agentleFS
Sign inStart free
agamaroraagamarora/second-brain/.claude/skills/extract-entities/SKILL.md

extract-entities

Skill2 starsChanged 7 months agoMITView on GitHub

Scan a source document and return the list of entities it mentions, classified by kind (person, product, partner, competitor, concept, organization, decision), with pointers to existing wiki pages. Subskill of /ingest. Does not write; returns structured data.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read source (already passed in).

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Scan the source content you are given. Return a structured list of entities.

Output format

Return a JSON array. No prose, no padding.

[
  {"entity": "Jane Doe", "kind": "person", "existing_page": "wiki/people/Jane-Doe.md"},
  {"entity": "Acme Corp", "kind": "organization", "existing_page": null},
  {"entity": "cold-start problem", "kind": "concept", "existing_page": "wiki/concepts/cold-start-problem.md"}
]

Rules

  • Only real entities. Skip generic nouns, stop-words, and boilerplate.
  • Deduplicate. One entry per unique entity. Merge variants (e.g., "J. Doe" → "Jane Doe" if context makes it clear).
  • Resolve existing pages. For each entity, glob the relevant wiki path and check if a page exists. If yes, return the path. If no, return null.
  • Kinds: person, product (your own products), partner, competitor, concept, organization, decision. If unsure, use concept.
  • Decisions are only entities if the source explicitly states a decision in first person ("we decided X", "agreed to Y"). Otherwise, they are concepts.
  • Slugify entity names for path lookup: lowercase, hyphen-separated for concepts; PascalCase or "First-Last" for people, products, partners, competitors, organizations.

Steps

  1. Read source (already passed in).
  2. Scan for entities across 7 kinds. Aim for coverage without inflation.
  3. For each, build path using the lookup table in /ingest.
  4. Glob the path. Set existing_page to the path if match, else null.
  5. Return the JSON array.

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.

Check your setup, free