跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
搜索与研究

lean-beam

Use this when an AI should work on an external Lean project through the installed `lean-beam` wrapper, giving it direct efficient access to Lean's proof engine to avoid repeated inner-loop rebuilds through cheap speculative checks and zero-build module checkpoints.

leanprover · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add leanprover/lean-beam --skill lean-beam

技能说明


name: lean-beam description: Use this when an AI should work on an external Lean project through the installed lean-beam wrapper, giving it direct efficient access to Lean's proof engine to avoid repeated inner-loop rebuilds through cheap speculative checks and zero-build module checkpoints.

Lean Beam

Use this skill for Lean projects when you want the AI to replace repeated inner-loop lake build runs with cheap speculative Lean probes, optional follow-up handle execution, and targeted file checkpoints. A successful checkpoint is normally enough for local development. CI should run a clean lake build; do not force an expensive clean local rebuild after every checkpoint. Before calling work batch-validated, require a successful clean CI build, or run one clean local build when no such CI result is available or server-sensitive elaboration is suspected.

This is the Lean-only skill. It should stay focused on Lean and should not require Rocq setup or Rocq concepts. Do not factor shared Lean/Rocq skill instructions into a common helper; duplicate short guidance if both skills need it.

Setup

From the lean-beam repo root:

./scripts/install-beam.sh --codex

Use --claude, --pi, --opencode, or --vibe instead when installing for Claude Code, Pi Agent, OpenCode, or Mistral Vibe. Use --all-skills when you want every supported agent skill target.

The installer puts lean-beam, lean-beam-search, and lean-beam-mcp in ~/.local/bin, stages the self-contained runtime under BEAM_INSTALL_ROOT (default ~/.local/share/beam), requires elan on PATH, prebuilds the pinned lean-toolchain bundle by default, and installs the bundled Lean skill only for the agent flags you request. Use the setup docs for additional supported or custom toolchain prebuilds.

Use lean-beam --version for CLI bug reports and installed runtime identity checks. Use lean-beam-mcp --version to verify which installed MCP server wrapper, server binary, runtime payload hash, manifest, and source commit a client command resolves. Source checkout runs also report git commit/branch/dirty state when available. From a live MCP session, call beam_version to report the running server process identity as structured content. Installed identities include runtime_current; if a live session reports false after reinstalling, restart the agent or MCP client so it launches the current runtime. If a newly resolved installed wrapper still reports false, the install root's current link is missing or broken; stop normal Beam work and reinstall. If an installed identity reports runtime_error, do not treat it as a source checkout or try to clean it with lean-beam prune. After stopping active Beam agents and MCP clients, move an invalid manifest runtime out of BEAM_INSTALL_ROOT/versions, preserve it for inspection, and rerun the installer. For an invalid install-root marker, preserve and rename the exact BEAM_INSTALL_ROOT as a unit before reinstalling; do not recreate its ownership marker in place or delete the preserved state.

MCP workspace-bound tools carry an explicit local workspace descriptor on every call. Dropping that workspace only evicts its cached runtime and retained handles; it does not prove the MCP server binary itself was refreshed. Retain the canonical descriptor when a Lean operation, non-confidential feedback result, or drop result echoes it so a cached runtime can still be dropped if the project path or its Lean/Lake markers become unavailable.

Restart active agent or MCP client sessions after installation.

For the authoritative install and bundle-resolution order, see the repo docs/SETUP.md and Validated And Compatible Toolchains sections.

Skill Surface

This skill documents the current Lean-facing lean-beam workflow surface. Use the smallest command family that fits the task.

Agents may access Beam through the lean-beam wrapper or through a registered lean-beam-mcp server. This skill names wrapper commands because they are always available after installation. When your client exposes the matching MCP tools, use them with the same saved-file, version, update, sync, and isolation rules; do not treat MCP as a raw Lean LSP proxy.

Supported command families:

  • start and own a wrapper session: lean-beam serve
  • inspect the selected session state: lean-beam status
  • inspect existing code, navigation data, or proof state: lean-beam hover, lean-beam signature-help, lean-beam definition, lean-beam references, lean-beam document-symbols, lean-beam workspace-symbols, lean-beam goals before, lean-beam goals after
  • inspect actionable Lean items in a range: lean-beam todo
  • inspect file or daemon state: lean-beam open-files, lean-beam doctor, lean-beam stats
  • produce a local, pasteable bug report card from JSON input: lean-beam feedback-report
  • try one isolated speculative Lean snippet: lean-beam run-at
  • continue from one exact speculative state: lean-beam run-at-handle, lean-beam run-with, lean-beam run-with-linear, lean-beam release
  • refresh or checkpoint one tracked workspace module: lean-beam sync, lean-beam refresh, lean-beam save, lean-beam close-save
  • run shell-oriented search loops over the same handle APIs: lean-beam-search

What to treat as the normal agent workflow surface:

  • default workflow commands: lean-beam hover, lean-beam signature-help, lean-beam definition, lean-beam references, lean-beam document-symbols, lean-beam workspace-symbols, lean-beam goals, lean-beam todo, lean-beam run-at, lean-beam sync, lean-beam refresh
  • operational commands: lean-beam open-files, lean-beam doctor, lean-beam stats, lean-beam feedback-report, lean-beam save, lean-beam close-save
  • pre-stable support APIs: lean-beam run-at-handle, lean-beam run-with, `lean-beam ru
阅读完整来源 ↗