defuddle

Name: defuddle
Author: AgriciDaniel

306installs1.1kforks

How to install defuddle?

agricidaniel/claude-obsidian/defuddle

$npx -y skills add AgriciDaniel/claude-obsidian --skill defuddle

Installs into the current project.

Summary

Strip clutter from web pages before ingesting into the wiki. Removes ads, navigation, headers, footers, and boilerplate: leaving clean readable markdown that saves 40-60% tokens. Triggers on: defuddle, clean this page, strip this url, fetch and clean, clean web content before ing

Files · 1

View on GitHub

SKILL.md

1	# defuddle: Web Page Cleaner
2
3	Defuddle extracts the meaningful content from a web page and drops everything else: ads, cookie banners, nav bars, related articles, footers, social sharing buttons. What remains is the article body as clean markdown.
4
5	Use this before any URL ingestion. It is optional but strongly recommended. It cuts token usage by 40-60% on typical web articles and produces cleaner wiki pages.
6
7	Substrate note (v1.7+): Unlike `obsidian-markdown` / `obsidian-bases` / `json-canvas` (where we defer to kepano/obsidian-skills as upstream), the `defuddle` skill is original to claude-obsidian — kepano's marketplace does not ship a defuddle skill. This is the canonical version. The underlying `defuddle-cli` is independent of either marketplace and lives at [github.com/kepano/defuddle](https://github.com/kepano/defuddle).
8
9	---
10
11	## Install
12
13	```bash
14	npm install -g defuddle-cli
15	```
16
17	Verify: `defuddle --version`
18
19	---
20
21	## Usage
22
23	### Clean a URL directly
24	```bash
25	defuddle https://example.com/article
26	```
27	Outputs clean markdown to stdout.
28
29	### Save to .raw/
30	```bash
31	defuddle https://example.com/article > .raw/articles/article-slug-$(date +%Y-%m-%d).md
32	```
33
34	### Add frontmatter header after saving
35	After running defuddle, prepend the source URL and fetch date:
36	```bash
37	SLUG="article-slug-$(date +%Y-%m-%d)"
38	{ echo "---"; echo "source_url: https://example.com/article"; echo "fetched: $(date +%Y-%m-%d)"; echo "---"; echo ""; defuddle https://example.com/article; } > .raw/articles/$SLUG.md
39	```
40
41	### Clean a local HTML file
42	```bash
43	defuddle page.html
44	```
45
46	---
47
48	## When to Use
49
50	Use defuddle when:
51	- Ingesting a news article, blog post, or documentation page from a URL
52	- The page has a lot of surrounding content (most web pages do)
53	- You want to stay within token budget on a long article
54
55	Skip defuddle when:
56	- The source is already a clean markdown or PDF file
57	- The page is a dashboard, app, or structured data (defuddle expects article-style content)
58	- defuddle is not installed and the article is short enough to process raw
59
60	---
61
62	## Fallback
63
64	If defuddle is not installed, check:
65
66	```bash
67	which defuddle 2>/dev/null \|\| echo "not installed"
68	```
69
70	If not installed: use WebFetch directly. The content will be less clean but still workable.
71
72	---
73
74	## Integration with /wiki-ingest
75
76	The `/wiki-ingest` skill checks for defuddle automatically when a URL is passed. You do not need to run defuddle manually before ingesting a URL. The ingest skill will call it if available.
77
78	To manually clean a page and save before ingesting:
79	1. Run the save command above
80	2. Then: `ingest .raw/articles/[slug].md`
81
82	---
83
84	## How to think (10-principle mapping)
85
86	When working on this skill, apply the 10-principle loop. See [`skills/think/SKILL.md`](../think/SKILL.md) for the canonical framework.
87
88	\| # \| Principle \| Application here \|
89	\|---\|-----------\|-------------------\|
90	\| 1 \| OBSERVE (ext) \| Which URL? What's actually on the page? Don't assume the title matches the content. \|
91	\| 2 \| OBSERVE (int) \| Am I assuming the page has the content the user expects? Verify before extracting. \|
92	\| 3 \| LISTEN \| Did the user say "the article" (main content only) or "the link" (everything visible)? \|
93	\| 4 \| THINK \| Strip boilerplate, preserve structure, capture metadata. Quote URLs in shell to avoid injection. \|
94	\| 5 \| CONNECT (lat) \| How does this domain typically render? Some sites mangle defuddle's heuristics; track those. \|
95	\| 6 \| CONNECT (sys) \| Shells out to defuddle-cli (kepano); output lands in `.raw/` for wiki-ingest pickup. \|
96	\| 7 \| FEEL \| Clean markdown that reads like the original, not boilerplate residue. \|
97	\| 8 \| ACCEPT \| Some pages don't extract well. Flag and move on; don't force when the heuristic loses. \|
98	\| 9 \| CREATE \| Markdown to stdout, redirected to `.raw/articles/<slug>-<date>.md`. \|
99	\| 10 \| GROW \| Extraction failures suggest defuddle-cli upgrade or alternative extractor — track them as backlog. \|

AgriciDanielPublisher · 206 listings

Preview

AgriciDaniel/claude-obsidian

# defuddle: Web Page Cleaner

Defuddle extracts the meaningful content from a web page and drops everything else: ads, cookie banners, nav bars, related articles, footers, social sharing but

Use this before any URL ingestion. It is optional but strongly recommended. It cuts token usage by 40-60% on typical web articles and produces cleaner wiki page

**Substrate note (v1.7+)**: Unlike `obsidian-markdown` / `obsidian-bases` / `json-canvas` (where we defer to kepano/obsidian-skills as upstream), the `defuddle`

