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.

rhwp-gui-agent

18098

leeryong/rhwp-Agent-Skills_by_BLUESKY

Skill Codex

Control, test, and extend the rhwp web HWP/HWPX editor through its browser GUI and agent automation bridge. Use when an AI agent needs to run rhwp-studio, open or create HWP/HWPX files, exercise menus/toolbars/dialogs, verify document editing features, automate GUI operations with Puppeteer/CDP, use the hwpctl…

not rated 4 2mo ago A 95 tokens

ame

18099

CSKishan/ame-skill

Skill Claude CodeCodex

Use when the user invokes /ame, says "ask me exhaustively", "interview me about this", "help me think through what I want to build", "ask me questions about my idea", or wants to clarify requirements before planning or coding. Runs a structured adaptive interview across all software quality dimensions in a single…

not rated 4 5mo ago A 113 tokens original MIT

x-post-text

18100

sandover/agent-skills

Skill Codex

Extract the text of one or more X/Twitter posts or tweets, especially when the user wants only the post content and the page must be read through an authenticated Chrome session.

not rated 4 5d ago A 39 tokens

fortrabbit-api-access

18101

fortrabbit/agent-skills

Skill Claude Code

Use when connecting an agent, MCP client, or script to fortrabbit — installing the fortrabbit MCP server (mcp.fortrabbit.com/mcp), calling the /v1 REST API, or resolving 401 / "Authentication required" / "Invalid access token" errors. Prefers the browser-based OAuth install (no credential handling) and falls back to a…

not rated 4 changed 26d ago C 223 tokens original MIT

ncm-listening-profile

18102

dragonknightk/ncm-listening-profile

Skill Codex

A skill for collecting listening-history data from the NetEase Cloud Music desktop app on Windows or macOS. It uses the app's logged-in session to export playlists and listening rankings as local JSONL, CSV, and aggregate files, plus an analysis prompt.

not rated 4 3mo ago A 131 tokens MIT-0

repo-tour

18103

ntaffzii/Skill-Agents

Skill Claude CodeCodex

Use after graphify has already built graphify-out/graph.json for a project, to generate a dependency-ordered guided tour, an onboarding doc for new team members, or a diff-impact analysis before a commit/PR — reading the existing graph instead of re-scanning the repo. Trigger on "onboarding guide"…

not rated 4 21d ago A 146 tokens original MIT

article

18104

TrendTweekers/article-autopilot

Skill Claude Code

Generate a publication-ready article for any site, in any language. Composes the anthropic-skills pipeline (content-brief → write-content → eeat-audit) and applies your site-config.yaml — brand voice, audience, terminology, language profile — as drafting constraints. Use when the operator says "write an article about…

not rated 4 4mo ago A 95 tokens original MIT

intelligence-update

18105

ainova-systems/intelligence-sync

Skill Claude Code

Update intelligence-sync, then offer the one-way switch to the intelligence CLI - performed only on the user's explicit approval.

not rated 4 1mo ago A 26 tokens original MIT

maccabi-pharm-search

18106

alexpolonsky/agent-skill-maccabi-pharm-search

Skill Claude CodeCodex

Search for medications and check real-time stock availability at Maccabi pharmacies in Israel. Use when searching for drugs like "nurofen", "acamol/אקמול", "advil", or finding nearby pharmacy branches with stock. Supports Hebrew and English drug names. מכבי פארם, תרופות, מלאי, בית מרקחת.

not rated 4 7mo ago A 78 tokens original MIT

data-cleaning-planner

18107

lianxhcn/PXa2026a

Skill Claude CodeCodex

Use this skill when planning or reviewing data cleaning for empirical research. Given a variable list and data dictionary, it drafts a cleaning plan; checks whether a merge/join is sound (1:1 vs m:1, key name/case/type/leading-zero consistency, expected match rate); explains the differences among missing-value…

not rated 4 2mo ago A 146 tokens

reviewcourt

18108

Chris1Wang3/Idea-on-Trial

Skill Claude CodeCodex

A review tool for completed Tencent Meeting requirements or technical-plan meetings. It turns the meeting notes and transcript into a verdict, such as approved, conditionally approved, rejected, or lacking enough information.

not rated 4 14d ago A 150 tokens original MIT

workbench-sim

18109

svd-ai-lab/sim-plugin-workbench

Skill Claude CodeCodex

Use when the user asks Codex, Claude Code, ChatGPT-style coding agents, or another AI agent to connect to Ansys Workbench through sim-cli. Supports Workbench journal execution, project inspection, persistent sessions, Mechanical handoff, bounded execution, artifact reporting, and troubleshooting. Requires a user-owned…

not rated 4 4mo ago A 70 tokens original Apache-2.0

justin-sun-narrative

18110

william19307/justin-sun-narrative

Skill Claude CodeCodex

A Chinese-language writing guide for long articles, X posts, and first-person narratives, based on a specified restrained narrative style associated with Justin Sun.

not rated 4 1mo ago A 75 tokens

xueqiu-prediction-audit

18111

icekale/xueqiu-prediction-audit

Skill Claude CodeCodex

Use when auditing a Xueqiu or similar public influencer's stock predictions, scoring directional calls, copy-trade P&L, quantifying public cubes against benchmarks, producing a public-text AI profile, producing a client prediction-audit PDF/PNG, or deeply fetching Xueqiu posts plus the influencer's own comments with a…

not rated 4 1mo ago A 150 tokens original MIT

openplan-auto

18112

BANANASJIM/openplan-skill

Skill Codex

Orchestrate OpenPlan-style skills in auto or YOLO mode while preserving human decision boundaries. Use when Codex, Claude Code, or another agent should automatically inspect, align enough to proceed, research, test, review, garden, summarize, hand off, or generate temporary HTML without silently approving, changing…

not rated 4 18d ago A 139 tokens original MIT

loop-architect

18113

Frontier-Intelligence-Lab/loop-architect

Skill Codex

Design a safe, verifier-first loop for an AI coding agent — or refuse when a task should not be looped. Use when someone asks "can I automate this with an agent?" or wants to create, audit, or improve a loop for coding agents, scheduled agent work, autonomous repo maintenance, CI/QA loops, refactoring loops…

not rated 4 2mo ago A 167 tokens original MIT

mb-cli

18114

jthingelstad/mb

Skill Claude CodeCodex

Use this skill whenever you are using the mb CLI to read, post, manage follows, or build pipelines against micro.blog. It covers command selection, output modes, public boundaries, and cheap-versus-expensive mb workflows.

not rated 4 1mo ago A 48 tokens original MIT

adversarial-research

18115

TheEnigmaticT/adversarialresearch

Skill Claude CodeCodex

Research a topic adversarially: attack provisional theses and present only the most defensible conclusion under an explicit evidence boundary.

not rated 4 1mo ago A 30 tokens CC-BY-4.0

crucible

18116

ryanelian/crucible-agent-skill

Skill Claude Code

Autonomous, loop-until-clean diff refinement engine. Iteratively burns down feature and refactor diffs by deleting dead code, flattening empty abstractions, and enforcing strict layer boundaries (Sink & Lift). Every change is verified against tests. Use when asked to "crucible", "refine until clean", "burn down diff"…

not rated 4 2mo ago A 86 tokens original MIT

nimbuu-ui-ux

18117

Haamiahphp/nimbuu-ui-ux

Skill Claude CodeCodex

Nimbuu UI/UX Skill. Logic-driven interface design distilled from Refactoring UI, Practical UI, and Fundamentals of Creating a Great UI/UX. Three uses. (1) ALWAYS when starting a new project, greenfield app, landing page, or prototype with no design system, no tokens, no brand kit, so spacing, type, colour, hierarchy…

not rated 4 1mo ago A 245 tokens original MIT

skill-issues

18118

mateuszperlak/skill-issue

Skill Claude CodeCodex

This skill makes the agent completely useless. It doesn't help. It gives confidently wrong short answers and blames the user.

not rated 4 7mo ago C 28 tokens

llm-council

18119

Sdinzsh/PowerHou53

Skill Claude CodeCodex

Run a decision through 5 independent AI advisors (Contrarian, First Principles, Expansionist, Outsider, Executor) that peer-review anonymously and synthesize a verdict. Trigger on 'council this', 'pressure-test this', 'war room this', or any high-stakes either/or choice. Skip for factual lookups, summaries, or simple…

not rated 4 14d ago A 85 tokens

midjourney-prompting

18120

leggiemint/legnext-skills

Skill Claude CodeCodex

Expert Midjourney prompt engineering skill. Use this skill when users need help crafting effective Midjourney prompts, converting natural language descriptions into optimized prompts, or want guidance on Midjourney parameters and techniques. Specializes in V7 best practices, the 7-Element Framework, and photography…

not rated 4 9mo ago A 67 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: