Skip to content
SkillModel-led2,880 tokens in use

wiki-digest

Writes a day, week or month digest of what an Obsidian wiki learned: new and updated pages, rising tags, notable links, open threads and pages to re-read.

3,792 stars on the repository MIT LicenseAr9av/obsidian-wiki · skills/wiki-digest
pip install obsidian-wiki
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing wiki-digest costs

43tokens idle
2,880tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter8/15
  • Structure25/25
  • Examples12/15
  • Output15/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 212

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community60
  • Maturity28
  • Momentum40

wiki-digest turns recent vault activity into a readable review. It reads the log and the hot context file, finds pages created or updated in the chosen period, and writes headlines that state the insight gained.

The digest shows new pages, notable updates, emerging tags, cross-category connections, open threads and recommended re-reads. It prints in chat by default and saves to the journal folder when asked.

What You Get

  • A digest with a headlines section that synthesizes the knowledge gained in the period
  • Tables of new pages and notable updates with one-line summaries
  • Top emerging tags, including vocabulary not yet in the taxonomy
  • Three to five notable cross-category connections, each with a reason
  • Open threads: drafts, ambiguous-claim counts, unstaged notes in the raw folder
  • Two or three recommended re-reads with concrete reasons
  • An optional saved journal page and a log entry

Common Use Cases

  • Running a weekly review of what your knowledge base gained
  • Seeing which new tags and topics appeared after a burst of ingestion
  • Finding older foundational pages worth revisiting given new material

What Makes It Unique

It summarizes knowledge, and leaves sources to the sibling wiki-status, which reports what is pending ingestion. Links are scored by how rarely two categories connect and whether the target is a hub, and pages tagged as private are left out of tables and counted separately. The only writes are an optional journal page and a log line, so existing pages are never modified.

Under The Hood

The skill is instructions for the agent. It resolves the vault path from the shared config, globs markdown files and reads their frontmatter and links. It writes only a log line and, on request, a journal page plus an index entry. When a QMD collection is configured it runs the qmd command line tool to refresh the search index after writing. It does not fetch web pages or call remote APIs.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers