Agent Skillsmohitagw15856/pm-claude-skills › whiteboard-to-spec

whiteboard-to-spec

GitHub

将白板、便利贴或草图照片转化为结构化执行规范。通过忠实转录、视觉语法解析及歧义记录,生成包含决策、流程图(Mermaid)和待办事项的文档,确保信息完整且无猜测。

plugins/pm-vision/skills/whiteboard-to-spec/SKILL.md mohitagw15856/pm-claude-skills

Trigger Scenarios

提供白板或草书照片后要求整理内容 询问'写出我们画的内容' 需要解读工作坊后的视觉笔记

Install

npx skills add mohitagw15856/pm-claude-skills --skill whiteboard-to-spec -g -y
More Options

Non-standard path

npx skills add https://github.com/mohitagw15856/pm-claude-skills/tree/main/plugins/pm-vision/skills/whiteboard-to-spec -g -y

Use without installing

npx skills use mohitagw15856/pm-claude-skills@whiteboard-to-spec

指定 Agent (Claude Code)

npx skills add mohitagw15856/pm-claude-skills --skill whiteboard-to-spec -a claude-code -g -y

安装 repo 全部 skill

npx skills add mohitagw15856/pm-claude-skills --all -g -y

预览 repo 内 skill

npx skills add mohitagw15856/pm-claude-skills --list

SKILL.md

Frontmatter
{
    "name": "whiteboard-to-spec",
    "description": "Turn photos of a whiteboard, sticky-note wall, or napkin sketch into a structured spec the team can execute. Use when given whiteboard photos after a workshop, sketch images of a flow or architecture, or asked to 'write up what we drew'. Produces a structured write-up — decisions, flows, open questions, owners — that preserves everything on the board and flags what was ambiguous. Requires image input."
}

Whiteboard To Spec Skill

The whiteboard is where teams decide; the photo of it is where decisions go to die. This skill reads the photo like the person who was in the room — arrows, crossings-out, shorthand, spatial grouping — and produces the write-up that should have been made that afternoon.

What This Skill Produces

  • A faithful transcription of everything legible on the board, organised by its spatial grouping
  • The structured spec: decisions made, flows/diagrams redrawn as text or Mermaid, options considered (including crossed-out ones — rejections are decisions), open questions
  • An ambiguity ledger: what couldn't be read or could mean two things, flagged instead of guessed

Required Inputs

  • The image(s) — one or more photos of the board/wall/sketch. If none is attached, ask for it; never proceed on a verbal description alone.
  • Context (ask if missing): what was the session about, who attended, what decision it served

Reading Method

  1. Transcribe first, interpret second. Pass one lists what is physically on the board, region by region (top-left, centre…), including arrows, boxes, colours, underlines, and crossings-out. Do not skip marginalia — the small note at the edge is often the real decision.
  2. Honour the visual grammar. Boxes = entities/steps; arrows = flow or causality (note direction); crossed-out = considered and rejected (keep it, labelled as rejected); circled/starred/underlined = emphasis; separate clusters = separate topics; a "?" = the room didn't agree.
  3. Redraw, don't describe. Flows and architectures become Mermaid diagrams or ordered steps, not paragraphs about arrows.
  4. Never invent legibility. Unreadable text becomes [illegible — looks like "…"] in the ambiguity ledger. A wrong guess presented confidently poisons the whole spec.
  5. Multiple photos: establish overlap first (same board, different angles vs. different boards) and merge without duplicating.

Output Format

Board write-up: [session topic] — [date]

What the board says (transcription by region): [region] — [contents, verbatim where legible]

Decisions on the board:

# Decision Evidence on the board Confidence
[e.g. "circled, arrow from both options"] high / read-between-lines

Flows / structures (redrawn):

[the diagram the board was drawing]

Considered and rejected: [crossed-out items, with what replaced them]

Open questions from the board: [every "?", disagreement marker, or dangling arrow]

Ambiguity ledger: [illegible or two-way-readable items — for the room to resolve]

Suggested next step: [the one action the board implies, e.g. "confirm decision #2 with the two owners named"]

Quality Checks

  • Every legible element on the board appears somewhere in the write-up — nothing silently dropped
  • Crossed-out content is preserved as "rejected", not omitted
  • Diagrams are redrawn as Mermaid/steps, not prose descriptions of arrows
  • Every uncertain reading is in the ambiguity ledger, not presented as fact
  • Decisions carry their on-board evidence, so a sceptic can check the photo

Anti-Patterns

  • Do not proceed without an image — this skill reads boards, it doesn't imagine them
  • Do not "clean up" the room's thinking into what it should have decided — transcribe what it did decide
  • Do not guess illegible words silently — a confident wrong guess is worse than a flagged gap
  • Do not ignore spatial grouping — merging two separate clusters into one list destroys the meaning
  • Do not drop the marginalia — initials, dates, and edge notes are often owners and deadlines

Version History

  • a38bc30 Current 2026-07-05 11:27

Same Skill Collection

exports/openclaw/360-feedback-template/SKILL.md
exports/openclaw/401k-plan-decoder/SKILL.md
exports/openclaw/ab-test-planner/SKILL.md
exports/openclaw/ab-test-readout/SKILL.md
exports/openclaw/accessibility-audit/SKILL.md
exports/openclaw/account-plan/SKILL.md
exports/openclaw/acquirer-red-team/SKILL.md
exports/openclaw/ad-copy/SKILL.md
exports/openclaw/aeo-optimizer/SKILL.md
exports/openclaw/agenda-or-cancel/SKILL.md
exports/openclaw/agent-design-review/SKILL.md
exports/openclaw/agent-observability-spec/SKILL.md
exports/openclaw/agent-spec/SKILL.md
exports/openclaw/ai-ethics-review/SKILL.md
exports/openclaw/ai-eval-plan/SKILL.md
exports/openclaw/ai-feature-prd/SKILL.md
exports/openclaw/ai-product-canvas/SKILL.md
exports/openclaw/air-quality/SKILL.md
exports/openclaw/altitude-shifter/SKILL.md
exports/openclaw/ambiguity-resolver/SKILL.md
exports/openclaw/analyst-relations-brief/SKILL.md
exports/openclaw/announcement-card/SKILL.md
exports/openclaw/api-docs-writer/SKILL.md
exports/openclaw/api-test-plan/SKILL.md
exports/openclaw/api-versioning-strategy/SKILL.md
exports/openclaw/apology-letter/SKILL.md
exports/openclaw/architecture-decision-record/SKILL.md
exports/openclaw/architecture-diagram/SKILL.md
exports/openclaw/archive-strategy/SKILL.md
exports/openclaw/assumption-bounty/SKILL.md
exports/openclaw/assumption-mapper/SKILL.md
exports/openclaw/async-update-format/SKILL.md
exports/openclaw/auto-repair-estimate-decoder/SKILL.md
exports/openclaw/autopilot-charter/SKILL.md
exports/openclaw/benefits-decoder/SKILL.md
exports/openclaw/bid-tender-review/SKILL.md
exports/openclaw/board-deck-narrative/SKILL.md
exports/openclaw/board-minutes/SKILL.md
exports/openclaw/board-pre-read/SKILL.md
exports/openclaw/bom-cost-review/SKILL.md
exports/openclaw/bookkeeping-categorization/SKILL.md
exports/openclaw/boolean-search-builder/SKILL.md
exports/openclaw/brag-doc/SKILL.md
exports/openclaw/brainstorming/SKILL.md
exports/openclaw/brief-builder/SKILL.md
exports/openclaw/briefing-note/SKILL.md
exports/openclaw/budget-builder/SKILL.md
exports/openclaw/budget-variance-analysis/SKILL.md
exports/openclaw/bug-diagnosis/SKILL.md
exports/openclaw/bug-report/SKILL.md

Metadata

Files
0
Version
471c606
Hash
e6f0f4f1
Indexed
2026-07-05 11:27

- 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-07-30 16:24
浙ICP备14020137号-1 $방문자$