defuddle · agricidaniel — Claude Code skill: readable Markdown from web pages
Plans Defuddle extraction and retains already available local source files. No network cleaning ships with it — just the plan and the capture.
npx skills add AgriciDaniel/claude-obsidian --skill defuddle -a claude-codeWhat defuddle does
The skill runs in two modes. First, an inert plan for an HTTPS link: it takes the address, drops credentials, fragments and non-public hosts, then reports the normalized host, required network egress, redirect policy and execute: false. Second, a capture of an existing local HTML or Markdown file into the selected vault's inbox/.
No network request happens here. The reason is concrete: the Defuddle CLI follows redirects and enables asynchronous extraction, so even parsing a local HTML file can pull in third-party resources. Consent for the initial URL does not prove every eventual destination stays approved. A configured state means an executable was found without a bundled behavioral verifier — running it just because it turned up is the wrong move.
Capture goes through scripts/claude-obsidian.py: capture plan first, then capture apply with a pinned timestamp and operation ID, and --approved-plan-sha256 plus --apply for the write. Bytes land in create-only .raw/captured/ storage, and a repeated identical payload is a no-op. Cleaning HTML, verifying source metadata and synthesizing pages are separate operations.
What it helps with
- strip page clutter and get readable Markdown from a web page
- build an extraction plan for a URL without a network request
- retain a local HTML or Markdown file in the vault as raw bytes
- prepare a web source for later wiki ingestion
- check which hosts and redirects an extraction would require
Example prompts for the agent
- defuddle, clean this URL and show me the extraction plan
- turn this web page into readable Markdown
- retain the local file
$VAULT/inbox/source.mdin the vault
How to install defuddle
1Skills CLI (Vercel)
npx skills add AgriciDaniel/claude-obsidian --skill defuddle -a claude-code2Manually: put the files in place
~/.claude/skills/defuddle/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/defuddle/
1Skills CLI (Vercel)
npx skills add AgriciDaniel/claude-obsidian --skill defuddle -a codex2Manually: put the files in place
.agents/skills/defuddle/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add AgriciDaniel/claude-obsidian --skill defuddle -a cursor2Manually: put the files in place
.cursor/skills/defuddle/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install AgriciDaniel/claude-obsidian defuddle2Manually: put the files in place
.github/skills/defuddle/SKILL.md1Skills CLI (Vercel)
npx skills add AgriciDaniel/claude-obsidian --skill defuddle -a gemini-cli2Platform CLI
gemini skills install https://github.com/AgriciDaniel/claude-obsidian --path skills/defuddleManually: put the files in place
.devin/skills/defuddle/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add AgriciDaniel/claude-obsidian --skill defuddle -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about defuddle
How do I install defuddle in Claude?
Run npx skills add AgriciDaniel/claude-obsidian --skill defuddle -a claude-code. The skill lands at ~/.claude/skills/defuddle/SKILL.md.
What does defuddle do?
It builds an inert extraction plan for an HTTPS URL and retains already available local files in the vault. It does not perform network cleaning.
Why does URL extraction stop before running?
The Defuddle CLI follows redirects and enables asynchronous extraction, so checking the initial URL cannot guarantee approved destinations. The URL stays queued until an enforcing adapter is verified.
Source text
SKILL.md · MIT
--- name: defuddle description: Plan optional Defuddle extraction and retain already available local source files through reviewed filesystem capture. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion. Network extraction remains unavailable until an enforcing adapter is verified. --- # Defuddle Treat Defuddle as an optional external extractor. This package supports inert URL plans and filesystem capture; it does not ship an enforcing network cleaner. Cleaning, raw capture, and wiki ingestion are separate operations. Resolve the installed product root from this skill's own location, never from the selected vault or process working directory: ```bash PRODUCT_ROOT=/absolute/path/to/installed/claude-obsidian CORE="$PRODUCT_ROOT/scripts/claude-obsidian.py" test -f "$CORE" ``` Every `../wiki/references/` link in this file resolves the same way, relative to this skill's own directory under `$PRODUCT_ROOT`, never relative to the selected vault's `wiki/` directory. Upstream flags may be checked in a separately installed `kepano/obsidian-skills` reference, but do not override this package's privacy and transaction boundary. ## Inert URL plan Accept HTTPS URLs only. Reject credentials, fragments, controls, sensitive query parameters, and non-public hosts or IP addresses. Never interpolate a URL into a shell string. Use one argv element when constructing a plan: ```bash python3 "$CORE" capture external-plan url "HTTPS_URL" python3 "$CORE" contracts --verify --capability defuddle --vault "$VAULT" ``` The plan executes no network request. Report the normalized host, required network egress, redirect policy, optional dependency, and `execute: false`. An `available` state means no executable was found. A `configured` state means an executable was discovered without a bundled behavioral verifier. Identify the manual executable and its reported reason; never run it merely because it was found. Never relabel `configured` as `verified`. ## Why execution stops here The upstream CLI inspected at commit [`556d74e8c8fd68c49912d4b11a4ae9ec04d7b2b5`](https://github.com/kepano/defuddle/tree/556d74e8c8fd68c49912d4b11a4ae9ec04d7b2b5) (checked 2026-10-17) follows redirects and enables asynchronous extraction. Even parsing a local HTML file can request additional resources or third-party fallbacks. Inspecting argv or obtaining consent for the initial URL cannot prove that every eventual destination remains approved. Do not execute the bare CLI against a URL or local HTML under this workflow. Do not silently substitute a browser, fetcher, proxy, cookies, or another runner. A future runnable adapter must enforce approved destinations after DNS and on each redirect, disable uncontrolled async/fallback traffic, constrain proxy behavior, and bound bytes, time, and subprocess output. It must retain original and final locators, exact version, approved hosts, capture hash, and mode. Behavioral tests must prove these limits before execution is offered. Consent for each destination remains required even with an enforcing adapter. Do not install tools or claim cleaning, extraction quality, or token savings. Leave the URL queued, or accept an already available local file. A local file may be retained as bytes without rendering HTML or running its scripts. ## Reviewable filesystem capture When the user asks to retain an existing local HTML or Markdown file, place it in the selected vault's `inbox/` first. Preview and apply the filesystem plan with a pinned timestamp and operation ID: ```bash python3 "$CORE" capture plan --vault "$VAULT" "$VAULT/inbox/source.md" python3 "$CORE" capture apply --vault "$VAULT" "$VAULT/inbox/source.md" \ --generated-at "$GENERATED_AT" --operation-id "$OPERATION_ID" # Set APPROVAL_SHA256 to the reviewed approved_plan_sha256 from the dry run. python3 "$CORE" capture apply --vault "$VAULT" "$VAULT/inbox/source.md" \ --generated-at "$GENERATED_AT" --operation-id "$OPERATION_ID" \ --approved-plan-sha256 "$APPROVAL_SHA256" --apply ``` This preserves source bytes in create-only `.raw/captured/` storage. It does not clean HTML, verify source metadata, or synthesize pages. Inspect the actual result and record extraction limitations. If already cleaned text is supplied, retain its known extractor/version and locator without inventing missing fields. Report the operation ID and exact changed paths. A repeated identical payload is a no-op; never overwrite immutable raw state. Use [operation-transactions.md](../wiki/references/operation-transactions.md) for custom capture drafts. Read or analyze transiently when retention was not requested. Invoke `wiki-ingest` only as a distinct requested operation.
© AgriciDaniel · MIT · AgriciDaniel/claude-obsidian
Similar skills
All skills for Agent setup: memory, context, orchestration →defuddle by other authors comes first.