RepoAgriciDaniel/claude-obsidian

LicenseMIT

TypeSkills

CategoryProductivity

UpdatedMay 2026

Repo stars9.8k

First seenJul 22, 2026

People who liked this also viewed

6 picks

Type

defuddle

306installs1.1kforks

View on GitHub

How to install defuddle?

agricidaniel/claude-obsidian/defuddle

$npx -y skills add AgriciDaniel/claude-obsidian --skill defuddle

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# defuddle: Web Page Cleaner
2
3	Defuddle extracts the meaningful content from a web page and drops everything else: ads, cookie banners, nav bars, related articles, footers, social sharing buttons. What remains is the article body as clean markdown.
4
5	Use this before any URL ingestion. It is optional but strongly recommended. It cuts token usage by 40-60% on typical web articles and produces cleaner wiki pages.
6
7	Substrate note (v1.7+): Unlike `obsidian-markdown` / `obsidian-bases` / `json-canvas` (where we defer to kepano/obsidian-skills as upstream), the `defuddle` skill is original to claude-obsidian — kepano's marketplace does not ship a defuddle skill. This is the canonical version. The underlying `defuddle-cli` is independent of either marketplace and lives at [github.com/kepano/defuddle](https://github.com/kepano/defuddle).
8
9	---
10
11	## Install
12
13	```bash
14	npm install -g defuddle-cli
15	```
16
17	Verify: `defuddle --version`
18
19	---
20
21	## Usage
22
23	### Clean a URL directly
24	```bash
25	defuddle https://example.com/article
26	```
27	Outputs clean markdown to stdout.
28
29	### Save to .raw/
30	```bash
31	defuddle https://example.com/article > .raw/articles/article-slug-$(date +%Y-%m-%d).md
32	```
33
34	### Add frontmatter header after saving
35	After running defuddle, prepend the source URL and fetch date:
36	```bash
37	SLUG="article-slug-$(date +%Y-%m-%d)"
38	{ echo "---"; echo "source_url: https://example.com/article"; echo "fetched: $(date +%Y-%m-%d)"; echo "---"; echo ""; defuddle https://example.com/article; } > .raw/articles/$SLUG.md
39	```
40
41	### Clean a local HTML file
42	```bash
43	defuddle page.html
44	```
45
46	---
47
48	## When to Use
49
50	Use defuddle when:
51	- Ingesting a news article, blog post, or documentation page from a URL
52	- The page has a lot of surrounding content (most web pages do)
53	- You want to stay within token budget on a long article
54
55	Skip defuddle when:
56	- The source is already a clean markdown or PDF file
57	- The page is a dashboard, app, or structured data (defuddle expects article-style content)
58	- defuddle is not installed and the article is short enough to process raw
59
60	---
61
62	## Fallback
63
64	If defuddle is not installed, check:
65
66	```bash
67	which defuddle 2>/dev/null \|\| echo "not installed"
68	```
69
70	If not installed: use WebFetch directly. The content will be less clean but still workable.
71
72	---
73
74	## Integration with /wiki-ingest
75
76	The `/wiki-ingest` skill checks for defuddle automatically when a URL is passed. You do not need to run defuddle manually before ingesting a URL. The ingest skill will call it if available.
77
78	To manually clean a page and save before ingesting:
79	1. Run the save command above
80	2. Then: `ingest .raw/articles/[slug].md`
81
82	---
83
84	## How to think (10-principle mapping)
85
86	When working on this skill, apply the 10-principle loop. See [`skills/think/SKILL.md`](../think/SKILL.md) for the canonical framework.
87
88	\| # \| Principle \| Application here \|
89	\|---\|-----------\|-------------------\|
90	\| 1 \| OBSERVE (ext) \| Which URL? What's actually on the page? Don't assume the title matches the content. \|
91	\| 2 \| OBSERVE (int) \| Am I assuming the page has the content the user expects? Verify before extracting. \|
92	\| 3 \| LISTEN \| Did the user say "the article" (main content only) or "the link" (everything visible)? \|
93	\| 4 \| THINK \| Strip boilerplate, preserve structure, capture metadata. Quote URLs in shell to avoid injection. \|
94	\| 5 \| CONNECT (lat) \| How does this domain typically render? Some sites mangle defuddle's heuristics; track those. \|
95	\| 6 \| CONNECT (sys) \| Shells out to defuddle-cli (kepano); output lands in `.raw/` for wiki-ingest pickup. \|
96	\| 7 \| FEEL \| Clean markdown that reads like the original, not boilerplate residue. \|
97	\| 8 \| ACCEPT \| Some pages don't extract well. Flag and move on; don't force when the heuristic loses. \|
98	\| 9 \| CREATE \| Markdown to stdout, redirected to `.raw/articles/<slug>-<date>.md`. \|
99	\| 10 \| GROW \| Extraction failures suggest defuddle-cli upgrade or alternative extractor — track them as backlog. \|

AgriciDanielPublisher · 206 listings

Preview

AgriciDaniel/claude-obsidian

# defuddle: Web Page Cleaner

Defuddle extracts the meaningful content from a web page and drops everything else: ads, cookie banners, nav bars, related articles, footers, social sharing but

Use this before any URL ingestion. It is optional but strongly recommended. It cuts token usage by 40-60% on typical web articles and produces cleaner wiki page

**Substrate note (v1.7+)**: Unlike `obsidian-markdown` / `obsidian-bases` / `json-canvas` (where we defer to kepano/obsidian-skills as upstream), the `defuddle`

RepoAgriciDaniel/claude-obsidian

LicenseMIT

TypeSkills

CategoryProductivity

UpdatedMay 2026

Repo stars9.8k

First seenJul 22, 2026

People who liked this also viewed

6 picks

Type