From skills
Ingests articles, URLs, videos, and book notes into Obsidian Resources notes after discussing key ideas with the user. Automates note creation with synthesis and linking.
How this skill is triggered — by the user, by Claude, or both
Slash command
/skills:ingestThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Synthesize source material into the vault's knowledge layer. Ingesting without synthesis just
Synthesize source material into the vault's knowledge layer. Ingesting without synthesis just creates noise — the value is the conversation that happens before anything gets written.
Boundaries: use process-inbox for PARA triage of raw inbox notes, and save-note for saving the
current conversation answer as a standalone wiki page.
Rule: always discuss before writing. Never silently file a note.
If the user specified a file or URL, use that directly.
Otherwise, list the inbox:
obsidian files folder="0 - Inbox/" format=json
If multiple items, ask which one to process (or process all in sequence).
obsidian read path="0 - Inbox/[filename]"
For URLs or web content: fetch the content directly.
Surface for conversation — don't skip this step:
qmd query "<key concept>" --json -n 8 2>/dev/null
Present these and wait for Chris to confirm:
3 - Resources/ to targetBased on similarity to existing notes:
Update existing page (score ≥ 0.7 match):
obsidian read path="3 - Resources/<subfolder>/<existing-page>.md"
# Then append a dated section:
obsidian append path="3 - Resources/<subfolder>/<existing-page>.md" \
content="\n## Update — $(date +%Y-%m-%d)\n\n<synthesized content>"
Ambiguous match (score 0.5–0.7): show the candidate pages and ask whether to append, create a distinct page, or cancel. Do not decide silently.
Create new page (score < 0.5, genuinely new territory):
obsidian create path="3 - Resources/<subfolder>/<new-page>.md" content="..."
New page frontmatter:
---
source: claude-memory
created: YYYY-MM-DD
aliases: [<acronyms, alternate names, spelling/casing variants>]
tags: [claude-memory, <topic-tags>]
---
Generate 2–6 aliases: the off-title terms someone would search to find this page (acronyms,
alternate names, "X vs Y" framings). This is what makes the page recall-able from queries that don't
match the title verbatim. Skip only when the title is the sole term anyone would use.
Write in wiki style: neutral, reference-focused, no "I learned that..." framing. This is reference material, not a diary. Target 3–10 pages per source — focus on durable concepts, not summaries of the source itself.
Source type → subfolder mapping:
3 - Resources/Articles/3 - Resources/Tweets/3 - Resources/Videos/3 - Resources/Books/Add to index under the right category heading (Articles / Tweets / Videos / Books /
Concept notes). The CLI has no patch, so the entry can't be inserted under a specific section
directly — ask the user: use the MCP obsidian_patch_content tool (target the heading,
operation: append) or read + create ... overwrite. Entry format:
- **<Title>** ($(date +%Y-%m-%d)) — [[<stem>]] (<path>) · from <hostname>. _<summary>_
Append to log (chronological — append is fine):
obsidian append path="3 - Resources/log.md" content="\n## $(date +%Y-%m-%d)\ningest | <title>"
After confirming the write succeeded:
obsidian move path="0 - Inbox/[filename]" \
to="3 - Resources/[Type]/[filename]"
Never delete inbox items — always move to the appropriate Resources subfolder.
process-inbox for PARA triagesave-note| Priority | Load when | Reference |
|---|---|---|
| 1 — High | Creating or linking wiki pages — block refs, aliases, evergreen structure | references/advanced-workflows.md |
| 2 — Medium | User wants Dataview queries or dynamic MOC views inside a note | references/dataview-patterns.md |
| 3 — Medium | Creating a MOC or deciding MOC vs standalone note | references/moc-advanced.md |
npx claudepluginhub kriscard/skillsIngests external materials as source notes into a project-scoped Obsidian knowledge base under structured source directories. Useful when adding papers, web pages, docs, data, interviews, or other references.
Ingests sources (files, URLs, batch) into an Obsidian vault: extracts entities/concepts, creates/updates wiki pages with cross-references, and logs operations.
Builds and maintains a self-organizing Obsidian wiki vault with AI ingestion, querying, linting, and autonomous research. Knowledge compounds with every ingest. Supports multi-agent and session memory.