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.

bf-caprt-dev

7753

okwinds/miscellany

Skill Claude CodeCodex

A guide for delivering skills, agents, and workflows through capability-runtime, the runtime layer that executes these capabilities and reports their results.

not rated 50 6mo ago A 258 tokens original MIT

accessibility

7754

mwd1234/ios-agentic-skills

Skill Claude CodeCodex

Comprehensive SwiftUI accessibility audit against Apple HIG. Checks VoiceOver labels, Reduce Motion, Dynamic Type, color contrast, and accessible controls. Use before App Store submission or when adding new UI.

not rated 50 9mo ago A 43 tokens original MIT

adversarial-reviewer

7755

Marc-Moeller/aicms

Skill Claude CodeCodex

Run an adversarial review of the current git diff before committing, tuned to the AI First CMS monorepo.

not rated 50 2mo ago A 29 tokens AGPL-3.0

interview-the-system

7756

luanmorenommaciel/uc-transact-co

Skill Codex

Turn an ambiguous question about an unfamiliar or brownfield system into a bounded, read-only, evidence-backed investigation with a confirmed investigation contract, deliberate context manifest, claim ledger, ontology, owned open questions, and reviewable technical brief. Use when asked to investigate a repository…

not rated 50 2mo ago A 95 tokens

agentbay-ai/agentbay-skills

Skill Claude CodeCodex

A public-opinion monitoring workflow that collects posts or other information by keyword and platform, analyzes sentiment, and produces a report.

not rated 50 9mo ago A 125 tokens

ppt-from-anything

7758

Benioh/ppt-from-anything

Skill Claude CodeCodex

Create a polished presentation deck from arbitrary source material by planning a narrative, generating one 16:9 slide image per slide, and assembling the images into a .pptx file. Use when the user wants a PPT from an article, webpage, document, prompt, repo, notes, or mixed materials and an image-based deck is…

not rated 50 6mo ago A 73 tokens

quailyquaily/quail-ui

Skill Claude CodeCodex

Use this skill when integrating Quail UI into a Vue 3 frontend, migrating an existing screen to Quail UI components, or needing the library's themes, tokens, icons, demo-backed usage patterns, and agent-facing onboarding docs.

not rated 50 6mo ago A 56 tokens original Apache-2.0

auto-test-code

7760

huangwb8/skills

Skill Claude CodeCodex

A structured process for critically reviewing and testing software code. It records review findings, test plans, commands, results, and supporting files in a project workspace.

not rated 50 changed 2mo ago A SkillSpector: pass 56 tokens original MIT

agpair

7761

logicrw/agpair

Skill Claude Code

Use when Claude Code handles non-trivial coding, refactor, test-fix, research, review, or multi-file work where AGPair external CLI agents can produce implementation candidates, alternative analysis, or verification evidence.

not rated 50 4mo ago A 46 tokens original MIT

invoice-chaser

7762

Amazon-Quick/Amazon-Quick-official-catalog

Skill Claude CodeCodex

Pulls overdue invoices from QuickBooks, segments them into Friendly / Firm / Final Notice tiers by days overdue, drafts tone-appropriate follow-up emails and SMS, and sends only after owner approval. Supports scheduled automation and customer segmentation. Use for overdue invoice follow-up, AR aging review, or…

not rated 50 changed today A 101 tokens MIT-0

livefigures

7763

seandavi/agentic-coding-intro

Skill Claude CodeCodex

Author figures in Quarto documents using the quarto-livefigures extension — editable, version-controlled figure sources (Excalidraw, Vega-Lite, Graphviz, PlantUML, and 14 more) rendered at build time. Use when creating or editing diagrams, charts, schemas, or timing figures in a Quarto project, when the user asks for…

not rated 50 3mo ago A 97 tokens

skill-quality-checker

7764

shaozhengmao/skill-quality-checker

Skill Claude CodeCodex

A tool that checks installed coding-agent skills against five quality areas, including how well the instructions match their purpose, completeness, error handling, description accuracy, and token use.

not rated 50 5mo ago A 85 tokens original MIT

task-extraction

7765

giosakti/duragent

Skill Claude Code

Extract actionable tasks from a message or conversation.

not rated 50 8mo ago A 12 tokens original MIT

bolan

7766

BlackFast/bolan-skill

Skill Codex

A tool for turning books and other reading materials into a conversational persona that answers in the book's style of thinking. It can also combine several related books into a versioned, evolving perspective while keeping their disagreements visible.

not rated 50 5mo ago A 269 tokens original MIT

qmd-sessions

7767

wbelk/claude-qmd-sessions

Skill Claude Code

Convert Claude Code session transcripts to searchable markdown files for qmd indexing.

not rated 50 8mo ago D 18 tokens

apps-script-push

7768

Divide-By-0/autolatex

Skill Claude CodeCodex needs its repo

Use when pushing this repo's Common, Docs, Slides, Sheets, or Workspace projects to their remote Google Apps Script projects, especially when library linking, sidebar builds, or deployment/version confusion could cause a bad push.

not rated 50 1mo ago A SkillSpector: pass 48 tokens original MIT

api-graphql

7769

dragnoir/Shopify-agent-skills

Skill Claude CodeCodex needs its repo

Work with Shopify GraphQL APIs including Admin API and Storefront API. Use this skill for querying and mutating Shopify data, managing products, orders, customers, handling pagination, working with metafields, and understanding rate limits. Covers authentication, queries, mutations, and webhooks.

not rated 50 9mo ago A 60 tokens original MIT

coordination

7771

nicobailon/pi-coordination

Skill Claude CodeCodex

Multi-agent coordination for parallel plan execution with the coordinate and coordoutput tools.

not rated 50 +1 10mo ago A 18 tokens

screenclaw

7772

GinSing1226/ScreenClaw

Skill Claude CodeCodex

Desktop software automation through screenshots and coordinate grids. It can repeat recorded actions as reusable templates without needing the software to provide an API or command line.

not rated 50 4mo ago A 298 tokens original MIT

supertag-cli

7773

jcfischer/supertag-cli

Skill Claude CodeCodex

Skill "supertag-cli" from jcfischer/supertag-cli, covering supertag cli skill, mcp tools reference, progressive disclosure (start here), tanacapabilities and tanatoolschema.

not rated 50 changed 19d ago A 0 tokens original MIT

vault-for-llm

7774

zycaskevin/Vault-Agent-Memory

Skill Claude CodeCodex

Connect OpenClaw to Vault Agent Memory as a local-first governed project memory layer. Search first, then bounded-read cited source ranges; propose new memories as candidates instead of writing directly into active memory.

not rated 50 2mo ago A SkillSpector: pass 46 tokens original Apache-2.0

world-room

7775

ChenKuanSun/openclaw-world

Skill Claude CodeCodex

Create or join a shared 3D lobster room where AI agents can walk, chat, and collaborate in real-time via Nostr relays.

not rated 50 9mo ago A 32 tokens original MIT

aiwritex

7776

lza6/AIWriteX-Skills

Skill Claude CodeCodex

A Chinese-language content creation workflow for OpenClaw, an automation platform. It covers seven stages from finding current topics through writing, quality review, and publishing.

not rated 50 7mo ago A 104 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: