Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 272,651 indexed, measured the same four ways as everything else here.
Connect a third-party coding agent (Claude Code, Codex, Cursor, or any other MCP-capable client) to Warp Factory by installing and authenticating the oz CLI and registering the Factory MCP server. Use when someone outside Warp wants to set up Factory MCP access — for example to create or operate a software factory…
Use when designing or reviewing domain models — covers Bounded Contexts, Context Mapping, Aggregate Root, Value Objects vs Entities, Domain Events, Ubiquitous Language, Repository pattern, Domain vs Application Services, and DDD anti-patterns (anemic domain model, feature envy) with examples in TypeScript, Java, Go…
Yogic meditation protocol for AI agents - hold a single concept (water, a product, a mantra, any idea) through mantra repetition with caught-and-returned breaks, then harvest non-obvious associations after the cliche wave burns off. Three modes - live (the practice itself, traceless by design), open (the default - the…
MASTER ROUTER — activates FIRST on every non-trivial task. Analyzes the problem, determines if a specialized tool/skill can resolve it without spending reasoning tokens, and orchestrates execution. Also enforces token-compression on ALL output. Trigger: ANY task involving computation, simulation, literature…
Power BI debugging and optimization assistant. Use when diagnosing Power BI errors, optimizing slow DAX queries, running model health checks, reviewing calculated tables, or debugging relationship issues. Triggers on error messages, performance complaints, model validation requests, and DAX troubleshooting. Always…
Use when the user says something like "add login", "users need to sign in", "I want auth", "gate this behind a user account". The auth surface (login / signup / OAuth / sessions) is NOT something you build. Read this whole page before touching auth code.
The shared-record practice for sessions that run more than one agent. Open a run file, append typed messages with provenance as work happens, resolve rank disagreements explicitly, and validate the file before closing. Use whenever a task is dispatched to two or more agents, or when a run file already exists in the…
Use this skill when the user wants to create, edit, review, redline, comment on, polish, or verify structured document deliverables. Use it for Word or Google Docs-style reports, memos, briefs, proposals, letters, handbooks, forms, templates, redlines, comment-based revisions, accessibility cleanup, metadata cleanup…
Deep customer research — review mining, competitor audience analysis, survey design, interview frameworks, and language pattern extraction. Turn research into actionable insights.
Context, prompts, and sanity checks for editing Hemrock financial models. Covers the Standard Financial Model, Cap Table, Venture Fund Model, Fund Economics Tool, Venture Valuation, SaaS, Ecommerce, Unit Economics, and Runway. Point the AI at the template the user is editing; the skill supplies the sheet structure…
Use the mdt-cli CLI for quick ticket and project lookups from the terminal. This skill should be used when the user wants to inspect tickets, list projects, create tickets, or update attributes without MCP tools. Prefer mdt-cli over MCP read operations for single-entity lookups. Covers epic-level tickets (level=epic)…
A workflow for processing files from an `unprocessed/` folder, including screen recordings, exported conversations, notes, PDFs, and images. It moves information through raw and wiki stages.
A Chinese-language planning assistant for marketing directors. It guides annual business planning through market analysis, competitor strategy, goals, budgets, execution, and review.
Rebound recomposition budget monitor skill for Compose performance analysis. Guides budget class interpretation, violation diagnosis, skip rate analysis, stability optimization, CLI usage, and IDE plugin workflow. Use this skill whenever the user mentions recomposition, budget, violation, Rebound, skip rate, jank…
A long-running research workflow for topics with measurable results. It repeatedly tests a hypothesis, scores the attempt, records lessons, and can continue through an automated loop.
A skill containing climate-related domain knowledge, including its boundaries, supported intents, risk controls, and tools.
★not rated 6▲
+1 4mo agoA0 tokens
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: