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.
A Chinese writing skill that turns source material—such as a GitHub project, news event, academic paper, product experience, or tutorial—into a complete Markdown article.
A student-assignment helper for creating and processing documents, analysing data, and making slides. It uses Claude Code’s built-in document tools, though some features are limited in Codex and Cursor.
A development workflow for using Codex's multi-agent features with Owner, Admin, and Worker roles. It is described in Japanese as a flow for parallel implementation.
Write and test Supabase/Postgres Row-Level Security policies so users can only access their own rows. Use when a table holds user data, when enabling RLS, or when auditing access control on Supabase.
Use AgenticFlywheel for bootstrap, AIP creation, implementation audit, AIP reconciliation, checklist validation, and zero-context AGENTPROMPT generation. Trigger when the user asks to bootstrap AFW, create or update an AIP, run the implementation audit, validate CHECKLIST.yaml, reconcile packet docs, or generate…
Bootstrap a repository-level "super harness" for long-running agent and human collaboration, so durable team knowledge, experiment progress, and verification evidence live in the repo rather than individual chat history. Use when initializing or normalizing the harness structure in a new or messy repository…
A natural-language screener for shares listed in mainland China’s A-share market. It turns written investment filters into verified Pandadata API queries and returns matching stocks with supporting evidence.
Use when the user mentions AGENTS.md, CLAUDE.md, copilot-instructions, Cursor rules, project brief, context for coding agents, agency kickoff, onboarding a new project, or asks "how do I set up Project Spine". This is the orientation skill — reach for it FIRST when the user's intent involves Project Spine, then chain…
A skill for managing predefined agent profiles, which are saved sets of behavior, preferences, operating rules, and metadata for coding agents and development tools.
Turn a high-level concept and a high-level architecture into a conceptual set of interfaces, domain models, implementations, and their relationships. Use when the user describes what a project should do plus a rough architecture and asks for the interfaces/classes/traits to implement, a target/goal architecture, an…
Canonical LangGraph patterns for typed State, conditional routers, interrupt/resume, checkpointers, structured outputs, tool/MCP wiring, subgraphs, parallel branches, async streaming, and LangSmith tracing. Use when designing or implementing any LangGraph node, router, or graph. Reference; not a runbook.
A local development check for the Mentora application, which runs across API, web, and desktop parts. It starts the project on a Windows computer and verifies that the parts work together.
Use Token Ops to reduce wasted context during AI coding sessions. Trigger when the user asks about saving tokens, reducing Cursor costs, compact context, avoiding broad file reads, or checking token savings.
Take a rough idea from the user (a few lines of text), summarize it, then act as a domain-expert product manager to interactively refine it into a full requirement document and MVP plan. Use when someone says "I have an idea", "help me build X", "turn this into a product", "what would the MVP look like", or provides a…
A same-day summary of coding-agent work, organized by project or repository rather than by time. It combines session records with plans, completed work, commits, and uncommitted changes.
Give AI-generated Flutter UI good taste. Encodes high-end mobile design DNA (bento grids, glassmorphism, mesh gradients, parametric "dials" for variance/motion/density, and a strict anti-slop ban list) into a portable Agent Skill. Use when building or restyling Flutter/Dart screens, when the user wants premium…
Onboarding layer that maps the user's opening intent to relevant agent skills before work begins. Use when the user describes a new project, multi-step workflow, file-heavy setup, or asks which skills apply; also when re-evaluating mid-session after a major pivot. Reads references/skill-index.md and applies…
A ten-stage workflow for mathematical modelling, which uses mathematics and algorithms to represent and solve a real-world problem. It includes checklists for choosing methods, implementation, validation, sensitivity analysis, visualisation, and writing up results.
Use when turning a vague Web/App product idea, feature, bugfix, refactor, or LLM pipeline change into specs, plans, execution-window handoffs, tests, and reviewable AI-assisted implementation.
Use when summarizing text, video transcripts, audio transcripts, podcasts, lectures, interviews, demos, or meetings where the output must preserve the source's main thread, attention weight, decision model, concrete examples, and evidence instead of becoming a polished but source-drifting essay.
Decide whether unreleased develop work warrants a release, pick the version per semver.org, and cut it following this repo's established commit/PR/tag/release pattern.
Use this skill whenever a developer wants to set up, design, audit, or debug an automated agent loop for their project. Triggers include: "help me set up a loop", "I want agents to run while I sleep", "automate my CI triage", "set up a goal loop", "review my loop setup", "design an agentic workflow", "loop…
SEONIB AI ecommerce marketing agent. Helps merchants generate SEO blogs, product marketing content, create blog cover images, manage drafts, read brand settings, and publish content to Shopify, WordPress, Shopline, Shoplazza, Wix. Use for: ecommerce SEO, AI blog writing, content marketing automation, Shopify content…
★not rated 2 2mo agoA191 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: