Skills for Codex

214,760 that install into Codex. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.

ai-council

11065

event4u-app/agent-config

Skill Claude CodeCodex needs its repo

Use when polling external AIs (OpenAI, Anthropic) outside the host session for a neutral second opinion on a roadmap, diff, prompt, or file set — or 'cross-check with another model'.

not rated 10 changed 12d ago A SkillSpector: warn 47 tokens original MIT

fulcra-csv

11066

ashfulcra/fulcra-tools

Skill Claude CodeCodex

Import any CSV stream into a Fulcra account as annotations — body weight, mood scores, expenses, sleep, media plays, anything timestamped. Use when the user wants to ingest a CSV they got from somewhere (a wearable, a Pipedream/IFTTT workflow, a hand-rolled spreadsheet) into Fulcra.

not rated 10 15d ago A SkillSpector: warn 71 tokens original MIT

eduorchestrate

11067

haroontrailblazer/EduOrchestrate

Skill Claude CodeCodex

Universal EduOrchestrate adapter for openclaw. Use /eduorchestrate for learner onboarding, adaptive plans with a 30-day minimum, trend research, daily email plans, progress logging, prebuilt skill progression cards, weekly summaries, and next-skill recommendations.

not rated 10 2mo ago A 60 tokens original MIT

autoresearch

11068

Maleick/AutoResearch

Skill Claude CodeCodex

Run a subagent-first structured improve-verify loop in OpenCode. Activate with /autoresearch or specialized modes like /autoresearch:plan, /autoresearch:debug, /autoresearch:fix, /autoresearch:learn, /autoresearch:predict, /autoresearch:scenario, /autoresearch:security, /autoresearch:ship. Supports recursive…

not rated 10 1mo ago A 81 tokens original MIT

ampl-tuner

11069

marcos-dv/ampl-agents

Skill Claude CodeCodex needs its repo

Expert in AMPL/MP solver options across all supported solvers. Recommends and configures lim:time, mip:gap, threads, IIS, barrier, and solver-specific knobs. Fetches official option pages from dev.ampl.com before citing names. Use when tuning solve performance, setting optimality gaps, choosing LP/MIP/NLP algorithms…

not rated 10 1mo ago A SkillSpector: pass 99 tokens original MIT

ChainAware/behavioral-prediction-mcp

Skill Codex

Use this skill whenever a user asks about wallet safety, fraud risk, rug pull detection, wallet behavior analysis, DeFi personalization, on-chain reputation scoring, AML checks, token ranking by holder quality, airdrop screening, lending risk, token launch auditing, or AI agent trust scoring. Triggers on questions…

not rated 10 1mo ago A 440 tokens original MIT

competitor-gap-analysis

11071

scrollmark/socialgpt-mcp

Skill Claude CodeCodex

Compare a creator's top content against 1-3 named competitors to find where the competitors win and the creator is silent. Use when a SocialGPT user asks "what are my competitors doing that I'm not", "find my content gaps", "what should I steal from @rival", "where am I getting beaten", or wants a side-by-side read of…

not rated 10 1mo ago A 144 tokens original MIT

gptadmin-mcp-testing

11072

megamen32/gptadmin_opensource

Skill Claude CodeCodex

Verify a Memos-style MCP integration through GPTADMIN without duplicating the backend, leaking credentials, or confusing the native ShellMCP supervisor with legacy per-agent services.

not rated 10 changed 20d ago A 40 tokens AGPL-3.0

compiling-architecture

11073

inetgas/arch-compiler

Skill Claude CodeCodex needs its repo

Use when: user wants to select architecture patterns, compile a spec, iterate on constraints/NFRs, audit why patterns were selected/rejected, or finalise an architecture for implementation. Not when: no repeatable decisions needed, or constraints/NFRs are not yet known (gather those first).

not rated 10 4mo ago A 66 tokens original MIT

build-html-artifacts

11074

amol-patil/html-artifact-kit

Skill Codex

Build polished, self-contained HTML artifacts. Always use for requests to create, design, improve, or validate a dashboard, report, presentation or slides, narrative document, microsite, portal, console, operational tool, webpage, quick side artifact, or any standalone HTML deliverable, even when the user does not…

not rated 10 1mo ago A 95 tokens original MIT

kube-medic

11075

cacheforge-ai/cacheforge-skills

Skill Claude CodeCodex

Kubernetes Cluster Triage & Diagnostics — instant AI-powered incident triage via kubectl.

