skill-name
1417Skill Claude CodeCodex
Describe when this skill should be used.
not rated 5 7mo ago A 10 tokens
original MIT
pw-admin-ui
1418Skill Claude CodeCodex
Use when designing, structuring, or rendering HTML for ProcessWire Admin interfaces, custom Process modules, or Inputfields.
not rated 5 15d ago A 28 tokens
report-compose
1419Skill Claude Code
A Paper Scout research-report workflow creates and archives reports in Lark, a collaboration and document platform. It covers document structure, diagrams, local media, delivery through Lark, and user notification.
not rated 5 17d ago A 57 tokens
a11y-annotate
1420Skill Claude CodeCodex
Use this skill on every UI turn that touches composition — building, modifying, restructuring, or annotating any page, component, route, form, layout, navigation, modal, focus behaviour, or live region. Make sure to use this before any UI code change, and whenever the user asks what an a11y.md captures. Triggers on…
not rated 5 3mo ago A 133 tokens
original MIT
react-best-practices
1421Skill Claude CodeCodex
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…
not rated 5 26d ago A 65 tokens
original Apache-2.0
memory-curator
1422Skill Claude CodeCodex
Curate the project's long-lived review memory in .mimir/memory. Decide whether a decision is durable enough to remember, write it as one atomic well-scoped entry, update instead of duplicating, and refuse to record untrusted claims. Used on an explicit maintainer command and when the reviewer proactively spots a…
not rated 5 1mo ago A 71 tokens
original MIT
Agent Development
1423Skill Claude CodeCodex
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…
not rated 5 4mo ago A 80 tokens
copy · 91% MIT
architect
1424Skill Claude CodeCodex
Design the architecture and task breakdown for a REQ. Phase 2 of /proceed. Dispatches codebase-explorer to inform the design, then drafts architecture.md and tasks/TASK-.md. On high-stakes REQs, dispatches the architecture-adversary to attack the design before the gate so the user reviews a stress-tested plan. Ends in…
not rated 5 1mo ago A 87 tokens
generate-adr
1425Skill Claude Code
Generates an Architecture Decision Record (ADR) from meeting notes, refinement transcripts, or a brief decision summary. Use when the user asks to document an architecture decision, create an ADR, or record a technical decision made in a meeting.
not rated 5 2mo ago A 51 tokens
original MIT
newsroom-style
1426jamditis/prompt-engineering-journalists
Skill Claude CodeCodex
Enforces AP Style and newsroom conventions when writing or editing.
not rated 5 2mo ago A 0 tokens
chohra-med/claude_design_skill
Skill Claude CodeCodex
Take a UI from a one-line idea to on-brand, shippable design with Claude, in the correct order — brand foundation first, then components, screens, interactions, accessibility, and only then generation via /design. Use whenever someone wants to design, redesign, or generate a screen, page, component, or onboarding flow…
not rated 5 2mo ago A 135 tokens
original MIT
loop-limit
1428Skill Claude CodeCodex
Stop a workflow loop after a maximum number of iterations.
not rated 5 3mo ago A 14 tokens
original MIT
github-repo-audit
1429Skill Claude CodeCodex
A review process for checking whether a GitHub repository and its release materials are complete and consistent.
not rated 5 19d ago A 118 tokens
web-ai-slop
1430Skill Claude CodeCodex
Filters web output against a multi-discipline checklist of AI default patterns. Use before shipping any design, copy, UI code, infrastructure config, or documentation. Trigger when the user asks for something 'premium' or 'not AI-looking', when you're about to reach for a glowing gradient, bento grid, SaaS empowerment…
not rated 5 1mo ago A 91 tokens
original MIT
Skill Claude CodeCodex
Use the local LLM endpoint proxy (localhost:18090) — or your own gated public deployment — to route Claude Code / Claude SDK through custom providers (OpenRouter, Moonshot, Groq, ZAI) via an Anthropic-compatible gateway. Covers adapter-specific behaviors, auth patterns, proxy codenames, and common failure modes.
not rated 5
changed 9d ago A SkillSpector: pass 77 tokens
original Apache-2.0
Skill Claude CodeCodex
Use when the user asks to search Perplexity, query Perplexity through the web UI, perform web research with Perplexity, save a Perplexity answer as Markdown, or retrieve a Perplexity answer through browser automation.
not rated 5 2mo ago A 55 tokens
original MIT
one-shot-ui
1433Skill Claude CodeCodex
Extract UI designs from screenshots and iteratively refine implementations to match a reference image pixel-perfectly using comparison and fix suggestions.
not rated 5
+1 1mo ago A 28 tokens
original MIT
arabic-writing
1434ahmeddabak/claude-arabic-writing
Skill Claude CodeCodex
Write and translate natural, grammatically correct Arabic — Modern Standard Arabic plus Egyptian, Levantine, Gulf, and Maghrebi dialects — that avoids machine-translation tells. Use whenever producing Arabic prose: writing original Arabic, translating into Arabic (especially from English), or editing/proofreading…
not rated 5
+1 2mo ago A 117 tokens
original MIT
Skill Claude CodeCodex
Use when users want a premium, demo-worthy cinematic web experience, immersive landing page, portfolio, product showcase, or Claude-made wow-factor UI with motion, 3D, particles, WebGL, or scroll-driven storytelling.
not rated 5 4mo ago A 51 tokens
original MIT
web3-bug-classes
1436Olaradiallysymmetrical491/web3-bug-bounty-hunting-ai-skills
Skill Claude CodeCodex
Complete reference for all 10 DeFi smart contract bug classes. Use this when hunting for specific vulnerability types, need attack patterns for accounting desync, access control, incomplete path, off-by-one, oracle manipulation, ERC4626 vaults, reentrancy, flash loans, signature replay, or proxy/upgrade bugs.
not rated 5
+1 today A 72 tokens
copy · 100% MIT
markdown-search
1437Skill Claude CodeCodex
Search and navigate local markdown via MCP. Use when the user asks to search docs, find a README section, list headings/TOC, extract code examples by language, read frontmatter, or grep internal wikis and ADRs on disk.
not rated 5 1mo ago A 52 tokens
original MIT
nvdigitalsolutions/mcp-ai-wpoos
Skill Claude CodeCodex
Register a custom Query type for JetEngine's Query Builder — extend \JetEngine\QueryBuilder\Queries\BaseQuery for the runtime query class, extend \JetEngine\QueryBuilder\QueryEditor\BaseQuery for the editor component, then hook BOTH register actions — jet-engine/query-builder/queries/register (factory) for the…
not rated 5 today A 186 tokens
skill-creator
1439Skill 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 5 5mo ago A 64 tokens
baoyu-xhs-images
1440nevergoodstudy-hub/wechat-article-summarizer
Skill Claude CodeCodex
An infographic generator that turns information into a series of visual cards for Xiaohongshu, a Chinese social platform also known as Little Red Book or RedNote.
not rated 5 2mo ago A 84 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: