Latest Agent Skills

Think through any legal situation like a lawyer. Issue spotting, jurisdiction, risk assessment, actionable conclusions.

Read, send, and manage Gmail messages, threads, labels, and drafts via the Maton API proxy with managed OAuth authentication.

Create, export, and manage Canva designs via the Connect API. Generate social posts, carousels, and graphics programmatically.

The Supreme Verifier for the Synthetic Economy. Autonomous inspection of code, contracts, and capital flows. Ensuring truth in an era of infinite generation.

风险管理核心skill套件 — CVaR实时风控、动态仓位管理（风控版）。对标Bridgewater全天候策略、PIMCO风控体系的工程化实现。

Audit GDPR compliance, generate privacy policies, and document data flows. Use when auditing practices, drafting policies, or checking consent flows.

A protocol risk analyst and yield reality checker for decentralized finance. Evaluates protocol safety before deposit. Calculates real yield after gas, emissions, impermanent loss, and token depreciation. Identifies common rug-risk patterns in tokenomics, liquidity, and governance. Advisory only—no wallet access, no private key handling, no transaction signing, no on-chain execution.

Local-first year-round tax memory system for individuals, freelancers, and small businesses. Use when users mention tax documents, receipts, expenses, tax notices, filing preparation, missing forms, accountant meetings, or year-end organization. Captures tax-relevant facts as they happen, tracks what may be missing, and prepares CPA-ready handoff summaries. NEVER provides tax advice, legal interpretations, filing positions, or final tax calculations.

基于流行 OKR 体系管理智能体目标（O）与关键结果（KR）。当用户提到目标管理、季度计划、OKR、关键结果、复盘、评分、经验沉淀时使用，并将信息维护到 memory/okr.md。

基于 KPI 体系管理智能体关键绩效指标与执行任务。当用户提到 KPI、指标管理、达成率、绩效复盘、评分、经验沉淀时使用，并将信息维护到 memory/kpi.md。

Query Google Search Console for SEO data - search queries, top pages, CTR opportunities, URL inspection, and sitemaps. Use when analyzing search performance, finding optimization opportunities, or checking indexing status.

Query Google Analytics 4 (GA4) data via the Analytics Data API. Use when you need to pull website analytics like top pages, traffic sources, user counts, sessions, conversions, or any GA4 metrics/dimensions. Supports custom date ranges and filtering.

Be the COO with process design, organizational scaling, cross-functional execution, and operational excellence.

Be the CFO with financial planning, cash management, fundraising, capital allocation, and strategic financial leadership.

Execute the next incomplete step (or full phase with --phase), ship the result, and prepare the next step

Use only for developer-facing products; position against alternatives by workflow, ecosystem, trust, and switching cost

Create or amend a self-contained PowerPoint-like HTML briefing slide deck for alignment pages, interrogation questions, research findings, framework/workshop artifacts, specs, reports, or documentation plans. Use when Codex should make review material more visual and navigable while preserving dense alignment/interrogation pages and source documents as linked references instead of auto-opening them.

Audit specs against codebase — find unimplemented features, diverged implementations, and undocumented code

Decompose a single roadmap phase into implementation steps, tests, and file-level detail

Scaffold the local env file with required variable stubs from .env.example and code, open it for the user to fill, and verify completeness by key names only — never reading secret values

Derive a portable product-idea kickoff prompt from the invoking repository for use with $idea-scope-brief in a different repository. Use when a repo suggests an adjacent product, SaaS, devtool, library, workflow, or experiment worth briefing elsewhere, but the user wants an idea prompt rather than code extraction or repo creation.

Orchestrator — author the flow-anchored logical domain model (entities, state machines, events/commands, read models, policies, logical contracts) from an approved user-flow map, running one domain-modeling framework per session, before UX variation work

Rank a topic's user-flow branches by proof priority (value × risk × frequency) right after user-flow-map, ordering the branches, gating variation breadth, and promoting or pruning flows so state-model and ux-variations grow the tree in proof order — writes only existing flow-tree ordering fields, no schema change.

Use only for video game projects; define playtest metrics for time-to-fun, replay, confusion, quit points, sharing, and retention

Use only for developer-facing products; analyze install, quickstart, first success, debugging, and production adoption journeys

Use only for developer-facing products; audit docs for quickstart clarity, examples, API reference, troubleshooting, and migration paths

Audit and implement behavior-preserving cleanup across types, dead code, dependencies, errors, and comments

Broad risk assessment — key-person, technical, regulatory, competitive, financial, and execution risks beyond product/market

Audit and reconcile the shared project glossary — find stale terms, missing definitions, conflicts, shadows, inheritance gaps, and cross-path divergences across research docs

Post-launch metrics & funnel analysis — cohort retention, channel performance, and progress against targets from $metrics

Nir Eyal engagement loop design — trigger, action, variable reward, investment

Design lean validation experiments — hypothesis, method, success criteria, sample size, timeline, and decision rules

Create or amend a portable HTML alignment review page in a target repo using bundled conventions and skillpacks alignment commands

Analyze a YouTube channel with evidence-first metadata, transcripts, performance fields, portfolio shape, and repeated content-quality patterns

Interview the user to define the characteristics of a skill they want created

Convert one Markdown report or a collection of documented Markdown outputs into clean JSX routes for a polished, readable frontend website

Loop feature-interviews over a brainstorm idea set and consolidate survivors into the roadmap

Evaluate the codebase and suggest ideas to explore with $feature-interview

Use only for video game projects; plan Steam/store page, capsule, trailer, screenshot, tag, and wishlist validation

Conduct a thorough project-wide code review as an expert panel, cross-referencing specs, changelogs, and design documents

Financial runway & unit economics tracker — burn rate, revenue trajectory, runway in months, scenario modeling

Manage the portfolio of product paths — review, activate, archive, restore, promote, fork, and check revisit triggers across the product-path manifest

Click-by-click instructions for manual blockers — DNS, OAuth, signups, and other GUI-dependent tasks

Use only for video game projects; design playable prototype tests and success criteria for fun, clarity, and replay

Use only for developer-facing tools, libraries, SDKs, CLIs, APIs, and infrastructure products

Use only for developer-facing products; map users, buyers, champions, contributors, and operational stakeholders

Use only for developer-facing products; plan adoption loops, examples, templates, community, and proof artifacts

Generate a project-level context snapshot for resuming work in a fresh session

Guide a structural migration or dependency upgrade with a step-by-step plan and verification

Evaluate codebase against enterprise ICP for production readiness, compliance, and multi-stakeholder journey coverage

Make the base agentic-skills available in a project by installing them project-local with npx skillpacks init, report and fix skill-install drift, clean up legacy user-home installs, and run guided setup for project-local domain packs. Use when Codex needs to enable base skills for a project, repair stale installs, confirm initialization status, remove old global installs, or set up and route domain packs.

Scan task pipeline health, build or update the project roadmap, and maintain a priority task queue

Derive owner/operator dogfood scenarios from product evidence and active-use cadence, then produce adoption instructions and manual evaluation checks

Adversarial one-question-at-a-time questioning to verify deep reading comprehension of alignment pages, specs, or any document

Define success metrics framework — activation, engagement, retention, growth, and business metrics tied to journey stages

Extract a bounded part of the invoking codebase into a new GitHub repository with private and public-OSS readiness gates

Audit codebase for opportunities to reduce lines of code while preserving functionality, performance, and quality

Validate user claims against codebase and git history, trace to root cause, and propose a fix

Estimate monthly burn rate from infrastructure signals and calculate payback period against revenue projections

Scaffolds a program.md research program for autoresearch by auto-detecting codebase signals and interviewing for missing details.