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.
Acquire and verify data for CNS papers that passed paper-filter. Clones repositories, downloads and organizes datasets per evaluation setting, performs Level 4 deep verification (acquisition integrity, initial state, separability, consistency, per-setting completeness), creates an organized data environment. Updates…
Audit and improve recording and alerting rules. Use when reviewing alert coverage or rule health, drafting new alerts or recording rules, investigating flapping or noisy alerts, or speeding up slow dashboards with pre-computed expressions; produces complete rule-group YAML.
A natural-language assistant for querying and operating Kingdee Cloud Galaxy, an enterprise resource planning system for business records such as orders, inventory, materials, customers, and production.
A study-planning assistant for the People’s Education Press junior-high geography textbooks. It turns a specified grade, book, unit, and learning situation into tasks based on maps, data, regional comparison, and explanations.
Designing and building any user-facing surface: a web page, landing page, dashboard, report, HTML document, email, or a component inside an existing app. Use when asked to build, style, redesign, or beautify UI, when writing HTML/CSS or a React/Vue/Svelte component that a person will look at, and when a generated page…
Report what the AWS DevOps Agent itself costs to run, and where that cost comes from, per Agent Space and per role on demand in chat or on a schedule through a custom agent. Use this skill when a user asks to measure, break down, attribute, explain, or forecast DevOps Agent spend, or the cost of the downstream AWS API…
Use the locally installed CAD-Agent-Hub SolidWorks MCP to inspect, create, and edit native SolidWorks parts on this Windows computer, including feature graphs and parametric gears.
Produce a professional, code-grounded refactor or implementation design report from identified technical problems, product gaps, review findings, architecture concerns, or frontend-backend contract issues. Use when Codex is asked to turn bugs, missing protections, design gaps, API/UI mismatches, or desired behavior…
Teaches AI agents to recognize and avoid security threats during normal activity. Covers phishing detection, credential protection, domain verification, and social engineering defense. Use when building agents that access email, credential vaults, web browsers, or sensitive data.
Guide for setting up automated npm package releases via GitHub Actions using Trusted Publishing (OIDC). Use when creating release workflows, publishing to npm, or troubleshooting CI/CD publish failures.
Create Framer Code Components and Code Overrides. Use before writing or editing any .tsx for Framer, including deciding whether a feature needs code at all. Covers building custom React components for Framer, writing Code Overrides (HOCs) to modify canvas elements, implementing property controls, working with Framer…
Use when the user asks to build a new feature and wants a structured Codex CLI workflow with discovery, clarifying questions, architecture comparison, implementation, and review.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
Run a structured behavioral diagnosis using COM-B, the Behavior Change Wheel, and BCT Taxonomy v1. Activate when the user describes a stuck or problematic behavior, wants to understand why people aren't doing something, or asks for a COM-B analysis.
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.
Use when recursive-mode needs to route delegated audit, review, or bounded implementation work through external transports, CLIs, and models while preserving controller verification and fallback behavior.
Use c9watch CLI to monitor, query, and coordinate Claude Code sessions. Trigger when the user asks about other running Claude Code sessions, wants to check what agents are doing, needs to find past session work, asks about Claude Code costs or spending, wants to stop or coordinate sibling sessions, or mentions…
A coding assistant for the traditional Kuikly DSL, a language used to build user interfaces. It covers Kuikly components, system modules, layouts, events, state, animations, routing, networking, lists, and custom extensions.
Ingest one or more agent trajectories (raw bob/claude traces or normalized JSON) into an agent-wiki end-to-end — convert, summarize, extract guidelines, synthesize skills, optionally compare outcomes, consolidate into clusters, and catalog. Use when you have a batch of traces to turn into a wiki in one pass.
An adult-focused information skill about feminine presentation, voice, skincare, makeup, body exploration, and related sexual-health topics, using community knowledge with medical safety limits.
★not rated 136▲
+1
changed 1mo agoA109 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: