Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 274,255 indexed, measured the same four ways as everything else here.
A communication coach based on Nonviolent Communication, a method for discussing difficult situations by separating observable facts, feelings, needs, and specific requests. It helps turn blame or judgment into clearer, more respectful wording.
A tool for exploring companies in Y Combinator’s startup portfolio and maintaining a private knowledge base about them. Y Combinator is a startup accelerator, and the data comes from its public company index.
Create, improve, diagnose, and tailor resume bullet points from raw work, existing bullets, or job descriptions using truthful evidence, role focus, CAR/XYZ framing, technical specificity, impact, and concise natural language.
A thinking and writing framework based on Michael Polanyi’s work on knowledge and learning. It focuses on tacit knowledge: practical know-how that people may use without being able to fully explain it.
Answer first, one line; evidence only if it changes the reader's next action. Cut preamble, restatement, hedging, and the closing summary. Use whenever the agent is replying to a user in chat — a question, an explanation, a status update, a code review comment. Also use when the user says "terse", "be brief"…
Update libraries in a Bun project or monorepo with control over overrides, exact pins, 0.x versions, peer conflicts, supply-chain risk, and lockfile rebuild. Use when updating dependencies, bumping libraries, checking outdated packages, running bun audit, cleaning up overrides/resolutions, deduplicating the tree, or…
use when generating a doc the user will read and share — specs, roadmaps, pr explainers, research reports, plans, strategy docs. trigger words: "glyph," "spec," "roadmap," "explainer," "report," "plan," "save as a doc.".
Master orchestrator skill that coordinates a full multi-agent startup pipeline. Triggers on: build SaaS, launch startup, startup accelerator, build product, create MVP, SaaS builder, million dollar startup, build me a business, or using the Startup Factory. Coordinates 8 specialized sub-skills in a gated…
Trie et structure des documents en vrac en dataroom M&A-ready (11 dossiers + sous-dossiers multilingues), avec classification IA, détection des doublons exacts (SHA-256), détection des versions obsolètes, et checklist contextuelle enrichie via scraping site web + sources juridiques/fiscales/comptables (Légifrance…
Initializes a project's SDD (Specification-Driven Development) structure. On an EXISTING project, runs a phased deep analysis with chunking and generates /docs/sdd/ (00-overview to 08-glossary), CONSTITUTION.md and the review rules guide. On an EMPTY project (greenfield), conducts a guided interview about…
Build and validate a bounded, evidence-linked implementation plan without editing source or executing commands. Use when the user explicitly invokes /aet-plan or asks AET for an evidence-guided code plan.
Planeja a sua Série de Episódios no Instagram (reality de bastidores que vende) para lotar evento presencial, imersão ou bater meta de lançamento documentando a jornada real. Parte do Episódios Squad do Master Outsider. Use SEMPRE que o usuário rodar /ep-serie ou pedir para planejar série de episódios, reels em…
Recursively decompose a repository goal until every implementation leaf has explicit files, dependencies, contracts, rollback, and acceptance evidence, then orchestrate bounded subagents in dependency waves, integrate their work, and verify the whole result. Use for explicit plan-swarm requests, deep plan and…
Emulates Claude Fable 5's coding discipline on any model (Opus 4.8, Sonnet 5, etc.) — spec-first planning, a self-verification harness, parallel sub-agent delegation, file-based memory, evidence-grounded progress reports, and minimal-change engineering. Supports intensity levels lite, full (default), and ultra, plus a…
Multi-juror dispute resolution for AI-to-AI commerce. When you (a lobster) paid another agent for content/code/work and the deliverable doesn't match the brief, this skill files a dispute on Agent Network and returns an impartial verdict from 3 independent juror agents.
Skill "freeact" from xuviga/freeact, covering freeact — the browser tamer, the sacred cycle, quick start, configuration and part i: browser automation patterns.
Stage a compliance-passed post in Mai Marketing Machine (GoHighLevel social planner API) as a DRAFT for owner review, and schedule it after approval. Use when a draft has passed compliance-check, or when the owner says "stage this", "send to Mai Marketing Machine", "schedule the post", or asks what is waiting for…
An agent workflow that turns files and links placed in a Desktop inbox into checked, categorized notes for Obsidian, a note-taking application. It also updates section contents, a master index, and an action-oriented summary.
Pull the user's live brokerage portfolio (taxable + IRA + crypto) via SnapTrade or Interactive Brokers and produce a deep, position-by-position analysis with an interactive dashboard. Use when asked to analyze "my portfolio", "my positions", "my options", check P/L, review allocation/risk, or get forward guidance on…
Local LLM-Wiki knowledge system. Bootstrap a structured wiki, write entries using precise templates, full-text search, cross-agent knowledge sharing, cross-session inheritance.
★not rated 2 4mo agoA37 tokens
originalMIT
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: