跳到正文
cccskills
免费在 GitHub 公开

book-evidence-writing

Revise the Harbor Book so prose, drawings, and marginalia explain the same argument without unpublished development-document dependencies. Use for chapter additions, substantive rewrites, caption editing, visual exposition, and eliminating internal ADR citations.

中文简介正在准备中。当前显示原文说明。

实测评分 未实测

查看安装方法

包含的文件(10)

  • SKILL.md4.9 KB
  • CHANGELOG.md497 B
  • examples/adr-to-inspectable-argument.md2.2 KB
  • examples/INDEX.md355 B
  • README.md701 B
  • references/01-argument-inspection.md1.7 KB
  • references/02-marginalia-and-cues.md1.6 KB
  • references/INDEX.md468 B
  • tests/INDEX.md326 B
  • tests/test_book_evidence_writing.py2.3 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Write the Argument the Reader Can Inspect

These are editorial decisions from manuscript review and visual evidence examples, ensuring every claim in the Harbor Book (The Harbor, the Person, and the Economy) can be inspected by the reader without relying on unpublished design records, private ADRs, or workshop jargon.

Read First

Read the target section with its neighbouring paragraphs, its rendered Book pages, and skills/tufte-evidence-design/references/margin-apparatus.md. For numerical or protocol figures, also read Tufte Evidence Design and the relevant chartwork rules. Consult the reference documents in references/:

See concrete worked before-and-after transformations in examples/:

Core Rules for Revision

  1. State the reader's difficulty first. Begin with the real-world operational problem: a revoked credential returns after restore; a new identity escapes a penalty; a reviewer shares another reviewer's blind spot.
  2. Give a concrete instance before generalizing. Name actors, quantities, actions, and consequences. Define necessary vocabulary at first use.
  3. State the mechanism and its assumptions. Replace "the design record says" with what must hold and why. Unpublished ADR numbers, private proposal paths, and branch histories cannot serve as reader-facing authority.
  4. Preserve epistemic status distinctions. Distinctly demarcate:
    • Theorem / formal proof
    • Bounded mechanical check
    • Implemented slice
    • Proposed mechanism
    • Empirical hypothesis Removing an internal citation must not convert a proposal into a shipping claim.
  5. Make each visual and textual mode contribute uniquely:
    • Prose develops reasoning.
    • A drawing exposes spatial or relational topology.
    • A table permits direct numeric lookup.
    • The margin offers an example, counterexample, or concrete warning. Eliminate redundant restatements across these modes.
  6. Eliminate workshop narration. Strip out filler phrases like "the honesty rider", "this is the hinge", "the whole story", and "precisely the synthesis". Replace them immediately with the concrete proposition being made.
  7. Conclude with consequences and remaining limits. Never end with a promotional summary. Cross-reference upcoming topics by concept name, never by private file path or issue number.
  8. Margin cues must state the claim or warning. Never print a bare "Pitfall", "Key idea", or "Note". Use an active sentence: "A restore can undo revocation" or "Access is not permission".

Verification Checklist

  • Read without captions: The text flows logically and makes sense on its own.
  • Read without prose: Figures and tables are self-explanatory with proper labels.
  • Zero private citations: No ADR-XXXX, internal branch names, or private issue IDs appear.
  • No bare margin tags: All margin annotations state active assertions or warnings.
  • Epistemic honesty: Implementation status is clearly separated from proposed designs.
  • Automated Tests: Verify bundle integrity and editorial gates with pytest tests/test_book_evidence_writing.py.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Expert in 2000s-era music visualization (Milkdrop, AVS, Geiss) and modern WebGL implementations. Specializes in Butterchurn integration, Web Audio API AnalyserNode FFT data, GLSL shaders for audio-reactive visuals, and psychedelic generative art. Activate on "Milkdrop", "music visualization", "WebGL visualizer", "Butterchurn", "audio reactive", "FFT visualization", "spectrum analyzer". NOT for simple bar charts/waveforms (use basic canvas), video editing, or non-audio visuals.

中文简介正在准备中。当前显示原文说明。

curiositech/port-daddy32026年10月19日 更新

Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape.

中文简介正在准备中。当前显示原文说明。

curiositech/port-daddy32026年10月19日 更新

Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).

中文简介正在准备中。当前显示原文说明。

curiositech/port-daddy32026年10月19日 更新

Apply crisis decision-making research to agent routing, uncertainty triage, and coordination failure analysis in time-pressured systems. Use when diagnosing handoff failures, analytical paralysis, or expert judgment under incomplete information. NOT for routine coding, simple CRUD design, or static single-agent tasks with complete information.

中文简介正在准备中。当前显示原文说明。

curiositech/port-daddy32026年10月19日 更新

Use for insight, reframing, contradiction, impasse, and anomaly-driven problem solving when execution effort no longer helps. NOT for routine optimization, error correction, or well-specified tasks with known solution paths.

中文简介正在准备中。当前显示原文说明。

curiositech/port-daddy32026年10月19日 更新

Apply cognitive task analysis to expert work that depends on perceptual cues, branching judgment, and recurring monitoring loops. Use when decomposing expert capability into agent structure, simulation design, or validation interviews. NOT for ordinary step-by-step SOP capture or simple pipelines with no tacit cue layer.

中文简介正在准备中。当前显示原文说明。

curiositech/port-daddy32026年10月19日 更新

查看 curiositech 的全部技能

报告此技能的问题