synthesis

Name: synthesis
Author: NatsuFox

62stars5forks

How to install synthesis?

natsufox/tapestry/synthesis

$npx -y skills add NatsuFox/Tapestry --skill synthesis

Installs into the current project.

Summary

Convert stored Tapestry artifacts into higher-level synthesis. Use when a user wants interpretation, consolidation, research notes, or analysis built on top of an already-ingested URL or note.

Files · 1

View on GitHub

SKILL.md

1	# Tapestry Synthesis
2
3	Analyze a stored Tapestry artifact: $ARGUMENTS
4
5	## When to use this skill
6
7	Use this skill when:
8	- A user wants interpretation or analysis of already-ingested content
9	- You need to consolidate multiple sources into research notes
10	- The user asks for synthesis, insights, or higher-level understanding
11	- You need to organize ingested content into the knowledge base hierarchy
12	- The deterministic ingest is complete and model-based reasoning is needed
13
14	## Overview
15
16	This skill is the workflow layer for model-eligible reasoning.
17
18	Use it after deterministic ingest has already produced:
19
20	1. a capture JSON file
21	2. a normalized feed JSON file
22	3. a Markdown knowledge-base note
23	4. a structured handoff payload describing the recommended analysis
24
25	The package runtime does not call any model APIs directly. This skill owns the interpretation step.
26
27	This skill is also responsible for maintaining the book-like knowledge base under `knowledge-base/`.
28
29	Important: The synthesis mode configuration controls when this skill should be invoked:
30	- `auto`: Agent evaluates note accumulation and decides whether to merge (intelligent, load-based)
31	- `manual`: Only runs when explicitly requested by user
32	- `batch`: Runs after multiple ingests to process all at once
33	- `deterministic`: Runs automatically after every single ingest (high overhead)
34
35	See `config/tapestry.config.json` for current mode setting.
36
37	## Workflow
38
39	1. Identify the target:
40	- if the user gave a stored note path, use it directly
41	- if the user gave a URL and it has not been ingested yet, run `$tapestry-ingest` first
42	2. IMPORTANT: Change to the project root directory before running the script:
43
44	```bash
45	cd /path/to/your/tapestry/project
46	python synthesis/_scripts/load_context.py \
47	"$ARGUMENTS"
48	```
49
50	Or use the --project-root flag:
51
52	```bash
53	python synthesis/_scripts/load_context.py \
54	--project-root /path/to/your/tapestry/project \
55	"$ARGUMENTS"
56	```
57
58	3. Read the returned handoff payload carefully:
59	- `digest` is the deterministic baseline
60	- `analysis.skill`, `analysis.instructions`, and `analysis.deliverable` describe the intended workflow
61	- `note_text`, `feed_payload`, and `capture_payload` are the factual source materials
62	- Identify the language by reading the content naturally (title, body, comments)
63	4. Ensure the book hierarchy exists:
64
65	```bash
66	cd /path/to/your/tapestry/project
67	python synthesis/_scripts/bootstrap_kb.py
68	```
69
70	Or use the --project-root flag:
71
72	```bash
73	python synthesis/_scripts/bootstrap_kb.py \
74	--project-root /path/to/your/tapestry/project
75	```
76
77	5. Read the knowledge-base governance files:
78	- `synthesis/_kb_rules/_shared-governance.md`
79	- `synthesis/_kb_rules/topic-taxonomy.md`
80	- `synthesis/_kb_rules/chapter-decision-rules.md`
81	6. CRITICAL: Read the existing knowledge base structure thoroughly:
82	- Explore `knowledge-base/books/` to understand existing topics and chapters
83	- Read relevant `index.md` files to understand chapter scope and content
84	- Look for existing chapters where this content naturally fits
85	7. Default to integration - Decide in this priority order:
86	1. FIRST CHOICE: Extend an existing chapter - Integrate the new content into an existing chapter's narrative if it matches the chapter's central concept. Do NOT just append; weave it into the existing structure.
87	2. SECOND CHOICE: Create a new chapter - Only if the content introduces a distinct subdomain that doesn't fit existing chapters
88	3. LAST RESORT: Restructure the topic tree - Only if multiple chapters overlap heavily or the taxonomy has become incoherent
89	8. IMPORTANT: Identify the language of the source content by reading it, then write your synthesis in that same language. Do not translate unless explicitly requested.
90	9. When extending an existing chapter:
91	- Read the full chapter content first
92	- Identify where the new information fits thematically
93	- Integrate it into the existing narrative structure (don't append at the end)
94	- Update section headers if the new content shifts the conceptual balance
95	- Maintain consistent voice and formatting
96	10. When creating a new chapter:
97	- Ensure it represents a recurring domain, not a one-off article
98	- Update the parent `index.md` to register the new chapter
99	- Follow the chapter structure patterns from existing chapters
100	11. Return the synthesis clearly, grounded in the stored artifacts rather than vague recollection.
101
102	## Synthesis Quality Standards
103
104	IMPORTANT: All synthesized content must go through this refinement process, regardless of the source crawler or content type. These standards ensure consistent, high-quality o

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

synthesis

62stars5forks

View on GitHub

How to install synthesis?

natsufox/tapestry/synthesis

$npx -y skills add NatsuFox/Tapestry --skill synthesis

Installs into the current project.

Summary

Convert stored Tapestry artifacts into higher-level synthesis. Use when a user wants interpretation, consolidation, research notes, or analysis built on top of an already-ingested URL or note.

Files · 1

View on GitHub

SKILL.md

1	# Tapestry Synthesis
2
3	Analyze a stored Tapestry artifact: $ARGUMENTS
4
5	## When to use this skill
6
7	Use this skill when:
8	- A user wants interpretation or analysis of already-ingested content
9	- You need to consolidate multiple sources into research notes
10	- The user asks for synthesis, insights, or higher-level understanding
11	- You need to organize ingested content into the knowledge base hierarchy
12	- The deterministic ingest is complete and model-based reasoning is needed
13
14	## Overview
15
16	This skill is the workflow layer for model-eligible reasoning.
17
18	Use it after deterministic ingest has already produced:
19
20	1. a capture JSON file
21	2. a normalized feed JSON file
22	3. a Markdown knowledge-base note
23	4. a structured handoff payload describing the recommended analysis
24
25	The package runtime does not call any model APIs directly. This skill owns the interpretation step.
26
27	This skill is also responsible for maintaining the book-like knowledge base under `knowledge-base/`.
28
29	Important: The synthesis mode configuration controls when this skill should be invoked:
30	- `auto`: Agent evaluates note accumulation and decides whether to merge (intelligent, load-based)
31	- `manual`: Only runs when explicitly requested by user
32	- `batch`: Runs after multiple ingests to process all at once
33	- `deterministic`: Runs automatically after every single ingest (high overhead)
34
35	See `config/tapestry.config.json` for current mode setting.
36
37	## Workflow
38
39	1. Identify the target:
40	- if the user gave a stored note path, use it directly
41	- if the user gave a URL and it has not been ingested yet, run `$tapestry-ingest` first
42	2. IMPORTANT: Change to the project root directory before running the script:
43
44	```bash
45	cd /path/to/your/tapestry/project
46	python synthesis/_scripts/load_context.py \
47	"$ARGUMENTS"
48	```
49
50	Or use the --project-root flag:
51
52	```bash
53	python synthesis/_scripts/load_context.py \
54	--project-root /path/to/your/tapestry/project \
55	"$ARGUMENTS"
56	```
57
58	3. Read the returned handoff payload carefully:
59	- `digest` is the deterministic baseline
60	- `analysis.skill`, `analysis.instructions`, and `analysis.deliverable` describe the intended workflow
61	- `note_text`, `feed_payload`, and `capture_payload` are the factual source materials
62	- Identify the language by reading the content naturally (title, body, comments)
63	4. Ensure the book hierarchy exists:
64
65	```bash
66	cd /path/to/your/tapestry/project
67	python synthesis/_scripts/bootstrap_kb.py
68	```
69
70	Or use the --project-root flag:
71
72	```bash
73	python synthesis/_scripts/bootstrap_kb.py \
74	--project-root /path/to/your/tapestry/project
75	```
76
77	5. Read the knowledge-base governance files:
78	- `synthesis/_kb_rules/_shared-governance.md`
79	- `synthesis/_kb_rules/topic-taxonomy.md`
80	- `synthesis/_kb_rules/chapter-decision-rules.md`
81	6. CRITICAL: Read the existing knowledge base structure thoroughly:
82	- Explore `knowledge-base/books/` to understand existing topics and chapters
83	- Read relevant `index.md` files to understand chapter scope and content
84	- Look for existing chapters where this content naturally fits
85	7. Default to integration - Decide in this priority order:
86	1. FIRST CHOICE: Extend an existing chapter - Integrate the new content into an existing chapter's narrative if it matches the chapter's central concept. Do NOT just append; weave it into the existing structure.
87	2. SECOND CHOICE: Create a new chapter - Only if the content introduces a distinct subdomain that doesn't fit existing chapters
88	3. LAST RESORT: Restructure the topic tree - Only if multiple chapters overlap heavily or the taxonomy has become incoherent
89	8. IMPORTANT: Identify the language of the source content by reading it, then write your synthesis in that same language. Do not translate unless explicitly requested.
90	9. When extending an existing chapter:
91	- Read the full chapter content first
92	- Identify where the new information fits thematically
93	- Integrate it into the existing narrative structure (don't append at the end)
94	- Update section headers if the new content shifts the conceptual balance
95	- Maintain consistent voice and formatting
96	10. When creating a new chapter:
97	- Ensure it represents a recurring domain, not a one-off article
98	- Update the parent `index.md` to register the new chapter
99	- Follow the chapter structure patterns from existing chapters
100	11. Return the synthesis clearly, grounded in the stored artifacts rather than vague recollection.
101
102	## Synthesis Quality Standards
103
104	IMPORTANT: All synthesized content must go through this refinement process, regardless of the source crawler or content type. These standards ensure consistent, high-quality o

People who liked this also viewed

6 picks

Type