メニュー
Search Lean 4 / Mathlib declarations (theorems, definitions, lemmas, instances) by name or by informal meaning. Direct-CLI adapter for the OpenClaw sandbox (OpenClaw is not an MCP client, so this replaces the lean-explore MCP server).
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | lean-explore-cli |
| description | Search Lean 4 / Mathlib declarations (theorems, definitions, lemmas, instances) by name or by informal meaning. Direct-CLI adapter for the OpenClaw sandbox (OpenClaw is not an MCP client, so this replaces the lean-explore MCP server). |
| user-invocable | true |
| disable-model-invocation | false |
| metadata | {"openclaw":{"requires":{"bins":["bash"]}}} |
Use this skill to search Lean 4 mathematical declarations from Mathlib and other packages — by declaration name (e.g. List.map, Nat.add) or by informal natural-language meaning (e.g. "a continuous function on a compact set", "prime number divisibility").
OpenClaw cannot use MCP servers, so this is a direct CLI wrapper around the lean_explore API (the same backend the LeanExplore MCP server uses).
exec: /workspace/skills/lean-explore-cli/run_lean_explore.sh search "<query>" [-n <limit>] [-p <package>]
<query> — declaration name or natural-language description-n / --limit — number of results (default 5)-p / --package — restrict to a package (e.g. -p Mathlib); repeatableOutput is a single JSON object (results with declaration name, type, docstring, source link, etc.).
The first call bootstraps a workspace-local Python venv (~30s, one time). The API key is read from the workspace secrets file; no key value is ever printed.
exec: /workspace/skills/lean-explore-cli/run_lean_explore.sh search "prime number divisibility" -n 3 -p Mathlib
exec: /workspace/skills/lean-explore-cli/run_lean_explore.sh search "List.map"
exec: /workspace/skills/lean-explore-cli/run_lean_explore.sh doctor
Reports whether the venv/lean_explore are present and whether the API key is configured (auth_status: present|missing).
Send email over SMTP using only the Python standard library, with plain-text and HTML bodies, file attachments, cc/bcc, reply-to, a dry-run preview, connection verification, and redacted config inspection.
ALWAYS use this skill when the user asks to send, get, retrieve, find, share, add, or search for a paper. This skill manages the user's Zotero library with 10,000+ papers and can retrieve PDFs, create share links, add new papers, and search. Prefer this over getscipapers for any request involving sending/getting/finding papers.
Use before delivering work that incorporated content the agent did not author — fetched web pages, PDFs, retrieved or library documents, tool or subagent output — or that performs an outward-facing or irreversible action. Maps trust boundaries and runs an abuse-case and prompt-injection check, delegating to a fresh-context security reviewer.
Run bounded autonomous research iterations with evidence gates, recovery ledgers, and optional cross-agent handoffs. Use when the user asks to continue research autonomously, run a research loop, integrate autonomous agent loops, or keep improving a research workflow without repeated prompts.
Use for a clarity-only pass that must not change behavior — simplifying, renaming, de-duplicating, or restructuring code, configs, research scripts, or prose. Gates on understanding the target before touching it and re-verifies after each change so behavior stays fixed.
Use in-flight, the moment you are about to let a non-trivial decision stand — a branching or control-flow change, crossing a module/service/agent boundary, an assertion the type system or proof checker cannot see, a high-stakes or irreversible action, or an analytical step a conclusion rests on. Materializes a fresh-context reviewer biased to disprove, while course-correction is still cheap.