41,017 tagged agent-skills, measured the same way as everything else here.
Browse within: agentic-ai 454coding-agents 214agents 192academic-research 182academic-writing 182journal 182azure 169foundry 169sdk 169agent-plugins 158ai-coding-agent 155ai-skills 152anthropic-claude 136claude-ai 136
Skill Claude CodeCodex
A read-only code review guide that checks a defined set of changes against the intended requirement, project rules, and evidence from the code and tests.
Skill Codex
Manage Linear tickets/comments via direct HTTP GraphQL with python3 scripts/linearmanager.py and token env vars only (no Linear MCP). Supports create/read/update/delete tickets and sub-tickets, issue templates, discovery commands (whoami, teams, projects), creating/moving tickets under a project, workflow status…
xxzxzmai-droid/dify-builder-skills
Skill Codex
A generator for Dify Chatflow agents. Dify is a platform for building AI chatbots and workflows, and a Chatflow is one of its configurable agent flows.
Skill Codex
Evidence-led Chinese investment research for listed stocks and China OTC public funds, using separate stock and fund workflows and nine-part report templates. Covers stock business models, industry cycles, competitive advantage, management and capital allocation, financial quality, earnings forecasts, valuation…
Skill Claude Code
Constrained optimization skill for maximizing or minimizing objectives under budgets, capacities, safety limits, equality/inequality constraints, and multi-objective trade-offs. Provides model normalization, ALM/ADMM/KKT routing, infeasibility diagnosis, shadow-price interpretation, capability-aware no-tool fallback…
Skill Claude CodeCodex
Create, modify, evaluate, and package portable Agent Skills for coding agents. Use this skill when users want to create a skill from scratch, turn a workflow into a reusable skill, improve an existing skill, set up evals, compare skill behavior against a baseline, or optimize skill trigger descriptions across agent…
Skill Codex
A writing rule that adds spaces where Chinese, Japanese, or Korean characters meet Latin letters, numbers, or symbols.
Skill Claude CodeCodex
Review user-facing software changes for accessibility barriers across semantics, keyboard and other input, focus, structure, content, feedback, and assistive technology behavior. Use for web, mobile, desktop, CLI, and interactive UI changes; adapt the checks to the platform.
Skill Codex
Use for implementing, fixing, refactoring, or reviewing code with the smallest correct change; routes only unresolved debugging, architecture/choice, or risk-boundary blockers, while code retrieval uses the cheapest sufficient available capability.
Skill Claude CodeCodex
Turn an article or book chapter into an order-preserving interactive outline tree with bidirectional links between tree nodes and full-text paragraphs. Use when the user wants a detailed reading structure, not a standalone summary.
Skill Claude Code
Build, lint, and evaluate agent skills that demonstrably change behaviour, instead of writing adjectives that change nothing. Use whenever the user asks to create a skill, write a SKILL.md, improve or fix an existing skill, make a skill "actually work", or evaluate whether a skill does anything. Also use when the user…
Skill Claude CodeCodex
Manage iCloud Hide My Email addresses — list, create, edit, deactivate, export.
nanxiaoyao/network-huawei-skills
Skill Claude CodeCodex
This skill should be used when the user asks to configure or troubleshoot AAA (Authentication / Authorization / Accounting) on Huawei S / CE / USG series devices — including 802.1X, MAC authentication, Portal authentication, RADIUS, HWTACACS (TACACS+), local authentication, authentication profiles, free-rule, NAC…
Skill Claude CodeCodex
Kinde Billing: models organization or user plan groups, features, and prices; connects test Stripe and publishes pricing; integrates plan selection, portal, and entitlements; records metered usage or handles billing webhooks and workflows; and troubleshoots subscriptions, trials, or tax. Use for Kinde billing work or…
swaaap-nil/system-design-skill
Skill Claude Code
Turns the current codebase into a Staff-level system design interview problem. Scans directory structure, routes, data models and infrastructure, then produces a grounded interview brief — The Question, Core Requirements, Below the Line, Non-Functional Requirements, High-Level Architecture (target vs as-built), Data…
coreline-ai/antigravity_gemini_skills
Skill Claude CodeCodex
A senior software-analysis process that reads a project's documentation and creates one master plan. It identifies whether the project is a website, an app, or both, then records the technology and architecture decisions it can justify from the documents.
Skill Claude CodeCodex
Analyze annotated UI screenshots and markdown documentation to generate agent-consumable UI flow specifications. Use when processing web app UI flows described via markdown + screenshots into structured, automation-ready knowledge.
2612evgenii-hue/business-idea-evaluator
Skill Claude Code
Objectively evaluates business ideas through 18 independent subagents, evidence grading, probabilistic modeling, and Business Reality Score (BRS). Use when the user asks to evaluate, validate, score, or stress-test a business idea, startup concept, side project, SaaS idea, or monetization plan. Always use for business…
Skill Claude Code
TEMPORARY skill loader — fetches remote SKILL.md files without permanent installation. Temp mode auto-cleans on restart. Frozen mode persists across sessions. NEVER uses npx skills add or installs permanently. Use when user wants to load a skill temporarily from a GitHub repo URL, raw URL, or any HTTP link to a…
gy910210/hermes-research-skills
Skill Claude CodeCodex
A Chinese research workflow coordinator that chooses and connects the right steps for starting, extending, comparing, and maintaining a research project.
mahlongit/capability-dispatch-center
Skill Claude CodeCodex
Local capability discovery and dispatch center. Use when the user wants to discover installed skills, plugins, MCP servers, or agents on their machine, open a local routing page, or generate a registry before choosing capabilities.
Skill Claude CodeCodex
Use when the user asks to lint, audit, test, benchmark, validate, or fix an agent skill — from a single SKILL.md frontmatter check to trigger-accuracy measurement or a corpus-wide audit of installed skills for duplication — driving the shakespii CLI (init, lint --json, test --run, bench) to resolve findings until…
Skill Claude CodeCodex
Use only when the user explicitly asks for igapyon-note-writer, asks for Note publishing metadata or Note canonical article management, or asks to prepare a Mikuku-authored Japanese technical essay for Note. Do not use for generic proofreading, ordinary technical articles, or character writing unless Note publishing…
Skill Claude CodeCodex
Work under an explicit time budget with deterministic deadline tracking, useful stretch work, scope control, isolated timers for parallel sessions/agents/apps, and handoff. Use when the user asks for a timebox, fixed duration, deadline, work for N minutes/hours, use the full time, keep improving until the deadline…
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: