openclaw-bot

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.

Use when drafting, rewriting, polishing, or revising prose while preserving author intent by tracking claims, evidence, caveats, and revision deltas.

Use when choosing an appropriate model, reasoning level, and role for subagents or multi-agent research work.

Use when the user mentions OpenProse or prose workflows, wants explicit multi-agent research and synthesis, or wants a reusable orchestration pattern. In Codex, emulate OpenClaw OpenProse using spawn_agent, structured decomposition, and workspace artifacts.

Use before a version- or spec-sensitive decision — framework or library code, a CLI flag, a config schema field, or a named standard/edition — when correctness depends on the exact version. Detect the version, ground the decision in the authoritative source, and cite it; flag the assumption when no source is available.

Use VNU eOffice from OpenClaw: monitor updates, list latest documents, search documents, download attachments, and send requested files through Telegram.

Use when the user wants to organize, rearrange, sort, or clean up workspace files with safe dry-run and explicit apply behavior.

Use when preparing optional AxiomMath AXLE MCP setup for manual formal-proof assistance.

Use when drafting, validating, or normalizing bounded cross-agent task/result packets for parent-controlled handoffs. This is a packet-contract skill, not a runtime delegation broker.

Resolve DOI/ISBN details, prepare manifests from text or txt files, use getscipapers for external retrieval/search after library-first routing, and manage request watches safely.

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).

Use when preparing optional LeanExplore MCP setup for Lean declaration search and formalization support.

Use when deciding whether a research claim should enter the optional Lean formalization lane.

Use when checking whether a Lean artifact can safely support a research claim.

Use when the user wants animated math (handwritten-style equation writing, equation morphing between derivation steps, and emphasis) rendered with Manim, as a silent video clip that can stand alone or be spliced into a slides-to-video deck. The free, optional companion to slides-to-video for math lectures.

Use when starting a nontrivial research task to frame scope, success criteria, evidence plan, and the right downstream workflow before expensive browsing or multi-agent work begins.

Use when a research draft or report exists and needs a pre-final review for unsupported claims, ambiguity, scope drift, or missing evidence before delivery.

Use when the user wants to turn prepared slides (PNG, PDF, or PPTX) into a narrated, captioned video in a chosen language and presenter role, using only free tools. A three-phase human-in-the-loop flow (analyze, draft transcript, render) gates rendering behind an explicit transcript approval.

Use when the user wants research, source gathering, current-information lookups, cross-source synthesis, or extraction from URLs/PDFs/videos using web search, page inspection, local tools, and sub-agents.

Use when selecting, ranking, or validating submission venues for an existing scholarly manuscript or draft venue shortlist. A deliverable venue recommendation requires comparator-paper evidence for every ranked venue; bibliography overlap and offline placeholders are discovery signals only. Do not use for generic draft review, rewriting, paper retrieval, paper download, Zotero mutation, or one-off venue facts.

Use when the user asks to draw, refactor, extract, compile, or review a TikZ/PGF figure, especially structural diagrams such as flowcharts, DAGs, trees, commutative diagrams, finite graphs, automata, or research-derived summary figures. Prefer this skill when the output should follow a structure-first workflow like figure brief to spec to render to check to compile to review, and when document-facing output should use adjustbox width fitting.

Fetch ranked RSS digests by tag; list, search, add, edit, import, export, disable, enable, or remove feeds; and run feed health checks.

Resolve DOI/ISBN details, prepare manifests from text or txt files, use getscipapers for retrieval/search, and manage request watches safely.

Dynamically plan a multi-agent discussion, review, or research workflow with role selection, model assignment, round control, and recovery-aware orchestration.

Use when the user wants structured information from public scientific, biomedical, regulatory, materials, patent, or economic databases. This is a reference-first skill for selecting the right database and query strategy.

Use when a research task benefits from an explicit phased workflow with structured source handoff across search, analysis, and writing, and when preserving citations across phases matters.

Extract paper identifiers from research/RSS digests and create getscipapers manifests for retrieval.

Use when the user wants to parse, convert, chunk, or structurally analyze PDFs, DOCX, PPTX, HTML, images, audio transcripts, or similar documents with Docling. Prefer this skill for local document parsing before ad hoc text extraction.

Generate a minimal Lean-style theorem skeleton locally.

Use at the start of computationally intensive local tasks to detect CPU, GPU, memory, and disk availability, and to emit a `.openclaw_resources.json` planning file with strategy recommendations.

Verify small graph-theoretic claims using a local Python helper.

Use when a research or engineering task needs automatic heavy-compute routing through the local broker for Modal-backed remote CPU, high-memory CPU, or GPU execution.

Use as a metadata and discovery fallback for papers, preprints, citations, DOIs, PMIDs, and open-access signals after local library routing is exhausted or when external paper discovery is explicitly needed.

Use for review-only requests for papers or books when the user did not explicitly ask for annotation. Handles the normal single-agent review flow.

Generate a local research digest from arXiv and OpenAlex using a local Python script. Also manages tracked research topics.