Sansheng Distill

REVIEW · 70
Community indexed

Claude Code skill: distill a book or video series into one interactive single-file HTML · 书籍/视频深度蒸馏

Verified installs0
Stars19
Version1.0.0
Quality71/100 · Strong
Trust70/100 · Sandbox only
Audit82/100 · Needs review

Supply asset profile

Research and knowledge work

Deep research, source comparison, literature review, RAG, knowledge search, and reports.

Browse track

Scenario

RAG and knowledge

I need my agent to build a RAG workflow over documents and retrieve reliable context.

Agent fit

Claude Code + CLI + Codex

Codex, Claude Code, Cursor, CLI, or custom agents.

Install

Ready

npx skills add sanshengai/sansheng-distill

Maintenance

fresh

9d since push

Risk

Needs review

Low GitHub adoption signal

GitHub quality

19

71/100 Quality · 78/100 Trust

Coverage tags

ResearchRAG and knowledgeclaude-codebook-distillationinteractive-html

Review notes

Low GitHub adoption signal · Quality score needs review

Agent adoption scorecard

Trust, audit, and install readiness at a glance

These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.

Quality

Strong
71

Solid option that is likely worth shortlisting for production workflows.

Trust

Sandbox only
70

Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.

Audit

Needs review
82

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

OpenAgentSkill Trust Score v5

Human review before install

Run only in a sandbox and compare close alternatives before using it for real work.

PythonCodexClaude CodeCursorOpenAgentSkill CLI

Stars

19 GitHub stars

Repo activity

19 stars, 2 forks

Maintenance

9d since push

License

MIT

Install

npx skills add sanshengai/sansheng-distill

Install safety

standard package or runtime install path

Permission surface

filesystem or document access

Agent outcomes

No agent outcome data yet

Docs

Strong README/SKILL.md context

Risk summary

Review before production

  • Low GitHub adoption signal
  • Quality score needs review
  • GitHub adoption: 19 GitHub stars
  • Stars/forks activity: 19 stars, 2 forks; issue activity unavailable in current metadata

Install readiness

Install path available

  • Install path is available
  • Repository evidence is available
  • License is declared
  • No Agent Proven outcome evidence yet

Agent-readable metadata

Machine-readable decision data for this skill.

Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.

Open JSON

Suited tasks

  • RAG and knowledge workflows
  • Claude Code teams
  • builders willing to evaluate younger projects
  • Chunk documents

Suited agents

PythonCodexClaude CodeCursorOpenAgentSkill CLICLI

Install decision

Command
npx skills add sanshengai/sansheng-distill
Policy
review
Human review
yes

Trust and risk

Trust
70/100
Audit
82/100
Risk level
Needs review

Outcome loop

Endpoint
/api/agent/outcome
Event ID
resolve
Outcomes
5

Install command

npx skills add sanshengai/sansheng-distill

Do not use when

  • teams that need a vendor-supported SLA
  • production agents without a repository review
  • Low GitHub adoption signal
  • Quality score needs review
  • GitHub adoption: 19 GitHub stars

Agent safety v2

66/100 · Review before install

Reviewed with permission notesreview

Usable candidate, but the agent should surface permission and audit notes before installation.

Require human approval before installing into a real workspace.

Resolve via API

medium

Network access

Skill likely fetches remote pages, APIs, repositories, or external services.

medium

Filesystem access

Skill may read or write project files, documents, generated artifacts, or local workspace state.

  • Low GitHub adoption signal

Install targets

Install this skill in your agent workflow

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

skill install

OpenAgentSkill CLI

Resolve policy, run the source installer safely, and report a verified install receipt.

$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install sanshengai-sansheng-distill

Agent resolve plan

Let an agent verify fit before installing.

The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.

Open text plan

Agent should check

  • Task fit and alternatives from Resolve API.
  • Audit score, trust score, and safety policy warnings.
  • Install target compatibility for Codex, Claude Code, Cursor, or CLI.

Copy prompt

Task: Use Sansheng Distill in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20Sansheng%20Distill%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/sanshengai-sansheng-distill/install
Install command: npx skills add sanshengai/sansheng-distill
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Agent handoff

Give an agent the install path, not another directory page.

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

Open install API

Agent prompt

Use Sansheng Distill for this task. Review https://www.openagentskill.com/api/skills/sanshengai-sansheng-distill/install, then install with: npx skills add sanshengai/sansheng-distill

Registry metadata

Agent-readable profile for automatic skill selection.

This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.

Open manifest

Agent fit

71/100

RAG and knowledge

Platforms

Python, Claude Code

Audit report

Needs review · 82/100

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

View audit reportView eval report

Agent decision cockpit

Fallback candidate for RAG and knowledge

Prototype with this skill first; keep a fallback candidate ready.

71
Readiness
Prototype
Stage

Role in stack

Fallback candidate

Primary fit

RAG and knowledge

Trust label

Prototype first

Install path

Command ready

Use when

  • RAG and knowledge workflows
  • Claude Code teams
  • builders willing to evaluate younger projects

Evidence

  • recent repository activity
  • install command or GitHub repo available
  • 71/100 quality profile
  • 2 OpenAgentSkill engagement events

review first

  • Low GitHub adoption signal

Implementation path

  1. 1Install it in a sandbox agent and run one RAG and knowledge task end to end.
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

Trust profile

Sandbox only

Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.

70
OpenAgentSkill Trust Score

GitHub adoption

FIX

19 GitHub stars

Stars/forks activity

FIX

19 stars, 2 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

9d since push

License clarity

PASS

MIT

Good signals

  • AI review approved
  • Install path is available
  • Repository evidence is available
  • Recently maintained repository
  • Install command has no obvious high-risk pattern
  • Outcome loop is ready but needs first real agent run

Review before install

  • Low GitHub adoption signal
  • Quality score needs review
  • GitHub adoption: 19 GitHub stars
  • Stars/forks activity: 19 stars, 2 forks; issue activity unavailable in current metadata
  • No real agent outcome reports yet
  • Human review required before unattended installation

Recommended action

Run only in a sandbox and compare close alternatives before using it for real work.

Quality profile

Strong candidate for agent workflows

Solid option that is likely worth shortlisting for production workflows.

71
GitHub stars
19
Freshness
9d ago
Install ready
Yes
License
MIT
Review before install: Low GitHub adoption signal

Workflow fit

Use this skill in these scenarios

Workflow fit

Add it to a complete workflow

Alternative shortlist

Compare before you install

Similar skills that may fit this task.

Compare all

Overview

# sansheng-distill · 书籍蒸馏引擎

> 把一本书(或一组视频),熬成一张能点、能跳、越读越厚的**单文件交互网页**。

**中文** | [English](./README_EN.md)

<p align="center"> <img src="assets/demo.gif" alt="用蒸馏 skill 处理尤瓦尔·赫拉利四本书的成品演示" width="100%"> <br> <sub><em>▲ 用它把尤瓦尔·赫拉利的四本书蒸成一个作品集页:作者思想演变、概念漂移、母题红线、跨书互链(12 秒静音循环预览)</em></sub> </p>

## 这是什么

丢给它一本书(`.epub` / `.pdf` / `.txt` / `.azw3` / `.mobi`),或一组视频,它跑完一条多步管线,吐出**一个可以直接双击打开的单文件 HTML 页** —— 不联网、不依赖服务器,一个文件就是全部。

它不是"摘要"。摘要是把书压短、读完就扔;蒸馏是把书**拆成一张知识地图**:凝练成一句公式、一张可点的思维导图、一章章能单独展开的精读、一组读完回看的自检问句,再联网补上作者档案、正反书评、跨书观点,并和你蒸过的其他书自动互链。**AI 拆书是拿来当地图,不是替你读原书** —— 这句话一直挂在页面底部。

## 先看产出,再决定装不装

它不是一个有界面的软件,没有"操作截图"可看 —— 但它的**成果**是可视的。下面是真实产出(用赫拉利四本书蒸的作品集,以及单本《人类简史》的蒸馏页):

<table> <tr> <td width="50%"><img src="assets/01-at-a-glance.png" width="100%"><br><sub><b>全书速览 + 餐巾纸公式</b> —— 真封面、一句公式、核心主张、思维导图、关键金句,一屏抓住全书骨架。</sub></td> <td width="50%"><img src="assets/02-mindmap.png" width="100%"><br><sub><b>可点跳思维导图</b> —— 节点可展开,点一下跳到对应章节。</sub></td> </tr> <tr> <td><img src="assets/03-chapter-deep-read.png" width="100%"><br><sub><b>逐章精读</b> —— 每章单独展开,忠实转述。</sub></td> <td><img src="assets/04-core-idea.png" width="100%"><br><sub><b>核心一击</b> —— 全书最反直觉的论点做成可视化。</sub></td> </tr> <tr> <td><img src="assets/05-action-checklist.png" width="100%"><br><sub><b>行动清单</b> —— 决策规则、心智模型、行动路线图。</sub></td> <td><img src="assets/06-critique.png" width="100%"><br><sub><b>批判与盲点</b> —— 作者盲点、时代局限,附正反书评来源。</sub></td> </tr> </table>

## 它到底帮你做什么 —— 一页里的五段阅读漏斗

一本书蒸完,是一页从"3 秒速览"层层展开到"深挖到底"的阅读漏斗:

| 段 | 你看到什么 | |---|---| | **① 全书速览** | 真封面 + 一句"餐巾纸公式" + 核心主张 + 可点思维导图 + 关键金句 —— 3 秒抓住全书骨架 | | **② 逐章精读** | 每章 800-1500 字忠实转述,可单独展开,不是标签式提炼 | | **③ 核心一击** | 把全书最反直觉的那个论点,单独做成一张可视化 | | **④ 行动 & 自检** | 因果链、心智模型、决策规则,配一组读完回看的自检问句(纯浏览、无打分) | | **⑤ 该信几分 / 再往下** | 批判段、内在张力、正反书评、同类书、跨书回声、作者档案 —— 全带可点来源 |

再叠上三个交互层:**可点跳思维导图**(自绘 SVG,无第三方库) · **7 套主题一键切换** · **跨书知识互链**(蒸的书越多,网越密)。

蒸一整套书(如赫拉利四本)时,还会额外合成一个**作者作品集页**:思想演变时间线、概念在不同书里的漂移、贯穿多书的母题红线、"该从哪本读起"的路线 —— 就是顶部演示里那个页面。

## 还能蒸「一个人」,不只是「一部作品」(v0.5.0)

上面说的都是把**一部作品**蒸成

Platform compatibility

pythonFULL

Technical details

Version
1.0.0
License
MIT
Last updated
Aug 18, 2026
Published
Aug 14, 2026

Frameworks & tools

Python

Decision snapshot

Fallback candidate

71
Ready
Prototype
Stage

recent repository activity

Audit

Install review

Install and adoption review

82
Needs review
Security
87/100
Maintenance
100/100
Install
92/100
Open full auditView eval report

Agent-proven evidence

Agent-proven evidence

Outcome reports after resolve, review, install, and one narrow run.

0
Proven
Needs first agent runAuto-install: review firstLast: Unknown
Success rate
Recent failure
Outcomes
0
Output quality
Failed
0
Not relevant
0
Installs
0
Risk blocked
0
Setup needed
0
Production
0

No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.

Install

Add to agent workflow

Free and open source. Review the report before installing into production agents.

Growth loop

Share kit

X

Scenario-led draft for Sansheng Distill, ready for a manual X post.

Curator note
A practical pick for design or creative work:

Sansheng Distill: A Claude Code skill that distills books or video series into a single interactive HTML knowledge map.

19 stars

https://www.openagentskill.com/skills/sanshengai-sansheng-distill?ref=x
Open X draft
Optional reply with install command
Listing + install path for Sansheng Distill:
https://www.openagentskill.com/skills/sanshengai-sansheng-distill?ref=x

Install: npx skills add sanshengai/sansheng-distill

Listing source

Community indexed

Claimable

This listing was indexed from public sources and is not marked official until a maintainer claim is approved.

Creator
sanshengai
Indexed by
OpenAgentSkill community index

Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.

Claim this skill

Owner claim

Claim this skill listing

This Community indexed listing is attributed to sanshengai but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.

Creator backlink kit

Add the evidence badges to your README

Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/sanshengai-sansheng-distill?metric=listed&label=Listed)](https://www.openagentskill.com/skills/sanshengai-sansheng-distill)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/sanshengai-sansheng-distill?metric=trust&label=Trust)](https://www.openagentskill.com/skills/sanshengai-sansheng-distill)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/sanshengai-sansheng-distill?metric=audit&label=Audit)](https://www.openagentskill.com/skills/sanshengai-sansheng-distill/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/sanshengai-sansheng-distill?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/sanshengai-sansheng-distill)

Author

S

sanshengai

@sanshengai

Platform fit

Health signals

GitHub stars
19
Quality score
43/100
Last GitHub push
Aug 13, 2026
Framework hints
1
OpenAgentSkill views
2
Install copies
0
Outbound clicks
0

Community signal

Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.

Trust & safety

Sandbox only

70
  • GitHub adoption19 GitHub starsFIX
  • Stars/forks activity19 stars, 2 forks; issue activity unavailable in current metadataFIX
  • Recent maintenance9d since pushPASS
  • License clarityMITPASS
  • README/SKILL.md completenessMetadata includes enough usage and workflow contextPASS
  • Dependency/runtime riskno major dependency risk hints in public metadataPASS