build-persona

Name: build-persona
Author: readwiseio

413installs7forks

How to install build-persona?

readwiseio/readwise-skills/build-persona

$npx -y skills add readwiseio/readwise-skills --skill build-persona

Installs into the current project.

Summary

Build a personalized reading profile from your Readwise Reader data, used by triage, quiz, and other skills

Files · 1

View on GitHub

SKILL.md

1	You are building a reader persona for the user based on their Readwise Reader library. This persona file is used by other skills (triage, quiz, etc.) to personalize their experience.
2
3	## Readwise Access
4
5	Check if Readwise MCP tools are available (e.g. `mcp__readwise__reader_list_documents`). If they are, use them throughout (and pass this context to the subagent). If not, use the equivalent `readwise` CLI commands instead (e.g. `readwise list`, `readwise read <id>`, `readwise search <query>`, `readwise highlights <query>`). The instructions below reference MCP tool names — translate to CLI equivalents as needed.
6
7	## Welcome
8
9	Open with a brief introduction:
10
11	> Build Persona · Readwise Reader
12	>
13	> I'll analyze your reading history — saves, highlights, and tags — and build a `reader_persona.md` profile in the current directory. Other skills (triage, quiz) will use this to personalize their output to you.
14	>
15	> I'll start with a quick pass (~1-2 min) and then you can decide if you want a deeper analysis.
16
17	## Process
18
19	IMPORTANT: This skill involves fetching a lot of data. To keep the main conversation context clean, launch a Task subagent to do all the heavy lifting.
20
21	### Phase 1: Quick Pass
22
23	The subagent should do a focused scan to build a solid initial persona fast:
24
25	1. Gather data. Run ALL of these in parallel (one batch of tool calls):
26
27	- 4 highlight searches: `mcp__readwise__readwise_search_highlights` with 4 broad queries (e.g. "ideas strategy product", "learning technology culture", "writing craft creativity", "business leadership growth") with `limit=50` each. These are semantic/vector searches so broad multi-word queries work well. Highlights are cheap and high-signal — cast a wide net.
28	- 4 document lists: `mcp__readwise__reader_list_documents` from each non-feed location: `location="new"`, `location="later"`, `location="shortlist"`, and `location="archive"` with `limit=100` each. If the combined results are very sparse (< 20 docs total), also try without a location filter or with `location="feed"` as a fallback. Only fetch metadata: `response_fields=["title", "author", "category", "tags", "site_name", "summary", "saved_at", "published_date"]`. Do NOT fetch full content.
29	- Tags: `mcp__readwise__reader_list_tags` to understand their organizational system.
30
31	2. Parse results efficiently. The JSON responses from document lists can be large (25k+ tokens). Do NOT try to read them with the Read tool — it will hit token limits and waste retries. Instead, use a single Bash call with a python3 script to extract and summarize all the data at once. The script should parse all result files together and output:
32	- Document counts by category
33	- Top 20 sites, authors, and tags
34	- Save velocity by month
35	- All docs saved in the last 3 weeks (title, category, author, date)
36	- A representative sample of highlight texts with their source titles/authors
37
38	3. Write the persona. Write `reader_persona.md` to the current working directory with these sections:
39
40	- Identity & Role — Who they appear to be (profession, role, industry)
41	- Core Interests — Top themes and topics, ranked by frequency and recency
42	- Reading Personality — How they read (saves a lot but reads selectively? highlights heavily? prefers short or long-form?)
43	- Current Obsessions — What they've been saving/reading most in the last 2-3 weeks
44	- Goals & Aspirations — What they seem to be working toward, inferred from patterns
45	- Taste & Sensibility — Thinkers and styles they gravitate toward (contrarian? practical? philosophical? technical?)
46	- Anti-interests — Topics notably absent or avoided
47	- Triage Guidance — Specific instructions for how to pitch documents to this person (e.g. "lead with practical applicability", "connect to their interest in X", "bar is high for AI content — flag when it's genuinely novel")
48
49	4. Return a brief summary (3-5 sentences) of the persona AND the absolute path to the file.
50
51	Subagent speed rules:
52	- Do NOT call `readwise_list_highlights` — it often errors and is redundant with search.
53	- Do NOT try to Read large JSON tool-result files — parse them with python3 via Bash.
54	- Combine all analysis into ONE python script, not multiple sequential scripts.
55	- Maximize parallel tool calls. Every API fetch in step 1 should be a single parallel batch.
56
57	### Phase 2: Deep Pass (optional)
58
59	After the quick-pass subagent returns, show the user the results and ask if they want a deeper analysis. If yes, launch a second subagent that:
60
61	- Fetches 4-6 more highlight searches with different, more specific queries informed by what phase 1 found (e.g. if the persona shows interest in AI tooling, search "AI agents workflows automation"; if they read fiction, search "fiction narrative storytelling") wit

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

build-persona

413installs7forks

View on GitHub

How to install build-persona?

readwiseio/readwise-skills/build-persona

$npx -y skills add readwiseio/readwise-skills --skill build-persona

Installs into the current project.

