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.
Lzy599775/agent-auto-sci-skills
Skill Codex
An academic writing and editing assistant for research papers in English and Chinese. It covers translation, proofreading, rewriting, paper sections, reviewer checks, cover letters, and responses to reviewers.
Skill Claude CodeCodex needs its repo
Use when running the full AutoSurvey-backed outline, draft, related-works, or unattended survey pipeline.
Skill Claude CodeCodex
Load when turning intent into an executable goal for an agent, spawn, work item, experiment, or handoff. Use to define outcome, evidence, constraints, anti-goals, stop conditions, and reporting shape before work begins.
arush15june/cyber-sales-agent-skills
Skill Claude CodeCodex
Use when you are given a company name, domain, or short description and need to determine which cybersecurity regulations, compliance frameworks, and data-protection laws apply to it — and which of those obligations mandate security testing, VAPT, red-teaming, or continuous control validation.
Skill Claude CodeCodex
REPLACE-WITH-WHEN-TO-INVOKE-THIS-SKILL (max 200 chars; clear trigger conditions).
KaelZhang321/teambition-agent-toolkit
Skill Claude Code
A setup tool for initializing TeamBition workspace configuration, including credentials, parameters, and commonly used projects. The description is in Chinese.
Skill Claude CodeCodex
Use this skill when reviewing a small code change and you need a concise checklist for correctness, tests, and maintainability.
wanglixin-DLUT/paper-writing-skills
Skill Claude CodeCodex
Use when the user wants to analyze target research articles, reverse-engineer journal or field writing conventions, create a reusable writing blueprint or outline for a scientific paper, integrate contentanalysis.md from a deep learning project, prepare shared context for other research-writing skills, or diagnose the…
Skill Claude CodeCodex
Spawn a subagent to perform the quality review. Pass it.
minguncle/a-share-agent-skills
Skill Codex
Maintain the rolling A-share strategy library that stores imported macro hypotheses, scenario cards, daily market entries, holdings-first actions, and main-board tradable picks under strategylibrary/. Use when Codex needs to convert user macro materials, live market validation, or same-day A-share review into…
olakunlevpn/olakunlevpn-react-skills
Skill Claude CodeCodex
Use when writing, reviewing, or refactoring React or Next.js code — components, hooks, state management, testing, performance, TypeScript patterns, server components, or project structure. Always apply these standards to all React work.
Mic-360/material3-expressive-flutter
Skill Claude CodeCodex
Expert guidance for building Material 3 Expressive (M3E) Flutter apps. Use when implementing expressive motion, dynamic shapes, and premium components like FAB menus and toolbars.
Skill Claude CodeCodex
Interrogate the user about a plan or design, then iterate against user-supplied acceptance checks in a self-scoring loop until every check passes. Use when the user wants their plan stress-tested AND wants the model to keep refining until a concrete set of pass/fail criteria are satisfied. Triggers on "grill me with…
Kacper0199/Opencode-Ultrathinker
Skill Claude CodeCodex
End-to-end testing specialist using Playwright. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.
LouisLau-art/multi-agent-skills-catalog
Skill Claude CodeCodex
UOW Assignment Helper - Use when starting UOW course assignments to generate standardized answer templates with student ID and auto-extracted questions from PDFs.
ansea09/agent-skills-and-protocols
Skill Codex
Public core for converting trusted local documents and data files to Markdown using the installed Microsoft MarkItDown wrapper, with reusable workflow profiles for standard local documents, EPUB LLM-analysis bundles, and textbook-like PDF audit/OCR. Use when Codex is asked to convert, extract, ingest, normalize, or…
Peak-Studios/peak-agent-toolkit
Skill Codex
Install, configure, integrate, troubleshoot, or improve public Peak Studios FiveM resources using versioned documentation and source provenance. Use when working with peak-bridge, peak-chess, peak-clothingitems, peak-sprays, or peak-trucking; when selecting a compatible Peak script; or when adapting one to ESX…
grailautomation/claude-plugins
Skill Codex
Query local Codex session history with jq. Use when users explicitly ask to search Codex sessions, inspect prior Codex conversations, find previous user messages, locate tool calls, summarize past work by working directory, or query Codex rollout JSONL files.
Skill Claude CodeCodex
MTG Commander deck builder with multi-agent pipeline. Build synergy-dense, format-legal, budget-compliant 100-card Commander decklists. Synergy-first card selection via Scryfall API. Triggers on phrases like "build a commander deck", "MTG deck", "commander deck", "EDH deck", "build me a deck", "100-card deck"…
Skill Claude Code
Automate browser interactions, test web pages and work with Playwright tests.
Skill Claude CodeCodex
Converts HTML files to PDF or PNG format. Use this skill when the user asks to convert, export, or generate PDF/PNG from HTML files, or when they want to create printable documents, presentations, or long-form images from web pages or HTML reports.
Skill Claude CodeCodex
Bidirectional bridge between ClickUp and spec-kitty feature specs. Use when the user mentions ClickUp tasks, CU- IDs, spec-kitty features, creating tasks in ClickUp, importing ClickUp context into specs, or exporting spec-kitty specs to ClickUp. Provides /specup.setup, /specup.new, /specup.import, and /specup.export…
eralmansouri/arktype-claude-plugin
Skill Claude CodeCodex
Runtime TypeScript validation library with 1:1 type syntax. Use when creating validators, parsing data, or working with ArkType schema definitions using type().
Skill Claude Code
Automatically scan the current conversation, extract all "aha moments" and insights the user gained, and save them to a personal knowledge base. Use when the user says /aha, asks to capture learnings, or says /aha retag to consolidate and unify categories and tags across all saved insights.
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: