一键导入
cli-appendix-job-outline
Plan headless blender --background export or render jobs when MCP chat control is a poor fit; cite upstream Blender CLI docs only.
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。
菜单
Plan headless blender --background export or render jobs when MCP chat control is a poor fit; cite upstream Blender CLI docs only.
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
Claude Desktop-facing BlendOps router skill for planning, runtime readiness, evidence truth, and non-Blender-user outputs using bundled references.
Help users and agents choose the next safe BlendOps action across skills, docs, runtime readiness, evals, packaging, and Draft v0 release boundaries.
Blender skills pack for non-Blender users. Use for scene planning, runtime readiness, render/export/GLB evidence, Claude Connect guidance, and plain-language handoff across multiple AI agents.
Turn a locked 3D brief plus chosen recipe into a measurable acceptance checklist with evidence hooks.
Verify brief completeness, runtime posture, skill coverage, and evidence habits before starting a pack workflow.
Outline Path 1 hosting options — Anthropic Blender Connector vs manual MCP client — both need Blender Lab MCP add-on in Blender 5.1+.
| name | cli-appendix-job-outline |
| description | Plan headless blender --background export or render jobs when MCP chat control is a poor fit; cite upstream Blender CLI docs only. |
Structure CLI fallback appendix jobs (batch render, batch export, scripted scene setup) using Blender's documented command-line interface — without presenting arbitrary Python as the user-facing product surface.
references/job-type-matrix.mdreferences/flag-order-reminders.mdreferences/stateless-limitations.md| Input | Why it is required |
|---|---|
| Job intent (render vs export vs scripted pipeline) | Chooses matrix row |
| Output artifact expectations | Drives validation hooks |
| Input | Use |
|---|---|
| GPU availability | Device flags note |
| Mixture of Windows/Linux paths | Quote escaping caution |
Runtime status: Not Run | Attempted | Produced | Verified | Failed | Blocked / Not Run
Artifact status: Not Run | Not Produced | Produced | Verified | Failed
Evidence used: <CLI logs when available>
Limitations: no viewport Grab; script args via `--` separator per upstream docs
../../laws/evidence-before-done.md../../laws/non-blender-user-language.md../../laws/no-arbitrary-python-interface.md../../laws/official-runtime-only.mdPlanning outline — BlendOps does not execute Blender. CLI fallback appendix is documented upstream as a first-class Blender CLI surface; BlendOps has no in-repo evidence file yet. Stay truthful: MCP paths remain Path 1 / Path 2 when interactivity matters.
Abstract outline only.
Allow attaching sample log locations — still no success claim without artifacts.
Describe intended future job pack.
| Verdict | Criteria |
|---|---|
| Pass | Coherent phased outline + evidence hooks |
| Warn | GPU device uncertain — dual-branch note |
| Fail | Presents giant opaque Python as deliverable |
../runtime-path-picker/SKILL.md../output-format-decision/SKILL.md../render-export-evidence/SKILL.mdreferences/job-type-matrix.mdreferences/flag-order-reminders.mdreferences/stateless-limitations.md../../docs/runtime-stack-strategy.md