菜单
Create an evidence-grounded framing document from transcripts, call notes, stakeholder notes, or conversation records.
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
| name | framing-doc |
| description | Create an evidence-grounded framing document from transcripts, call notes, stakeholder notes, or conversation records. |
| user-invocable | true |
| argument-hint | [transcript paths, notes, topic area, or frame request] |
Use this skill when the user has transcripts, VTT files, call notes, stakeholder notes, or conversation records and wants a frame that captures what problem is worth solving and why this one should be chosen over alternatives.
This is a Codex-safe adaptation of the upstream framing-doc shaping skill. It has no external command, model, deployment, credential, or network dependency.
Establish:
If source material may contain RED data, ask for sanitized input or keep the work local-only. Do not store transcripts in memory or .local-notes.
Produce a frame document with:
---
shaping: true
---
# [Topic] - Frame
## Source
### [Speaker] ([Date])
> "Verbatim quote..."
[Brief connective context where needed.]
---
## Pre-work: [Topic] Options Landscape
| Option | What it does | Who benefits | Signal strength |
| ------------- | ------------ | ------------ | --------------- |
| **A. [Name]** | ... | ... | ... |
**Why A now:** [Evidence-based argument.]
---
## Problem
- [Pain or broken condition, traceable to source]
## Outcome
- [High-level success state, not solution-specific]
---
## Less about
- [What this is not trying to solve]
## More about
- [What kind of solution actually fits]
Include Less about / More about only when the source material shows a meaningful boundary or a likely wrong direction.
The Source section is ground truth. Everything else is interpretation.
After writing each Problem or Outcome bullet, ask: who said this, and where?
Survey options that surfaced in the conversations. For each option, capture:
Make the case for the option to pursue now:
Do not invent a roadmap for the other options. The frame only claims which problem comes first and why.
Improve, audit, simplify, rewrite, or migrate prompts, tool descriptions, agent instructions, and prompt stacks for GPT-5.6 Sol or the GPT-5.6 family. Use for outcome-first prompt design, autonomy boundaries, tool routing, PTC, grounding, verbosity, reasoning effort, and prompt evals.
Apply a deep, design-minded engineering workflow for complex work that needs careful planning, iteration, and simplification.
Use when preparing or running a Claude CLI agentic engineering review through claude -p for repository audits, architecture analysis, system design, security review, large refactors, specs, RFCs, or evidence-grounded long-form engineering analysis.
Use when preparing or running a ZCode GLM-5.2 agentic builder workflow through zcode --prompt for fast implementation, iterative code generation, focused fixes, and validation on an existing repository.
Apply adversarial opposite-analysis to plans, specs, architecture, code changes, and claims. Use when the user asks for adversarial review, opposing analysis, contrarian review, red-team reasoning, or Z.ai and MiniMax cross-checks through the Ralph MCP router.
Review and adjudicate Bugbot, Cursor, Seer, and similar automated PR feedback with local evidence before accepting, fixing, or dismissing findings.