Skills

Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.

ast-grep

7729

OnlyTerp/windsurf-unlocked

Skill

Use ast-grep for structural (AST-aware) code search and refactoring instead of plain ripgrep when the intent depends on code structure — not just text matching. Triggers on refactors, codemods, "find all X that don't Y", or any search where naive grep would miss edge cases.

not rated 50 6mo ago A 66 tokens

Plateeocondense/r10-wshobson-commands-seo

Skill Claude CodeCodex

📈 SEO & Content Marketing skill suite derived from wshobson/commands. Keyword research, content audits, SERP analysis, technical SEO and content strategy. Provides 10 specialised commands for seo, content, marketing workflows.

not rated 50 6mo ago A 57 tokens

yt2bb

7735

Agents365-ai/yt2bb

Skill Claude Code

Use when the user wants to repurpose a YouTube video for Bilibili, add bilingual (English-Chinese) subtitles to a video, or create hardcoded subtitle versions for Chinese platforms.

not rated 50 2mo ago C 43 tokens original MIT

research-craft

7736

nik1t7n/research-craft-skill

Skill Codex

Use when planning, reviewing, or improving research work: choosing research problems, designing ML/AI experiments, reading papers, building experiment loops, analyzing outputs, writing research notes, or turning vague curiosity into a disciplined research plan. Emphasizes avoiding absorbed problems, upgrading…

not rated 50 4mo ago A 76 tokens original MIT

minions

7737

bahni-m/minions

Skill Claude CodeCodex

PM Ops — orchestrator of the minions AI subagent team. Single entry point: decomposes requests, delegates to minions- subagents in parallel or sequence, aggregates output.

not rated 50 3mo ago A 0 tokens

vowline

7738

chojondocho/vowline

Skill Codex

Universal operating skill: bind the public task, act from evidence, preserve boundaries, and verify the delivered result.

not rated 50 5mo ago A 26 tokens original MIT

brin-check

7739

superagent-ai/brin

Skill Claude CodeCodex

Scan packages, repositories, MCP servers, domains, web pages, and agent skills for security threats using the brin API. Use this skill before installing dependencies, visiting URLs, or integrating external resources.

not rated 50 7mo ago A 44 tokens

conductor

7741

jnorthrup/conductor2

Skill Claude CodeCodex

Compact Conductor skill. Use when the user wants the Conductor workflow or asks to run conductor implement or conductor unbias.

not rated 50 7mo ago A 33 tokens original Apache-2.0

code-review

7742

killop/code-review-skill

Skill Claude CodeCodex

A process for reviewing all code in a specified directory, dividing the work by module, and producing a report of discovered problems with their authors.

not rated 50 7mo ago A 49 tokens

skill-creator

7743

wuding129/agentClaw

Skill Claude CodeCodex

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

not rated 50 7mo ago A 64 tokens

xueqiu-summary

7745

chenmuwen0930-rgb/openclaw-skill-snowtrace

Skill Claude Code

A Chinese-language skill that gathers recent posts from followed Snowball influencers and market data for a user's watchlist. Snowball is a Chinese investment social network, and the skill combines the results into an investment reference report.

not rated 50 8mo ago A 40 tokens original MIT

ruby-rails-ci-matrix

7746

aki77/csb

Skill Claude Code

Maintain the Ruby and Rails version matrix tested in CI for a Ruby gem. Use this when you need to remove EOL versions, add the latest supported versions, and update gemfiles and gemspec accordingly. Always use this for requests like 'remove unsupported Ruby/Rails versions', 'add the latest Rails', or 'update the CI…

not rated 50 4mo ago A 75 tokens original MIT

SafeAgent-Beihang/clawguard

Skill Claude CodeCodex

ClawGuard Threat Detector - Real-time behavioral monitoring, attack pattern detection, MITRE ATT&CK mapping, and AI-powered anomaly detection for OpenClaw runtime environments.

not rated 50 7mo ago A ✓ AI review 40 tokens

octostore

7750

octostore/octostore.io

Skill Claude CodeCodex

Coordinate independent agents so one leads a group or owns one exact task before side effects.

not rated 50 today B 21 tokens original MIT

persona-cloner

7751

Ca1nlee/persona-cloner-skill

Skill Claude CodeCodex

Build an OpenClaw-ready public-figure persona package from public materials. Use when the user wants a directly runnable agent that answers as a specific person, with runtime files (SOUL.md, IDENTITY.md, AGENTS.md, MEMORY.md) as the default deliverable. Prioritize hard behavioral controls so the shipped runtime stays…

not rated 50 8mo ago A 91 tokens 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: