Skill Claude CodeCodexCursor
Uses AgentVouch marketplace and trust model to browse skills, inspect author trust, install free or paid skills, publish skills, and reason about vouch/report semantics. Use when working with agentvouch.xyz, web/public/skill.md, /api/skills, X-AgentVouch-Auth, purchaseSkill, author trust signals, or AgentVouch…
Instructions file CodexOpenCode
AGENTS.md instructions for dirtybits/agentvouch, covering agentvouch — agent operating manual, 0. orientation (read first, 60 seconds), 1. session start checklist, 2. conventions and planning and execution.
Instructions file
Claude Code instructions for dirtybits/agentvouch: Read and write to AGENTS.md instead of CLAUDE.md.
Skill Claude CodeCodex
End substantial Codex turns with concise outcomes, concrete verification status, useful numbered next steps, and an explicit prompt asking whether to proceed.
Instructions file CodexOpenCode
AGENTS.md instructions for dirtybits/agent-skills, covering agent instructions, finding and installing skills and repository contributions.
Skill Claude CodeCodex
Production-grade Ethereum/EVM development workflow for smart contracts, dApps, transactions, clients, gas optimization, testing, security review, deployment, verification, monitoring, and incident response across Foundry, Hardhat, Solidity, TypeScript, viem, ethers, wagmi, and common EVM networks.
Skill Claude CodeCodex
Guides and best practices for working with financial documents, building financial models, wrangling CSV data, and structuring Jupyter notebooks. Use when the user is building DCF models, LBO models, comparable analysis, analyzing financial data in CSVs, creating charts/visualizations of financial data, or structuring…
Skill Claude CodeCodex
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Skill Claude CodeCodex
Fetch, triage, and fix unresolved Cursor Bugbot or automated PR review comments. Use when the user asks to fix Bugbot findings, babysit a PR, resolve automated review comments, or make a pull request merge-ready.
Skill Claude CodeCodex
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
Skill Claude CodeCodex
Use when doing GitHub work end-to-end: auth, repository setup, issue triage, PR implementation, code review, CI monitoring, merge/release, and fallback REST workflows.
Skill Claude CodeCodex
Run production database schema changes without incidents, split additive runtime DDL from risky one-shot migrations, guard migration scripts with an expected-host check and a read-only preflight, rehearse the exact command on a disposable branch copied from production (Neon or similar branching Postgres), and verify…
Skill Claude CodeCodex
Operate safely in repositories where multiple coding agents (Claude, Codex, Cursor, humans) work in parallel git worktrees. Covers session bootstrap in a fresh worktree, toolchain/version pinning, lockfile-safe dependency installs, branch topology and reconciliation, recovering "lost" work without redoing it, commit…
Skill Claude CodeCodex
Use when publishing Node/npm packages from a repository or monorepo, especially scoped public packages, beta/latest dist-tags, workspace publishing, npm 2FA, publish verification, local tarball smoke tests, and debugging npm publish/install errors such as E403, E404, ENOVERSIONS, ELOOP, or pack destination failures.
Skill Claude CodeCodex
Ship multi-phase engineering work as one-PR-per-phase with plan-first review, adversarial cross-agent code review, per-thread fix verification, and an honest phase status ledger. Use when executing a phased plan across sessions or agents, when asked to review or babysit a PR produced by another agent, when responding…
Skill Claude CodeCodex
Write, review, and maintain implementation-ready .plan.md files with YAML frontmatter, actionable TODO lists, concrete execution details, verification gates, and rollback notes. Use when creating, splitting, reviewing, or updating plan files, especially files under .agents/plans or .cursor/plans — and also whenever…
Skill Claude CodeCodex
Use when researching papers, feeds, markets, knowledge bases, or long-form research outputs: arXiv, blog/RSS monitoring, LLM wiki knowledge bases, Polymarket, and paper-writing workflows.
Skill Claude CodeCodex
Write and revise technical content so labels, headings, instructions, plans, status names, error messages, identifiers, and Git branches are clear without hidden context. Use when creating or reviewing technical documentation, operational procedures, UI labels, project phases or gates, issue and PR titles, and branch…
Skill Claude CodeCodex
Organize and synchronize local agent skill directories across Codex, Claude, Cursor, Hermes, OpenClaw, and other agent tools. Use when the user asks to audit, mirror, link, migrate, or reconcile skill folders such as /.agents/skills, /.codex/skills, /.claude/skills, /.cursor/skills, /.hermes/skills, /.openclaw/skills…
Skill Claude CodeCodex
Use when planning, debugging, testing, reviewing, simplifying, or spiking code changes across languages: systematic debugging, TDD, debugpy/Node inspectors, code cleanup, and implementation strategy.
Skill Claude CodeCodex
Best practices for delegating work to sub-agents — when to spawn one vs. work inline, how to write self-contained prompts, orchestration patterns, and how to author reusable agent-type definitions.
Skill Claude CodeCodex
End substantial Codex turns with a concise outcome, concrete verification status, numbered recommended next steps, and an explicit prompt asking whether to proceed with one of those options. Use when wrapping up implementation work, debugging, research, planning, reviews, publishing flows, or other non-trivial tasks…
Skill Claude CodeCodex
Designs and reviews web3 protocols, incentive systems, token flows, governance, payments, disputes, launch specs, and threat models. Use when planning or reviewing on-chain products, DeFi mechanisms, staking or slashing models, marketplaces, DAOs, bridges, or oracle-dependent systems.