Summary

Build a personalized reading profile from your Readwise Reader data, used by triage, quiz, and other skills

Files · 1

View on GitHub

SKILL.md

1	You are building a reader persona for the user based on their Readwise Reader library. This persona file is used by other skills (triage, quiz, etc.) to personalize their experience.
2
3	## Readwise Access
4
5	Check if Readwise MCP tools are available (e.g. `mcp__readwise__reader_list_documents`). If they are, use them throughout (and pass this context to the subagent). If not, use the equivalent `readwise` CLI commands instead (e.g. `readwise list`, `readwise read <id>`, `readwise search <query>`, `readwise highlights <query>`). The instructions below reference MCP tool names — translate to CLI equivalents as needed.
6
7	## Welcome
8
9	Open with a brief introduction:
10
11	> Build Persona · Readwise Reader
12	>
13	> I'll analyze your reading history — saves, highlights, and tags — and build a `reader_persona.md` profile in the current directory. Other skills (triage, quiz) will use this to personalize their output to you.
14	>
15	> I'll start with a quick pass (~1-2 min) and then you can decide if you want a deeper analysis.
16
17	## Process
18
19	IMPORTANT: This skill involves fetching a lot of data. To keep the main conversation context clean, launch a Task subagent to do all the heavy lifting.
20
21	### Phase 1: Quick Pass
22
23	The subagent should do a focused scan to build a solid initial persona fast:
24
25	1. Gather data. Run ALL of these in parallel (one batch of tool calls):
26
27	- 4 highlight searches: `mcp__readwise__readwise_search_highlights` with 4 broad queries (e.g. "ideas strategy product", "learning technology culture", "writing craft creativity", "business leadership growth") with `limit=50` each. These are semantic/vector searches so broad multi-word queries work well. Highlights are cheap and high-signal — cast a wide net.
28	- 4 document lists: `mcp__readwise__reader_list_documents` from each non-feed location: `location="new"`, `location="later"`, `location="shortlist"`, and `location="archive"` with `limit=100` each. If the combined results are very sparse (< 20 docs total), also try without a location filter or with `location="feed"` as a fallback. Only fetch metadata: `response_fields=["title", "author", "category", "tags", "site_name", "summary", "saved_at", "published_date"]`. Do NOT fetch full content.
29	- Tags: `mcp__readwise__reader_list_tags` to understand their organizational system.
30
31	2. Parse results efficiently. The JSON responses from document lists can be large (25k+ tokens). Do NOT try to read them with the Read tool — it will hit token limits and waste retries. Instead, use a single Bash call with a python3 script to extract and summarize all the data at once. The script should parse all result files together and output:
32	- Document counts by category
33	- Top 20 sites, authors, and tags
34	- Save velocity by month
35	- All docs saved in the last 3 weeks (title, category, author, date)
36	- A representative sample of highlight texts with their source titles/authors
37
38	3. Write the persona. Write `reader_persona.md` to the current working directory with these sections:
39
40	- Identity & Role — Who they appear to be (profession, role, industry)
41	- Core Interests — Top themes and topics, ranked by frequency and recency
42	- Reading Personality — How they read (saves a lot but reads selectively? highlights heavily? prefers short or long-form?)
43	- Current Obsessions — What they've been saving/reading most in the last 2-3 weeks
44	- Goals & Aspirations — What they seem to be working toward, inferred from patterns
45	- Taste & Sensibility — Thinkers and styles they gravitate toward (contrarian? practical? philosophical? technical?)
46	- Anti-interests — Topics notably absent or avoided
47	- Triage Guidance — Specific instructions for how to pitch documents to this person (e.g. "lead with practical applicability", "connect to their interest in X", "bar is high for AI content — flag when it's genuinely novel")
48
49	4. Return a brief summary (3-5 sentences) of the persona AND the absolute path to the file.
50
51	Subagent speed rules:
52	- Do NOT call `readwise_list_highlights` — it often errors and is redundant with search.
53	- Do NOT try to Read large JSON tool-result files — parse them with python3 via Bash.
54	- Combine all analysis into ONE python script, not multiple sequential scripts.
55	- Maximize parallel tool calls. Every API fetch in step 1 should be a single parallel batch.
56
57	### Phase 2: Deep Pass (optional)
58
59	After the quick-pass subagent returns, show the user the results and ask if they want a deeper analysis. If yes, launch a second subagent that:
60
61	- Fetches 4-6 more highlight searches with different, more specific queries informed by what phase 1 found (e.g. if the persona shows interest in AI tooling, search "AI agents workflows automation"; if they read fiction, search "fiction narrative storytelling") wit

People who liked this also viewed

6 picks

Type