agentleFS
Agents4Academia-AIAgents4Academia-AI/UReKA/.claude/skills/obsidian/SKILL.md

obsidian

Skill9 starsChanged 5 months agoMITView on GitHub

Ingest an Obsidian/markdown note into a structured notes file in notes/

101 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use taskflow-inbox-triage, discord-e2e and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AtomicBot-aiSkill

    taskflow-inbox-triage

    Also in 6 projects that use this

  • molt-botSkill

    discord-e2e

    Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing. Distinguish API and Gateway evidence from manual user interactions.

    Also in 10 projects that use this

  • molt-botSkill

    openclaw-repair-sweep

    Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.

    Also in 10 projects that use this

  • clawdbotSkill

    openclaw-performance

    Performance work in OpenClaw: a slow or heavy flow (latency, CPU, memory, SQL, RPC, renders), writing or reviewing a perf PR, or adding a cache. Count the work, delete waste first, cache last.

    Also in 7 projects that use this

  • clawdbotSkill

    plugin-sdk-impact

    Count Plugin SDK consumers across live ClawHub releases and bundled OpenClaw plugins before deprecation, removal, or behavior changes; supports public release-date filters.

    Also in 7 projects that use this

  • emanueleieloSkill

    sonos

    Control Sonos speakers: discover, play/pause, volume, grouping, favorites, and queue management via sonos CLI.

    Also in 5 projects that use this

  • +2 more from molt-bot

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 4 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 96 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If $ARGUMENTS is empty, ask the user for a file path, then continue.

    line 10
  2. Very specific:

    All output is under notes/ (personal notes, as opposed to objective sources under sources/).

    line 14
  3. Very specific:

    Extract: Read the note at $ARGUMENTS with the Read tool.

    line 21
  4. Distinctive:

    Before writing, verify the envelope:

    line 50
  5. Distinctive:

    If any check fails, fix the envelope before writing.

    line 59
  6. Distinctive:

    Propose: After writing, suggest the user:

    line 66
  7. Very specific:

    Run /retrieve <topic> to find related sources and existing pages.

    line 67
  8. Very specific:

    Run /collate <topic> to synthesise a paper or concept page from this note together with other sources on the same topic.

    line 68

“Common” is measured: kept by at least 6 in 10 of the 96 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ingest an Obsidian note at $ARGUMENTS and produce a structured notes/obsidian_<slug>.md file following the project template.

If $ARGUMENTS is empty, ask the user for a file path, then continue.

Layout

All output is under notes/ (personal notes, as opposed to objective sources under sources/). Template lives at .claude/Templates/note.md. Existing files in notes/ are style references — read one before writing your first output.

Steps

  1. Extract. Read the note at $ARGUMENTS with the Read tool. Identify:
    • The H1 (# ...) line as the title. If absent, fall back to the filename stem with underscores/dashes converted to spaces, in Title Case.
    • [[wikilinks]] and #tags — leave them in place inside the body. The navigator uses [[wikilinks]] as graph edges, so they must be preserved verbatim.
    • Concepts list: collect the target of each [[wikilink]] (the part before | if aliased, trimmed) plus each #tag name (strip the leading #). Dedup at exact-string level, preserve first-occurrence order. This becomes the concepts_mentioned field.
  2. Format. Fill in the obsidian schema below. This skill extends the shared .claude/Templates/note.md with source_links (a list) and concepts_mentioned; the schema here is authoritative for obsidian notes.

    • type: obsidian_note
    • title: from Step 1
    • source_links: a YAML block list containing $ARGUMENTS verbatim as its single entry:

      source_links:
        - $ARGUMENTS
    • concepts_mentioned: an inline YAML list of the concepts collected in Step 1 (e.g. [chain-of-thought, tool-use, transformers]). Use [] if the note has no [[wikilinks]] or #tags.
    • ## Content: the full note text. Preserve the author's wording, headings, lists, code blocks, emphasis, [[wikilinks]], and #tags as faithfully as possible. Do not summarise unless the note is very long.

    Before writing, verify the envelope:

    • Starts with --- on line 1; has a closing --- delimiter.
    • Contains exactly these four frontmatter keys: type, title, source_links, concepts_mentioned.
    • type is the literal string obsidian_note.
    • source_links is a YAML list whose only entry equals $ARGUMENTS verbatim.
    • concepts_mentioned is a YAML list (possibly empty).
    • Body contains a non-empty ## Content section.

    If any check fails, fix the envelope before writing.

  3. Write. Slugify the title to snake_case (lowercase, spaces/dashes → underscores, drop non-alphanumeric characters). Write to notes/obsidian_<slug>.md with the Write tool. If the file already exists, ask the user before overwriting.
  4. Propose. After writing, suggest the user:
    • Run /retrieve <topic> to find related sources and existing pages.
    • Run /collate <topic> to synthesise a paper or concept page from this note together with other sources on the same topic.

Wrap up

Report: output file path, the title and wikilinks/tags preserved, and anything skipped (one-line reason each).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.