菜单
Use when the user wants a quick sanity check for a finite graph claim, construction, or encoding using the lightweight OpenClaw verifier.
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
Use when the user asks for a multi-agent discussion, panel review, multi-agent review, or multi-agent research session with role selection, round control, and template-based orchestration.
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.
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.
Runtime helper for autonomous-research-loop ledgers. Use to initialize, append, validate, inspect, or smoke-test autonomous research loop state files without network, package installation, provider CLI calls, or live agent spawning.
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 external DOI/ISBN/title resolution, manifest creation from pasted text, and paper retrieval after the local library-first workflow does not satisfy the request or the user explicitly opts out of library use.
| name | graph-verifier |
| description | Use when the user wants a quick sanity check for a finite graph claim, construction, or encoding using the lightweight OpenClaw verifier. |
| metadata | {"short-description":"Lightweight graph claim verification"} |
On native Windows, use the managed Windows runner and the native runtime command target. Set $runtime to the installed runtime root. Multi-agent installs usually use %LOCALAPPDATA%\ai-agents-skills\runtime. Then run:
$runtime = if ($env:AAS_RUNTIME_ROOT) { $env:AAS_RUNTIME_ROOT } else { "$env:LOCALAPPDATA\ai-agents-skills\runtime" }
& "$runtime\run_skill.bat" "skills/graph-verifier/run_graph_verifier.bat" <args>
POSIX examples below use run_skill.sh and .sh command targets; use the Windows command target above on native Windows.
This uses the managed ai-agents-skills runtime copy of the graph verifier workflow.
For heavier graph-theoretic or algebraic computations, route to sagemath instead.
$AAS_RUNTIME_ROOT/workspace/skills/graph-verifier/Use the managed runtime runner rather than invoking run_graph_verifier.sh directly.
Set AAS_RUNTIME_ROOT to the installed runtime root before using the shared
runner directly.
Shared runner:
runtime_root="${AAS_RUNTIME_ROOT:?Set AAS_RUNTIME_ROOT to the installed runtime root}"; bash "$runtime_root/run_skill.sh"/tmp/graph_input.json.Supported shapes include graph_data, edges, adjacency, and optional expected values.
runtime_root="${AAS_RUNTIME_ROOT:?Set AAS_RUNTIME_ROOT to the installed runtime root}"
bash "$runtime_root/run_skill.sh" skills/graph-verifier/run_graph_verifier.sh --input /tmp/graph_input.json
When this skill is involved, consider this workflow template (install via
the workflow-templates artifact profile, or --with-deps to pull backing skills):
tikz-figure-verification-runbook -- Bounded draw-compile-verify-redraw loop for a TikZ figure that guarantees it is free of overlap, wrong meaning, and bad layout, with Sage-assisted graph realization and fresh-agent visual confirmation before the strict approval gate.