not rated 10 7mo ago A 22 tokens original MIT

zotero

11076

ketthub/zotero-skill

Skill Claude CodeCodex

Query your local Zotero library. Supports keyword, fulltext, author, collection, tag, DOI, and recent-additions search. Trigger: /zotero, "my papers", "Zotero", "find paper", "references", "citations". After installation, verify DEFAULTDB path in scripts/zotero-search.py points to your zotero.sqlite.

not rated 10 6mo ago A 79 tokens

diataxis

11077

rlespinasse/agent-skills

Skill Claude CodeCodex

Helps maintain documentation pages based on the Diataxis method. Analyzes existing docs, classifies pages into tutorials/how-to/explanation/reference categories, identifies gaps, and helps create or restructure documentation following Diataxis principles. Use when user mentions documentation structure, Diataxis, doc…

not rated 10 6d ago A SkillSpector: pass 75 tokens original MIT

creating-figures

11078

isomoes/skills

Skill Claude CodeCodex

Creates publication-quality scientific figures for academic papers using TikZ. Use when creating block diagrams, system architectures, flowcharts, or technical illustrations for papers and theses. Always render a temporary PNG/JPG preview and self-verify visual quality before finalizing figure files.

not rated 10 5mo ago A 57 tokens original MIT

autoresearch

11079

a-tokyo/agent-skills-harness

Skill Claude CodeCodex

Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy's autoresearch. USE FOR: autonomous improvement…

not rated 10 1mo ago A 116 tokens original MIT

zeroplot

11080

blackblue-labs/zeroplot

Skill Claude CodeCodex

Create editable charts, diagrams, figures, posters, or slides from intent, data, or references.

not rated 10 2mo ago A 24 tokens original MIT

shadow-web

11081

ulinycoin/shadow-web

Skill Claude CodeCodex

Browser automation for Cursor via Shadow Web MCP and shadow-web exec: detail levels (minimal/terse/xml/full), page classifier, shadowgrep, navigate/click/fill by data-sid, SchemaSnap, diff snapshots, self-healing, Camoufox. Use when browsing the web, scraping, running shadow-web exec, compressing HTML, or when the…

not rated 10 1mo ago A 97 tokens original MIT

periscope

11082

segentic-lab/periscope-mcp

Skill Claude CodeCodex

Drive the Periscope MCP server (74 Playwright + headless-Chrome tools) to test, audit, and debug websites and web apps — static sites, SPAs, and apps behind a login. Use this skill whenever the user wants to test a website or web app, run an E2E or interactive flow, audit accessibility/SEO/GEO/ performance, measure…

not rated 10 2mo ago A 183 tokens AGPL-3.0

Knuckles-Team/gitlab-api

Skill Claude CodeCodex

Review and merge GitLab merge requests via the gitlab-api MCP server — by default the MRs assigned to you or where you are a reviewer, optionally scoped to a project, group, or the whole instance. Read an MR, gate it on a green pipeline (pipeline → jobs → job log), then approve, accept/merge, or set…

not rated 10 13d ago A SkillSpector: warn 158 tokens original MIT

ziran

11084

taoq-ai/ziran

Skill Claude CodeCodex

ZIRAN is an open-source security testing framework for AI agents. It discovers dangerous tool chain compositions via knowledge graph analysis, detects execution-level side effects (not just text output), and runs multi-phase trust exploitation campaigns that model real attacker behavior.

not rated 10 4d ago A 0 tokens original Apache-2.0

touch-browser

11085

nangman-infra/touch-browser

Skill Codex

Use for evidence-first public web research and claim verification with touch-browser. Trigger when the task needs browser-backed discovery, page-grounded citations, claim extraction, or safe unresolved outcomes instead of guessed answers. Do not use for private account automation, uncontrolled browsing, or final truth…

not rated 10 3mo ago A 63 tokens original MPL-2.0

npd-tax-calculation

11086

AlsKozlov/ru-buh

Skill Claude CodeCodex

A calculator for professional-income tax in Russia for self-employed people, known as НПД. It covers the 4% rate for income from individuals, the 6% rate for income from companies, a ₽10,000 deduction, and the ₽2.4 million yearly limit.

not rated 10 4mo ago A 68 tokens

ui-ux-pro-max

11087

Rayenbabdallah/GetMCP

Skill Claude CodeCodex

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks.

not rated 10 4mo ago B 34 tokens copy · 89% Apache-2.0

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: