菜单
Add a new AI coding agent adapter so it can participate in benchmarks. Use when integrating any new CLI-based coding tool (Cursor-like, Copilot alternative, open-source agent, etc.) into the adapter system.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Plan and execute code changes using a spec-driven workflow with structured documents. Use when making non-trivial changes (multi-file, multi-step, or behavior-impacting) that need structured planning before implementation. Not for trivial single-file edits.
Create and manage changesets for versioning with @changesets/cli. Use when making changes that need a changelog entry, preparing a release, or managing package versions.
Diagnose and fix failed benchmark runs. Use when a benchmark run fails, scores are unexpected, judges show errors, or traces are incomplete.
Build the pnpm monorepo correctly respecting inter-package dependencies. Use when building, verifying changes, or troubleshooting build failures.
Write and run tests using Node.js built-in test runner (node:test) with .mjs files. Use when creating new tests, debugging test failures, or understanding test infrastructure.
Understand the vanilla JS web-report app structure, patterns, and contribution guidelines. Use when modifying the UI, adding new views, or fixing frontend bugs.
| name | add-adapter |
| description | Add a new AI coding agent adapter so it can participate in benchmarks. Use when integrating any new CLI-based coding tool (Cursor-like, Copilot alternative, open-source agent, etc.) into the adapter system. |
Integrate a new coding agent into the benchmark adapter ecosystem.
Research the target CLI:
--version, --help)?Create packages/adapters/src/<agent>-adapter.ts:
AgentAdapter interface with: id, title, kind: "external", capability, preflight(), execute().capability, set supportTier ("supported", "experimental", or "blocked"), tokenAvailability ("available", "estimated", or "unavailable"), and list knownLimitations.buildAgentPrompt(context) for prompt formatting.runProcess() for CLI execution with timeout and cancellation support.probeHelp() and probeInvocationVersion() for preflight checks.AGENTARENA_<AGENT>_BIN environment variable for custom binary path."blocked" status with a clear explanation.Register in packages/adapters/src/adapter-registry.ts:
adapterEntries: ["<agent-id>", new <Agent>Adapter()].If the agent supports model selection, add --<agent>-model to packages/cli/src/args.ts and handle it in normalizeCliSelections() in packages/cli/src/index.ts.
Verify:
pnpm --filter @agentarena/adapters buildpnpm --filter @agentarena/cli buildpnpm test — existing tests must still pass.preflight() returns a meaningful status (not always "blocked" without explanation).knownLimitations if estimated or unavailable.tests/adapters-new.test.mjs.