cross-cutting responsibilities (deletion cascade, tenant-scope…

not rated 2 28d ago A 0 tokens

pulse-update

38961

codebloodedai/claude-code-ops-commands

Command Claude Code

Update a Pulse project brief (actions taken, next steps, risks, current reality) based on the work we just did in this session.

not rated 2 7mo ago A 30 tokens original MIT

review

38963

michaelcjoseph/agent-coding-setup

Skill Claude Code

Run the full review panel — test-specialist, security-auditor, code-reviewer, code-simplifier, and architecture-reviewer — in parallel against the current uncommitted working tree, then return one consolidated verdict.

not rated 2 6mo ago A 0 tokens original MIT

undrift-full

38964

larya-dot-eu/undrift

Skill Claude Code

Deep-mines the last 50 sessions of a project to find recurring corrections, repeated instructions, and reverted changes. Writes proposed CLAUDE.md rules to CLAUDE.md.undrift — review and merge manually. Run when patterns keep repeating or after /undrift-check flags a project as needing attention.

not rated 2 5mo ago A 66 tokens original MIT

doc-lint

38966

AnyiWang/agent-doc-lint

Skill Claude Code

Split instruction files (CLAUDE.md / AGENTS.md) into skills and keep them drift-free. Use when asked to audit docs, split docs, lint docs, reorganize documentation, or extract skills.

not rated 2 8mo ago A 46 tokens original MIT

mc-expert

38967

sikadi233-hub/mc-dev

Agent Claude Code

Use this agent when the user asks anything about Minecraft mod or plugin development - creating mods, adding features, debugging API issues, understanding Forge/Fabric/NeoForge/Paper APIs, or choosing the right approach. This is the primary entry point for Minecraft development tasks. It analyzes requirements…

not rated 2 3mo ago A 142 tokens original MIT

matchers

38968

romilly/claude-code-helpers

Command Claude Code

Command "matchers" from romilly/claude-code-helpers, covering pyhamcrest custom matchers guide, when to create a custom matcher, spotting opportunities, before - verbose and redundant length check and after - expressive, no length check needed.

not rated 2 9mo ago A 0 tokens original MIT

scientific-figures

38969

tknapen/lab-conventions

Skill Claude CodeCodex

Produce publication-quality scientific figures in a restrained, vision-science-inflected house style. Use this skill whenever the user asks for plots, figures, or visualizations for a paper, preprint, talk, or grant — especially for vision, psychophysics, neuroscience, or computational modeling work — and any time the…

not rated 2 changed 1mo ago A 133 tokens

project-init

38970

whchoi98/project-init

Plugin Claude Code

Bundles 1 skill, 9 commands, 1 agent · 388 tokens together

Initialize and maintain Claude Code project structures with adaptive project detection, CLAUDE.md quality scoring, and auto-sync documentation workflows.

not rated 2 changed 3d ago A tokens not measured original MIT

kusa

38971

kaze-jp/kusa

Command Claude Code

Open markdown files in kusa for beautiful rendered preview and review.

not rated 2 5mo ago A 14 tokens original MIT

new-sprint

38972

chrisdev1187/claude-code-forge

Command Claude Code

Run this at the start of a new sprint to create the gate file and update state.

not rated 2 7mo ago A 0 tokens original MIT

CLAUDE

38973

keychain-io/trustable-ai

Command Claude Code

Solves command invocation errors through validation, helpful error messages, and guided execution.

not rated 2 9mo ago A 0 tokens original MIT

closing

38974

Bidiche49/claude-conf

Skill Claude Code

Switch to freelance closing mode — mission qualification, scoping, quoting, and client relationship management.

not rated 2 6mo ago A 20 tokens original MIT

business-context

38975

ChristopherKahler/operator-kit-47

Command Claude Code

Extract comprehensive business context through structured interview — produces the foundation document every other Operator consumes.

not rated 2 4mo ago A 20 tokens

criar-spec

38976

VictorCostaOliveira/agents-tdd-flow

Skill Claude Code

Creates specifications before code. Phase 1 (Specify) is always delegated to the requison subagent — it elicits requirements and drafts content aligned to this skill’s template. Use when starting a project, feature, or large change without a spec. With Figma, run the MCP flow (below) before locking the spec. Suggested…

not rated 2 8d ago A 78 tokens

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: