← All skills

agent-engineering

CommunityMIT

Battle-tested engineering principles for AI coding agents. Covers plan-first workflow, subagent delegation, self-improvement loops, verification gates, elegant solutions, autonomous bug fixing, and structured task management. Use when configuring agent behavior, writing AGENTS.md files, or improving agent reliability and code quality.

The ZIP contains only this skill. It lives on GitHub Releases of the public orlandoneto/agent-skills repo — Ontoom is the showcase. A daily crawler refreshes the catalog.

How to install

  1. Download the ZIP and extract the skill folder.
  2. Cursor: .agents/skills/ck-agent-engineering/ or .cursor/skills/ck-agent-engineering/
  3. Claude Code: .claude/skills/ck-agent-engineering/
  4. Other AIs: .agents/skills/ck-agent-engineering/
cursorclaude-codecodexgeminiany

Source / credits: ckorhonen/claude-skills

Other skills in this collection

Skills (ckorhonen)

  • bird-fast

    Post tweets, read threads, search X/Twitter from the terminal using the bird CLI. Use when automating Twitter/X, posting from scripts, analyzing tweet threads, monitoring mentions, or working with the Twitter API without OAuth setup.

  • blockchain-auditor

    Security audit smart contracts for exploitable vulnerabilities from an unprivileged context. Use when analyzing Solidity contracts, reviewing bytecode, testing exploits on forks, or searching for ways to extract funds without owner access. Covers verified and unverified contracts, bytecode disassembly, vulnerability ranking, proof-of-concept exploit generation, DeFi protocol attacks, and cross-chain bridge security.

  • brainstorming

    Explore user intent, requirements and design before implementation through structured dialogue and design proposals. Use when asked to: create features, build components, add functionality, modify behavior, plan projects, or when user says 'help me design X', 'what should we build', 'let's brainstorm', or starts describing a new feature without a design.

  • ceo-review

    Review documents, proposals, and plans through the lens of a CEO. Simulates feedback from a founder-CEO who is technical, data-driven, and focused on long-term vision while navigating market volatility. Use when you want high-level strategic review: does this idea make sense as a company bet? Is the team right-sized? Will this survive a downturn? Is it community-first?

  • ck-review

    Review documents, proposals, and plans through the lens of a senior principal engineer. Simulates feedback from a technically deep IC who values clarity, pragmatism, and shipping velocity. Use when you want direct, blunt technical feedback on a proposal, architecture doc, design doc, or spec — especially around structure, tradeoffs, and scope.

  • codex-advisor

    Get a second opinion from OpenAI Codex CLI for plan reviews, code reviews, architecture decisions, and hard problems. Use when you need external validation, want to compare approaches, or are stuck on a difficult problem.