This skill should be used when a Seedance 2.0 request is a long story, connected set of clips, multi-generation scene, campaign sequence, dense storyboard, continuation-ready plan, or any idea that must be divided into stateful clips.

Select the right Proof of Life (PoL) probe based on hypothesis, risk, and resources. Use this to match the validation method to the real learning goal, not tooling comfort.

Single-agent mission orchestrator. Decomposes a mission into tasks, spawns one worker per task using the default model, verifies exit criteria, and chains tasks with retry. No critic pattern — each worker self-verifies. Simple, fast, works with any model config.

Compose a morning digest combining local weather, news for the user's interest topic, a structured summary, and a memory note.

Auditable compliance bundle: deep-research with citations → signable .docx report → read-only PDF archive → memory note of audit findings.

Convert normalized multi-search-engine results to minimal BibTeX, preserving real DOI, author, publication year, arXiv ID, source URL, and provenance metadata when available. Unknown years are omitted and duplicate DOI records collapse to one entry.

OpenSquilla-compatible audio generation adapter for webpage audio requests. Prefer OpenRouter config/API key in OpenSquilla; preserve the upstream CellCog workflow only as optional ClawHub provenance.

Safely update Excel workbooks by first locating candidate files, verifying workbook structure before editing, and running post-write validation against required sheets, populated columns, and sample counts.

Use shell commands or Python libraries to extract PDF text when read_file PDF handler fails

Fallback workflow for extracting text from PDFs when read_file returns binary data

Generate spreadsheet, diagram, and PDF report as a cohesive deliverable set with iteration budgeting per component

Handle LaTeX Unicode errors in pandoc PDF generation by normalizing special characters to ASCII

Fallback from execute_code_sandbox to run_shell when e2b sandbox is unavailable

Handle docx files using shell-based XML extraction and python-docx via run_shell when standard tools fail

Identify and handle pre-execution agent failures occurring before any iterations or tool usage

当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用

Use when an OpenShell sandbox returns policy_denied, mentions policy.local, or needs a narrow network policy proposal.

Production deployment principles and decision-making. Safe deployment workflows, rollback strategies, and verification. Teaches thinking, not scripts.

Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.

API — Headless CMS — 137 abstractions. Entry, model, and group event handlers and use cases.