agent-skills plugins

2,067 tagged agent-skills, measured the same way as everything else here.

Browse within: claude-code-plugin 254cursor 194agentic-ai 109agents 102claude-code-marketplace 97skills 93cli 84claude-code-skills 79agentskills 70ai-tools 68ai-coding 66LLM 63antigravity 57claude-code-plugins 57

audit-protocol

745

sturec5/code-audit-protocol

Plugin Claude Code

Bundles 1 skill · 133 tokens together

Audits a code change against a 54-phase failure taxonomy and reports what it did not check, not just what it found. Domain overlays run first and force critical-path treatment.

not rated 6 27d ago A tokens not measured original MIT

postey-analytics

747

posteyai/skills

Plugin Claude Code

Bundles 1 skill · 48 tokens together

Read what a post or account actually did and turn it into the next content decision.

not rated 6 +1 6d ago A tokens not measured original MIT

decision-ledger

748

Dupflo/decision-ledger

Plugin Claude Code

Bundles 3 skills · 225 tokens together

Three agent skills that catch structural decisions as you make them, ask you to defend each one, and hand back a mastery map of your project: /ledger, /ledger-audit, /ledger-report.

not rated 6 +2 changed today A tokens not measured original MIT

venture

749

heyparsadev/claude-venture-plugin

Plugin Claude Code

Bundles 9 skills, 3 agents · 2,044 tokens together

Business copilot: market research, competitor analysis, customer discovery, PMF assessment, GTM strategy, business model — chained through a per-venture workspace. Works in Persian and English.

not rated 6 +2 29d ago A tokens not measured original MIT

solidjs-v2-skills

750

khmm12/solidjs-v2-skills

Plugin Claude Code

Bundles 3 skills · 295 tokens together

SolidJS 2.0 skills for Claude Code: write, migrate, and review solid-js 2.x code without React/1.x reflexes.

not rated 8 +2 changed 7d ago A tokens not measured

oduncu

751

erayendes/oduncu

Plugin Claude Code

Bundles 1 skill · 138 tokens together

Silent-executor mode. Give it a task, it says "yaparım...", does the work, says "tamam." — no explanation, summary, code block, progress note or task list in between. Questions still get full answers. Commands: /oduncu kalk — mode on /oduncu yat — mode off /oduncu talk — trace on: the completion line carries the.

not rated 6 +1 20d ago A tokens not measured original MIT

grill-me

752

joshuawheelock/grill-me

Plugin Claude Code

Bundles 1 skill · 93 tokens together

Help developers using coding agents retain solution knowledge by quizzing them on the code they maintain.

not rated 6 +1 20d ago A tokens not measured original MIT

remakebench-skills

753

RemakeBench/skills

Plugin Claude Code

Bundles 8 skills · 978 tokens together

Evidence-driven Claude Code skills for playable 3D production, image-to-3D reconstruction, quality gates, gameplay verification, and cross-model subagents.

not rated 6 changed 5d ago A tokens not measured original MIT

engineering-docs

754

fattain-naime/engineering-docs

Plugin Claude Code

Bundles 22 skills, 4 agents, 1 hook, 1 MCP server · 1,592 tokens together

22 engineering documentation skills covering the complete software lifecycle: business concept, project planning, personas, specs, feasibility, UX flow, architecture, design system, API, database, ADR, access control, security, testing, implementation, deployment, SLO, operations, disaster recovery, and incident…

not rated 6 +2 6d ago A tokens not measured original MIT

aposd-skills

755

mhenke/john-ousterhout-skills

Plugin Claude Code

Bundles 4 skills · 138 tokens together

Use when writing, reviewing, or modifying any code. Applies complexity-driven design principles from A Philosophy of Software Design, 2nd Edition by John Ousterhout.

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

Nolpak14/getregdata

Plugin Claude Code

Bundles 28 skills · 5,735 tokens together

Free company lookups straight from official public APIs across 28 jurisdictions plus global LEI resolution - no Apify token and no per-result cost. Resolve and verify a company by name or national identifier.

not rated 6 1mo ago A tokens not measured original MIT

registry-maintenance

757

buildinternet/releases

Plugin Claude Code

Bundles 8 skills · 706 tokens together

Operator skills for maintaining the registry — ingest, backfills, overviews, release content, playbooks, coverage. Most need an admin API key.

not rated 6 today A tokens not measured original Apache-2.0

cyxj-image-studio

758

chenyuxiaojin/xiaochen-skills

Plugin Claude Code

Bundles 2 skills · 229 tokens together

An image-making add-on for creating posters, book covers, album covers, and video cover images in several visual styles and sizes.

not rated 6 6d ago A tokens not measured original MIT

usetemi

759

usetemi/skills

Plugin Claude Code

Bundles 7 skills · 593 tokens together

Open-source agent skills from Temi for Claude Code, Claude Cowork, Codex, Cursor, and Gemini CLI.

not rated 6 1mo ago A tokens not measured original MIT

skills-board

760

TommyBez/skillsboard

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 141 tokens together

Search your team's Skills Board library over MCP and get the install command for a saved skill or a published collection.

not rated 6 +1 today A tokens not measured original MIT

villagesql

761

villagesql/villagesql-skills

Plugin Claude Code

Bundles 2 skills · 165 tokens together

Skills for VillageSQL (MySQL with extensions): build extensions end-to-end (including porting PostgreSQL extensions to MySQL) and install VillageSQL Server.

not rated 5 today A tokens not measured

inquisitor

763

iamalisson/inquisitor

Plugin Claude Code

Bundles 1 skill, 1 hook, 1 MCP server · 55 tokens together

Hypothesis-driven problem solving for AI agents: probe, falsify, escalate — never blind-retry. Bundles the behavioral skill and the inquisitor-mcp server (web search, project analysis, code tracing, phase tracking).

not rated 5 1mo ago A tokens not measured original MIT

agentic-skills

767

theagenticguy/agentic-plugins

Plugin Claude Code

Bundles 1 skill, 7 MCP servers · 237 tokens together

Flagship skills for AI coding agents. Includes workbench-builder: disposable localhost Bun.serve + bun:sqlite + React 19 + Astryx workbenches with a two-way human↔agent loop over SSE — eval viewers, PR review rooms, document-redline surfaces, grid/spreadsheet editors, multi-surface triage queues, and trace replays…

not rated 5 1mo ago A tokens not measured original MIT

junebug

768

skycube/junebug

Plugin Claude Code

Bundles 1 skill · 89 tokens together

Concise, plain-language response mode for readers with a limited attention span and/or smaller vocabulary. Cuts filler, hedging, and politeness. Keeps every fact. Caps answer options at 3 with a read-more escape hatch. 150 words / 45 sec by default; /junebug lite doubles the budget.

not rated 5 1mo 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: