Skills

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.

reticle

2329

reticlehq/reticle

Skill Claude CodeCodex

Reticle embeds a dev-only SDK in the user's running app and exposes it to you as reticle MCP tools. You look, act, observe, and assert against the real app. No screenshots, and no browser download for the verify loop: it drives the tab the user already has open.

not rated 479 +35 changed yesterday A 0 tokens

anti-defensive-writing

2330

Kiterlin/anti-defensive-writing

Skill Claude CodeCodex

Reduce defensive writing in drafts and revisions by removing unnecessary caveats, disclaimers, hedges, apology-like framing, negative self-limiting statements, and over-explanations while preserving necessary scope, accuracy, safety, legal, ethical, and methodological limits. Use when drafting or revising academic…

not rated 479 +75 yesterday A 132 tokens original MIT

managedcode/dotnet-skills

Skill Claude CodeCodex

Use this skill before answering, planning, or editing any MSTest 3.x-to-4.x upgrade or post-upgrade failure. Triggers include "MSTest v4 breaking changes"; CS0507/CS0103/CS1061/CS1615; ExecuteAsync, CallerInfo, DisplayName, or custom TestMethodAttribute; ClassCleanupBehavior; ContainsKey; ThrowsExactly or…

not rated 479 +2 changed 8d ago A SkillSpector: warn 179 tokens original MIT

review-paper

2332

claesbackman/AI-research-feedback

Skill Claude Code

Run an 8-agent pre-submission referee report for an academic paper targeting a specified journal.

not rated 478 +1 16d ago A SkillSpector: warn 21 tokens original MIT

author-lookup

2333

poco-ai/Agentero

Skill Claude CodeCodex

A workflow for finding public contact details and online profiles for a research paper’s first and corresponding authors. It also looks for the paper’s OpenReview page; OpenReview is a website used to publicly discuss and review some research papers.

not rated 478 +46 today A SkillSpector: warn 100 tokens original MIT

aqe-ruflo

2334

proffesor-for-testing/agentic-qe

Skill Claude CodeCodex

Add optional Ruflo development-time orchestration to an Agentic QE workflow. Use when a task benefits from coordinated swarms, persistent cross-session memory, routing, or Ruflo hooks. Do not use for a one-shot edit, and never add Ruflo to shipped AQE runtime dependencies.

not rated 477 +2 today A SkillSpector: warn 64 tokens original MIT

career-coach

2335

davekilleen/Dex

Skill Claude CodeCodex

Personal career coach with 4 modes: weekly reports, monthly reflections, self-reviews, promotion assessments.

not rated 476 +1 changed 11d ago A 24 tokens

skill-creator

2336

tmustier/pi-extensions

Skill Claude CodeCodex

Create or update Agent Skills (SKILL.md plus optional scripts, references, or assets). Use when someone asks to design a new Agent Skill, refine an existing one, or structure skills for Pi discovery, packaging, or other Agent Skills-compatible clients.

not rated 476 +1 1mo ago A SkillSpector: warn 54 tokens original MIT

AI剪口播

2337

lcbuaaliu/ai-jian-koubo

Skill Claude CodeCodex

A Chinese-language tool for transcribing spoken-video content and identifying verbal mistakes. It produces a review draft and a list of deletion tasks.

not rated 476 +2 2mo ago A 41 tokens AGPL-3.0

pallas-release

2338

PallasBot/Pallas-Bot

Skill Claude CodeCodex

A release procedure for Pallas-Bot and its web interface, which is the part users interact with in a browser. It covers release notes, version changes, pull requests, tags, and automated release workflows.

not rated 475 +1 changed yesterday A SkillSpector: warn 110 tokens AGPL-3.0

weapp-vite/weapp-vite

Skill Codex

An engineering guide for building small-program projects with weapp-vite, a Vite-based toolchain for compiling mini-apps for several platforms.

not rated 475 changed 9d ago A SkillSpector: pass 134 tokens original MIT

redbook

2340

lucasygu/redbook

Skill Claude Code

A command-line tool for Xiaohongshu, also called Red or Little Red Book, a Chinese social-content platform. It supports searching and reading posts, analyzing creators, and automating certain engagement tasks.

not rated 475 +6 changed today A 23 tokens original MIT

colleague-distillation

2341

ZhixiangLuo/10xProductivity

Skill Claude Code

Distill a colleague into a reusable AI skill (work + persona) using tool connections — Slack, Slack AI, Jira, GHE, Bitbucket, Confluence, SharePoint, Teams, Outlook, Notion, Linear, Google Docs, and more — without manual paste. Use when the user wants a colleague skill, digital twin of a coworker, or capture of…

not rated 474 +1 2mo ago A SkillSpector: warn 104 tokens original MIT

glmv-stock-analyst

2342

zai-org/GLM-skills

Skill Claude CodeCodex

A stock-analysis workflow for Hong Kong, mainland Chinese, and United States shares. It combines company information, price charts, trading activity, news, and wider economic factors into a report.

not rated 474 5mo ago A 178 tokens original Apache-2.0

youtube-fetcher

2343

JimmySadek/youtube-fetcher-to-markdown

Skill Claude CodeCodex

Retrieve YouTube transcripts and subtitles, summarize or analyze what was said, or save an Obsidian-ready Markdown knowledge-base note with captions, creator metadata, chapters, language, and source provenance. Use for a YouTube URL or video ID when the request needs spoken content or an archival note. A bare YouTube…

not rated 473 +3 changed 7d ago A 74 tokens original MIT

audit-init

2344

RickyTong1/audit-harness

Skill Claude Code

An installation wizard for an audit framework called `audit-harness`. It checks a new project, creates the required files and folders, and configures the project for audit tracking.

not rated 472 3mo ago A SkillSpector: warn 45 tokens original MIT

sosumi

2345

NSHipster/sosumi.ai

Skill Claude CodeCodex

Fetches Apple documentation as Markdown via Sosumi. Use for Apple API reference, Human Interface Guidelines, WWDC transcripts, and external Swift-DocC pages.

not rated 472 2d ago A SkillSpector: pass 36 tokens original MIT

fusion-plan

2346

duolahypercho/fusion-fable

Skill Claude CodeCodex

Produce a high-confidence, CONCISE implementation / architecture / strategy PLAN that follows the OMC plan system end to end. It first runs OMC's real requirements interview (auto-chains the omc-plan skill: one question at a time, explore-first, Analyst consult) to produce an initial plan in .omc/plans/, then DEEPENS…

not rated 472 +1 1mo ago A SkillSpector: warn 266 tokens original MIT

skill-anything

2347

AgentSkillOS/SkillAnything

Skill Codex

Automatically generate production-ready Skills for any software, API, CLI tool, library, workflow, or service. Use this skill whenever the user wants to create a skill from scratch for a target application, convert an existing tool into an agent-native skill, generate skills for multiple platforms (Claude Code…

not rated 472 +1 5mo ago A 156 tokens original MIT

token-diet

2348

Kulaxyz/token-diet

Skill Claude CodeCodex

Cut token usage across the whole session without losing correctness or substance — concise user replies, lean tests/docs/plans/comments, tight code, disciplined context and tool use, and cheap sub-agent delegation. Load when the user wants less verbosity, lower cost, fewer tokens, or a "token diet" / "lean mode"; also…

not rated 471 +2 2mo ago A 81 tokens

agent-kanban

2349

saltbo/agent-kanban

Skill Claude CodeCodex

Work on an assigned Agent Kanban v2 Task through Realmroot Toolbox. Use when an Agent running in an Agency Session needs to inspect, claim, update, or submit assigned work.

not rated 470 +1 changed 7d ago A Socket: passSnyk: warn 41 tokens

zettaranc-perspective

2351

lululu811/zettaranc-skill

Skill Claude CodeCodex

A Chinese-language framework for analysing mainland Chinese stocks, trading methods, investment portfolios, and broader career or business decisions. It is an analysis framework, not a trading system.

not rated 469 +9 10d ago A 388 tokens original MIT

modsearch

2352

liustack/modsearch

Skill Claude Code

Plug-in web search, X (Twitter) search, and page fetch for models without native web access. Use whenever the task needs current information, external facts, source links, posts from X, or the content of a specific URL, and the active model/harness has no native search or fetch tool. Runs the modsearch CLI to return…

not rated 469 +62 changed 4d ago A SkillSpector: pass 99 tokens original MIT

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: