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.
LeoYeAI/openclaw-ultra-scraping
Skill Claude CodeCodex
Powerful web scraping, crawling, and data extraction with stealth anti-bot bypass. Bypasses anti-bot systems (Cloudflare Turnstile, CAPTCHAs) out of the box. Use when: (1) scraping websites that block normal requests, (2) extracting structured data from web pages, (3) crawling multiple pages with concurrency, (4)…
Skill Claude Code
A skill for extracting the main text from a web page and returning it as clean Markdown. It uses several fallback methods when the first method cannot access or parse the page.
Skill Claude Code
Turn Raw-layer traces (conversation, pitfalls, best practices) into Wiki-layer skills, or CRUD existing ones, then notify guide to update the routing table.
rothenbergt/backstage-agent-skills
Skill Claude CodeCodex
Build Backstage frontend plugins with the New Frontend System: createFrontendPlugin, blueprints, routes, Utility APIs, testing. Use for pages, nav, entity content, or cards.
Skill Claude CodeCodex
Route a DevRails 26 target through external bootstrap or the existing Memory Bank command workflow.
Just-Agent/make-agents-cheaper
Skill Codex
Use when the user wants to make Claude Code cheaper by improving prompt-cache hit rate, especially for MiMo or other OpenAI-compatible routed models. Trigger for Claude Code cache-hit analysis, cache-friendly command construction, paired baseline vs candidate evaluation, token usage logging, or use of…
Skill Claude CodeCodex
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Skill Claude CodeCodex
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer for context survival, Compaction Recovery, and battle-tested security patterns. Part of the Hal Stack 🦞.
stan-rym/liam-linkedin-ads-MCP
Skill Claude CodeCodex
Daily LinkedIn ads guardrail check via Liam that stays silent unless something is wrong. Catches active campaigns with zero delivery, daily spend spikes, cost-per-lead blowouts, spend with nothing back, stuck audiences, and CTR collapses. One line when all clear. Use for "health check", "anything on fire", "daily ads…
AI-Learning-Gems/AI-Learning-Gems.github.io
Skill Claude CodeCursor
Author a comprehensive, self-contained handoff document that lets a fresh agent (or subagent) fully reconstruct the current agent's context, reasoning, and decision history. Use when the user asks to "hand off", "create a handoff", "write handoff instructions", pass work to a new agent/subagent, summarize a session…
Skill Claude CodeCodex
Pydantic AI Python agent framework. Covers typed tools, model providers, evals, MCP, UI adapters, and observability. Use when building Python AI agents with Pydantic AI, configuring model providers, implementing typed tools/dependencies, running evals, or integrating MCP servers. Keywords: pydantic-ai, agents, evals…
Skill Claude CodeCodex
Analyze Ruby gem dependencies, vulnerabilities, outdated packages, maintenance health, and insecure gem sources with the gemtracker CLI. Use when asked to audit Ruby gems, check Gemfile.lock security, review dependency health, or run gemtracker.
VirtusLab-Open-Source/astro-strapi-starter
Skill Claude CodeCodex
Develop and extend the Astro + Strapi starter: content.config with @sensinum/astro-strapi-loader, Strapi 5 data in Astro pages, StrapiBlocks, BlockRenderer, Tailwind 4, shadcn. Covers onboarding (copy upstream skills), slug/CMS routes, Astro i18n, package upgrades, optional Vitest. Types in src/types/strapi/ with a…
Skill Claude CodeCodex
Create, validate, list, and load local Portable Handoff capsules for context transfer, continuing work in a new chat, compacting current work, or loading prior work. Use whenever the user asks for a handoff, context transfer, continuation briefing, or portable work-state summary.
Skill Claude CodeCodex
Use when starting ANY conversation. Mandatory: activate 10x. Governs project memory, ambiguity, records, tickets, subagents, evidence, review, closure, and retrospective learning.
Skill Claude Code
Author and modify editable .zen designs with the Zenith CLI. Use for posters, slides, diagrams, charts, brand kits, size variants, and CSV mail-merge. Export PNG, self-contained SVG with outlined text, or PDF with explicit raster fallback reports. Use other tools for photo generation, raster editing, and unrelated…
Skill Claude CodeCodex
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress or "compress memory…
Skill Claude CodeCodex
Drive a real Chromium browser through the tidesurf CLI or MCP tools. Use when a task needs live web browsing: reading pages as compact, token-efficient text with action IDs; clicking, typing, selecting, and scrolling elements by ID; taking screenshots of the full page, viewport, or one element; managing tabs; handling…
silverstein/claude-scientific-skills-desktop
Skill Claude CodeCodex
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and…
Skill Claude CodeCodex
Production durability patterns for AI agents on the JVM — crash recovery, audit trails, human-in-the-loop, and replay testing using JamJet runtime.
Skill Claude CodeCodex
A local tool for controlling HTML presentations from an iPhone or Android device while the slides run on a Mac or Windows computer. It keeps speaker notes private when the computer’s screen is mirrored to a projector.
Skill Claude CodeCodex
Reviews code for bugs, security issues, and best practices. Suggests improvements with concrete examples.
Skill Claude CodeCodex
Personal brand defaults and reusable animation recipes for editing talking-head videos with video-use — neon yellow + white brand, curated keyword callouts, circular picture-in-picture with a branded background, and an opening hook. Use this together with the video-use skill whenever editing a video for this creator…
cockroachlabs/cockroachdb-skills
Skill Claude CodeCodex
Audits the security posture of a CockroachDB cluster (Cloud or self-hosted) across network, authentication, authorization, encryption, audit logging, and backup dimensions. Use when assessing cluster security readiness, preparing for compliance reviews, or investigating security configuration gaps.
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: