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.

playwright-browser

6145

91fapiao-cn/playwright-browser-skill

Skill Claude CodeCodex

A browser-automation skill for controlling web pages, including opening sites, clicking elements, filling forms, reading text, taking screenshots, and monitoring page behavior. The instructions are written in Chinese and describe 101 browser tools.

not rated 70 +1 6mo ago A 35 tokens original MIT

deep-research

6146

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Autonomous multi-step deep research engine implementing an iterative Think → Search → Extract → Synthesize → Stop loop. The LLM drives every decision: what to search, what's relevant, what's missing, and when to stop. Produces a cited, magazine-quality report with inline citations, category- specific formatting, and…

not rated 70 +10 4d ago A SkillSpector: pass 147 tokens original MIT

behavioral-economics

6147

Tibsfox/gsd-skill-creator

Skill Claude CodeCodex

Systematic departures from rational choice theory and their implications for economic analysis and policy. Covers cognitive heuristics (anchoring, availability, representativeness), biases (loss aversion, status quo, overconfidence), prospect theory (reference dependence, probability weighting, diminishing…

not rated 70 +1 1mo ago A 103 tokens

levy

6148

seaworld008/Commonly-used-high-value-skills

Skill Claude CodeCodex

Domain knowledge agent for Japanese income tax filing (kakutei shinkoku). Guides income classification, deduction optimization, tax calculation, and filing for freelancers, sole proprietors, and side-business earners. Does not write code.

not rated 70 changed 8d ago A SkillSpector: warn 50 tokens original MIT

html-portal-generator

6149

athola/skrills

Skill Claude CodeCodex

Convert a codebase into a self-contained HTML portal app for ingestion into AI application systems. Produces a single deployable HTML file with embedded CSS, JS, and data.

not rated 69 12d ago A SkillSpector: pass 40 tokens original MIT

ai-bounty-claim

6150

aelf-hzz780/AI-bounty-skill

Skill Claude CodeCodex

Use when claiming the AI bounty on the tDVV mainnet sidechain. This public claim skill now supports Portkey AA/CA only, requires CA sync and holder preflight before any write, and routes to AA/CA onboarding, AA/CA claim, or diagnostics-only stop handling.

not rated 69 5mo ago A 65 tokens

aster-deposit-fund

6151

asterdex/aster-skills-hub

Skill Claude CodeCodex

Deposit funds to Aster from a wallet; private key from env. Use when the user wants to deposit to Aster or fund an Aster account.

not rated 69 5mo ago A 37 tokens

attio-skill-generator

6152

kesslerio/attio-mcp-server

Skill Claude CodeCodex

Generate use-case-specific Attio workflow skills from templates. Use when creating new skills for lead qualification, deal management, customer onboarding, or custom Attio workflows.

not rated 69 yesterday A 38 tokens

Self-Review

6153

dot-agents/dot-agents

Skill Claude CodeCodex

Review your own changes before committing or creating a pull request.

not rated 69 8mo ago A 15 tokens original MIT

avc

6154

study8677/Agent_View_Controller-AVC

Skill Claude CodeCodex

Use AVC (Agent View Controller) to present complex execution plans, architecture changes, and multi-step operations as interactive visual UIs. Instead of dumping walls of text, pipe structured JSON to avc for human visual review and confirmation. The human can drag-to-reorder, edit, skip, delete, and add steps before…

not rated 69 3mo ago B 71 tokens original Apache-2.0

yoanbernabeu/supabase-pentest-skills

Skill Claude CodeCodex

Create a test user (with explicit permission) to audit what authenticated users can access vs anonymous users. Detects IDOR, cross-user access, and privilege escalation.

not rated 69 7mo ago A Socket: passSnyk: fail 40 tokens

infographic-creator

6156

LingyiChen-AI/OpenSkills

Skill Claude CodeCodex

An infographic-generation skill turns written information into a visual layout using AntV Infographic, a tool for defining infographic structure and style in text.

not rated 69 +1 7mo ago A 25 tokens original Apache-2.0

evaluate-model

6157

xvirobotics/metaskill

Skill Claude Code

Load the latest model checkpoint, run evaluation on the test set, and generate a metrics report with confusion matrix. Use this after training to assess model performance or to re-evaluate a specific checkpoint.

not rated 69 +2 6mo ago A 42 tokens original MIT

buyer-eval

6158

salespeak-ai/buyer-eval-skill

Skill Claude Code

Structured B2B software vendor evaluation for buyers. Researches your company, asks domain-expert questions, engages vendor AI agents via the Salespeak Frontdoor API, scores vendors across 7 dimensions, and produces a comparative recommendation with evidence transparency. Use when asked to evaluate, compare, or…

not rated 69 4mo ago C 72 tokens original MIT

arco-design-vue

6159

arco-design/arco-design-skill

Skill Claude CodeCodex

A reference for building Vue 3 interfaces with Arco Design Vue, a library of ready-made user-interface components. It covers components such as buttons, tables, forms, dialogs, navigation, and date controls.

not rated 69 3mo ago A 181 tokens original MIT

plantuml-skill

6160

Agents365-ai/plantuml-skill

Skill Claude CodeCodex

Use when user requests diagrams, flowcharts, sequence diagrams, class diagrams, component diagrams, ER diagrams, architecture charts, or visualizations — including generating a diagram from existing source code, or rendering/extracting PlantUML embedded in a Markdown file to images (e.g. preparing docs for…

not rated 69 2mo ago B 114 tokens original MIT

livekit-simulations

6161

livekit/agent-skills

Skill Claude CodeCodex

Generate targeted test scenarios for a LiveKit voice or chat agent and run them as simulations — locally, from the agent's own code plus what the user wants stress-tested. Use whenever the user wants to "test my agent", "what should I test", "create/generate simulation scenarios", "make a sim test suite", "use lk…

not rated 69 +1 3mo ago A Socket: passSnyk: warn 183 tokens original MIT

genesis

6162

danielmeppiel/genesis

Skill Claude CodeCodex

Use this skill BEFORE drafting any agentic primitive module (skill, persona scoping file, scope-attached rule file, orchestrator workflow) or when refactoring an existing one. Activate whenever the task asks to design, restructure, or critique an agentic module across any agent harness (Claude Code, Copilot, Cursor…

not rated 69 +2 3mo ago A 169 tokens original Apache-2.0

auto-skill-installer

6163

lingbol088-spec/auto-skill-installer

Skill Codex

Detect missing capabilities during an AI agent task, search local skill folders plus configured GitHub skill registries, then install and validate the best matching skill before continuing. Use when an agent has loaded this skill and realizes another skill would make the current job safer, faster, or more accurate.…

not rated 69 +1 1mo ago A SkillSpector: pass 77 tokens original MIT

brainstorming

6164

roundpilot/superpowers-antigravity

Skill Claude CodeCodex

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

not rated 69 +4 22d ago A SkillSpector: warn 37 tokens original MIT

add-mcp-server

6165

oguzbilgic/kern-ai

Skill Claude CodeCodex

Add a Model Context Protocol (MCP) server to extend your toolbox with external tools.

not rated 69 +6 today A 22 tokens

deepseek-flow

6166

kanghelyu/dsh-deepseek-flow

Skill Claude CodeCodex

Build, import, inspect, and maintain DeepSeek Flow visual workflows with Markdown step workspaces and deterministic Boolean gates.

not rated 69 +1 27d ago A SkillSpector: warn 27 tokens original MIT

perf-review

6167

lemoncrow-lab/lemoncrow

Skill Claude Code

Verify a code change against measured performance gates — latency & tail-latency regression, profiler-confirmed hot paths, memory/leak soak, I/O & wire budgets, and scaling — by running it, not reading it. Use for 'perf review', 'did this slow down', 'check for a regression', or /perf-review. Enforces performance…

not rated 69 +4 2d ago A 87 tokens

avoid-ai-design

6168

funboy322/avoid-ai-design

Skill Claude CodeCodex

Audit and rewrite frontend UI to remove generic AI design patterns ("AI slop"). Use this skill when asked to "de-slop a UI", "make a design look less AI-generated", "audit a component or page for AI design tells", or "fix Claude/Codex-generated frontend that looks generic". Covers HTML/CSS and React/Tailwind/shadcn.…

not rated 69 +5 2mo ago A 90 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: