book-review

Name: book-review
Author: readwiseio

519installs7forks

How to install book-review?

readwiseio/readwise-skills/book-review

$npx -y skills add readwiseio/readwise-skills --skill book-review

Installs into the current project.

Summary

Draft a long-form book review from your Reader highlights — synthesizing the book with your broader reading history to generate original arguments

Files · 1

View on GitHub

SKILL.md

1	Draft a long-form book review from a user's Reader highlights — not just the target book,
2	but pulling in related highlights from their entire library to build original arguments.
3
4	The goal is a review that's more interesting than the book itself: summary + critique + original ideas,
5	where the original ideas come from connecting the book to everything else the user has read.
6
7	## Readwise Access
8
9	Check if Readwise MCP tools are available (e.g. `mcp__readwise__reader_list_documents`). If they are, use them throughout. If not, use the equivalent `readwise` CLI commands instead (e.g. `readwise list`, `readwise read <id>`, `readwise highlights <id>`, `readwise search <query>`). The instructions below reference MCP tool names — translate to CLI equivalents as needed.
10
11	## Setup
12
13	1. Check for persona file. Read `reader_persona.md` in the current working directory if it exists. Use it to understand the user's interests, reading goals, and voice — this shapes the review's framing, what connections to prioritize, and what the user is likely to care about. If no persona file exists, proceed without it and ask the user about their purpose for reading the book if it's not obvious from their highlights.
14
15	2. Parse the argument as a book title or search term.
16
17	```
18	/book-review Merchant Kings
19	/book-review 7 Powers
20	```
21
22	---
23
24	## Phase 1: Pull the Book's Highlights
25
26	### 1.1 Find the book
27
28	Search Reader for the target book:
29
30	```
31	mcp__readwise__reader_search_documents(query="[book title]", category_in=["epub", "pdf"])
32	```
33
34	If no results, broaden to all categories. If multiple matches, list them and ask the user to pick.
35
36	### 1.2 Get highlights
37
38	```
39	mcp__readwise__reader_get_document_highlights(document_id="[book_id]")
40	```
41
42	Read every highlight. Count them. If fewer than 10, warn the user — may not be enough material
43	for a substantive review. Ask whether to proceed or wait.
44
45	### 1.3 Get the full document details
46
47	```
48	mcp__readwise__reader_get_document_details(document_id="[book_id]")
49	```
50
51	Pull title, author, summary, cover image. You'll need these for the final output.
52
53	---
54
55	## Phase 2: Extract Claims
56
57	Process every highlight into an atomic claim. This is the step that turns
58	"I highlighted this paragraph" into structured, searchable research material.
59
60	For each highlight:
61
62	1. Read the highlighted text and any user note/annotation
63	2. Write a single present-tense declarative claim (under 10 words when possible)
64	3. If the user left a note, weight the claim toward what the note focused on
65
66	Claim quality standards:
67
68	Good claims are specific, searchable facts or assertions:
69	- "chimney sweeps died of scrotal cancer from coal soot"
70	- "Ottoman harem trained slave girls as elite bureaucrats"
71	- "monsoon winds enabled global maritime trade"
72
73	Bad claims are vague or generic:
74	- "coal mining had health consequences"
75	- "the author discusses Ottoman succession"
76	- "interesting point about slavery"
77
78	After processing all highlights, review the full list. Reject and rewrite any that are:
79	- Generic/boring ("author discusses X")
80	- Duplicative (two claims saying the same thing differently — consolidate)
81	- Vague (doesn't stand alone without reading the highlight)
82
83	Store the claims as a working list grouped by theme. This becomes your outline.
84
85	---
86
87	## Phase 3: Search the Library for Related Material
88
89	This is what makes the review more than a summary. For each major theme cluster
90	from Phase 2, search the user's full Reader library for related content.
91
92	### 3.1 Theme-based searches
93
94	For each theme cluster (aim for 3-6 themes):
95
96	```
97	mcp__readwise__reader_search_documents(query="[theme keywords]", limit=20)
98	```
99
100	Pull highlights from the top hits:
101
102	```
103	mcp__readwise__reader_get_document_highlights(document_id="[related_doc_id]")
104	```
105
106	You're looking for:
107	- Supporting evidence from other sources that strengthens a claim
108	- Contradictions that complicate the book's argument
109	- Parallel examples from different domains (the user read about X in biology, the book says the same about economics)
110	- The user's own prior thinking visible in their notes/annotations on related docs
111
112	### 3.2 Author search
113
114	```
115	mcp__readwise__reader_search_documents(query="[book author name]")
116	```
117
118	Check if the user has read other work by the same author. Prior context enriches the review.
119
120	### 3.3 Extract related claims
121
122	For each relevant highlight from a related document, extract a claim the same way
123	as Phase 2. Tag it with its source document so you can cite it properly.
124
125	Result: You should now have:
126	- The book's claims (Phase 2), grouped by theme
127	- Related claims from the broader library (Phase 3), mapped to those same themes
128	- A sense of where the user's reading supports, complicates, or extends the book
129
130	---
131
132	## Phase 4: Supplement with Web Research
133
134	Fill gaps that the

People who liked this also viewed

6 picks

Type

lark-drive飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sSkillsJul 2026382k16k
lark-sharedUse for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handlingSkillsJul 2026382k16k
lark-whiteboard飞书画板：查询和编辑飞书云文档中的画板。支持导出画板为预览图片、导出原始节点结构、使用多种格式更新画板内容。当用户需要查看画板内容、导出画板图片、编辑画板时使用此 skill。不负责：飞书云文档内容编辑（lark-doc）、文档内嵌电子表格/Base（lark-sheets / lark-base）。SkillsJul 2026380k16k
lark-task飞书任务：管理任务、清单和任务智能体。创建待办任务、查看和更新任务状态、拆分子任务、组织任务清单、分配协作成员、上传任务附件、注册或注销任务智能体、更新任务智能体的主页数据、写入智能体任务记录。当用户需要创建待办事项、查看任务列表、跟踪任务进度、管理项目清单或给他人分配任务、为任务上传附件文件、注册注销任务智能体、更新智能体主页数据、写入任务记录时使用。SkillsJul 2026380k16k
lark-attendance飞书考勤打卡：查询自己的考勤打卡记录SkillsJul 2026330k16k
lark-apps妙搭（Spark/Miaoda）应用开发与托管：应用创建、本地全栈开发、云端生成迭代、创意设计（UI mockup / 可交互原型 / 线框图 / 落地页 / 仪表盘 / 幻灯片 deck / 视觉探索）、AI相关能力和飞书平台能力或者其他外部能力集成、日志/Trace/监控指标/PV/UV 查询、环境变量管理、应用角色与成员管理、自动化触发器（定时/记录变更/Webhook/飞书审批）。当用户要SkillsJul 2026227k16k

book-review

519installs7forks

View on GitHub

How to install book-review?

readwiseio/readwise-skills/book-review

$npx -y skills add readwiseio/readwise-skills --skill book-review

Installs into the current project.

Summary

Draft a long-form book review from your Reader highlights — synthesizing the book with your broader reading history to generate original arguments

Files · 1

View on GitHub

SKILL.md

1	Draft a long-form book review from a user's Reader highlights — not just the target book,
2	but pulling in related highlights from their entire library to build original arguments.
3
4	The goal is a review that's more interesting than the book itself: summary + critique + original ideas,
5	where the original ideas come from connecting the book to everything else the user has read.
6
7	## Readwise Access
8
9	Check if Readwise MCP tools are available (e.g. `mcp__readwise__reader_list_documents`). If they are, use them throughout. If not, use the equivalent `readwise` CLI commands instead (e.g. `readwise list`, `readwise read <id>`, `readwise highlights <id>`, `readwise search <query>`). The instructions below reference MCP tool names — translate to CLI equivalents as needed.
10
11	## Setup
12
13	1. Check for persona file. Read `reader_persona.md` in the current working directory if it exists. Use it to understand the user's interests, reading goals, and voice — this shapes the review's framing, what connections to prioritize, and what the user is likely to care about. If no persona file exists, proceed without it and ask the user about their purpose for reading the book if it's not obvious from their highlights.
14
15	2. Parse the argument as a book title or search term.
16
17	```
18	/book-review Merchant Kings
19	/book-review 7 Powers
20	```
21
22	---
23
24	## Phase 1: Pull the Book's Highlights
25
26	### 1.1 Find the book
27
28	Search Reader for the target book:
29
30	```
31	mcp__readwise__reader_search_documents(query="[book title]", category_in=["epub", "pdf"])
32	```
33
34	If no results, broaden to all categories. If multiple matches, list them and ask the user to pick.
35
36	### 1.2 Get highlights
37
38	```
39	mcp__readwise__reader_get_document_highlights(document_id="[book_id]")
40	```
41
42	Read every highlight. Count them. If fewer than 10, warn the user — may not be enough material
43	for a substantive review. Ask whether to proceed or wait.
44
45	### 1.3 Get the full document details
46
47	```
48	mcp__readwise__reader_get_document_details(document_id="[book_id]")
49	```
50
51	Pull title, author, summary, cover image. You'll need these for the final output.
52
53	---
54
55	## Phase 2: Extract Claims
56
57	Process every highlight into an atomic claim. This is the step that turns
58	"I highlighted this paragraph" into structured, searchable research material.
59
60	For each highlight:
61
62	1. Read the highlighted text and any user note/annotation
63	2. Write a single present-tense declarative claim (under 10 words when possible)
64	3. If the user left a note, weight the claim toward what the note focused on
65
66	Claim quality standards:
67
68	Good claims are specific, searchable facts or assertions:
69	- "chimney sweeps died of scrotal cancer from coal soot"
70	- "Ottoman harem trained slave girls as elite bureaucrats"
71	- "monsoon winds enabled global maritime trade"
72
73	Bad claims are vague or generic:
74	- "coal mining had health consequences"
75	- "the author discusses Ottoman succession"
76	- "interesting point about slavery"
77
78	After processing all highlights, review the full list. Reject and rewrite any that are:
79	- Generic/boring ("author discusses X")
80	- Duplicative (two claims saying the same thing differently — consolidate)
81	- Vague (doesn't stand alone without reading the highlight)
82
83	Store the claims as a working list grouped by theme. This becomes your outline.
84
85	---
86
87	## Phase 3: Search the Library for Related Material
88
89	This is what makes the review more than a summary. For each major theme cluster
90	from Phase 2, search the user's full Reader library for related content.
91
92	### 3.1 Theme-based searches
93
94	For each theme cluster (aim for 3-6 themes):
95
96	```
97	mcp__readwise__reader_search_documents(query="[theme keywords]", limit=20)
98	```
99
100	Pull highlights from the top hits:
101
102	```
103	mcp__readwise__reader_get_document_highlights(document_id="[related_doc_id]")
104	```
105
106	You're looking for:
107	- Supporting evidence from other sources that strengthens a claim
108	- Contradictions that complicate the book's argument
109	- Parallel examples from different domains (the user read about X in biology, the book says the same about economics)
110	- The user's own prior thinking visible in their notes/annotations on related docs
111
112	### 3.2 Author search
113
114	```
115	mcp__readwise__reader_search_documents(query="[book author name]")
116	```
117
118	Check if the user has read other work by the same author. Prior context enriches the review.
119
120	### 3.3 Extract related claims
121
122	For each relevant highlight from a related document, extract a claim the same way
123	as Phase 2. Tag it with its source document so you can cite it properly.
124
125	Result: You should now have:
126	- The book's claims (Phase 2), grouped by theme
127	- Related claims from the broader library (Phase 3), mapped to those same themes
128	- A sense of where the user's reading supports, complicates, or extends the book
129
130	---
131
132	## Phase 4: Supplement with Web Research
133
134	Fill gaps that the

People who liked this also viewed

6 picks

Type