autoresearch
Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user…
Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.
$ npx -y skills add AgriciDaniel/claude-obsidian --skill defuddle --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/defuddleContext preview
The summary Claude sees to decide when to auto-load this skill.
Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.
name: defuddle description: Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.
Treat Defuddle as an optional external extractor, not an internal capability. 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:
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 `$PRODUCT_ROOT`, never relative to the selected vault's `wiki/` directory.
If a separately installed `kepano/obsidian-skills` `defuddle` skill is available, prefer it for current CLI flags. Retain the privacy, consent, and transaction rules in this skill.
addresses, control characters, and sensitive query parameters.
approved.
access requires explicit consent in the current request or a separate confirmation.
another network fetcher.
actual output.
Create an inert URL plan. This validates the URL and executes no network call:
python3 "$CORE" capture external-plan url "HTTPS_URL"
Report the normalized host, network egress, redirect policy, optional external dependency, and `execute: false`. Then inspect whether this package can find a configured Defuddle executable:
python3 "$CORE" contracts --verify --capability defuddle --vault VAULT
An `available` state means no executable was found; stop with the inert plan. A `configured` state means the executable was discovered, but this package has no bundled behavioral verifier for it. Show that state and reason, identify the resolved executable path, and require manual review of its provenance, version, and exact argv before execution. Never relabel `configured` as `verified`.
When unavailable or when manual review is declined, offer these honest fallbacks: let the user install/configure an external runner, accept a local HTML or Markdown file in `inbox/`, or leave the URL queued for later. Do not claim that content was cleaned, captured, or ingested.
After network consent, configured-state detection, and manual executable review, invoke the approved executable with an argv equivalent to:
defuddle parse HTTPS_URL --md
Capture bounded stdout in a temporary draft outside shared vault state. Fail closed on a non-zero exit, empty output, unexpected binary output, an unapproved redirect, or a response that is clearly an authentication/error page. Preserve headings, links, code fences, tables, quotations, and source wording; do not invent missing content.
Preview the cleaned Markdown and report extraction limitations. If the user asked only to read or analyze it, keep the result transient.
When the user asks to retain the cleaned source:
1. Resolve the user vault. 2. Hash the exact cleaned bytes with SHA-256. 3. Draft a new immutable payload such as `.raw/captured/<sha256>.md` and, when provenance metadata is needed, a new create-only sidecar with the normalized URL, retrieval date, extractor name and version, and content hash. 4. Use `expected_hashes: null` and `mode: create`. If that content-addressed payload already exists with the same bytes, report a no-op; never overwrite it. 5. Build, inspect, and apply one `claude-obsidian.transaction.v1` capture bundle as described in [operation-transactions.md](../wiki/references/operation-transactions.md).
Do not create wiki pages, update indexes, assess claims, or mark the source as ingested. Invoke `wiki-ingest` as a distinct requested operation if the user wants the captured payload incorporated into the knowledge base.
Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, personal knowledge management (PKM), and an open-source Notion alternative. Based on Karpathy's LLM Wiki pattern.
Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user…
Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones,…
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases,…
Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and…
Save a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks…
Apply the Fable-derived 10-stage OBSERVE, OBSERVE, LISTEN, THINK, CONNECT, CONNECT, FEEL, ACCEPT, CREATE, GROW loop to consequential or ambiguous reasoning and…