agentleFS
Sign inStart free
PthahnixPthahnix/De-Anthropocentric-Research-Engine/skills/canonicalize-entity/SKILL.md

canonicalize-entity

Skill504 starsChanged 49 days agoApache-2.0View on GitHub

Resolve aliases and near-duplicates into canonical entities while preserving provenance and rejecting false merges; entity schema is configurable.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search for near-duplicates and compare definitions, identifiers, and provenance.

    line 23
  2. Very specific:

    If canonical entities are stable enough to compare against the target domain, consider map-coverage-space as the next tactic.

    line 27
  3. Distinctive:

    Before merging aliases, verify pages refer to the same concept rather than merely related concepts.

    line 39

≈ “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

canonicalize-entity

Purpose

Resolve aliases and near-duplicates into canonical entities while preserving provenance and rejecting false merges.

Input contract

required: [raw_entities, entity_schema, alias_evidence]
optional: [synonym_dictionary, organization_relationships, graph_edges, canonicalization_policy]
constraints: [the entity schema is explicit; merge requires semantic identity evidence; preserve provenance and redirect relationships]

Procedure

  1. Normalize names, identifiers, and aliases under the caller-supplied entity schema.
  2. Search for near-duplicates and compare definitions, identifiers, and provenance.
  3. Merge only semantically identical entities into a canonical record and redirect dependent edges.
  4. Preserve rejected-merge pairs and rationale, then return the canonicalized register.

If canonical entities are stable enough to compare against the target domain, consider map-coverage-space as the next tactic.

Output contract

produces: [canonical_entities, alias_map, merge_decisions, redirected_edges, rejected_merges]
delta_fields: [findings, evidence_updates, decisions, uncertainties]

Quality gates

  • Preserve the source merge-candidates gate: scan at least 10 concepts, or all concepts if fewer than 10 exist; a candidate score >7.0 is a merge flag, not proof.
  • Before merging aliases, verify pages refer to the same concept rather than merely related concepts; retain inline links and edge redirects where applicable.
  • Assignee normalization preserves parent, subsidiary, and acquired-entity relationships rather than collapsing organizations into one name.

Parameterization

The caller must provide the entity type and schema, canonical naming policy, alias/synonym evidence, merge confidence rule, graph-edge policy, and whether the task concerns concepts, assignees, or another entity class.

Failure and counterexamples

Reject merges without semantic identity evidence, threshold-only matches, or records that lose provenance or dependent edges.

Provenance map

  • resolved: knowledge-structuring/merge-candidates
  • resolved: knowledge-structuring/alias-resolution
  • resolved: knowledge-acquisition/assignee-normalization
  • intermediate: Pass3/merge-near-duplicate-concepts
  • intermediate: Pass3/normalize-assignee
  • intermediate: Pass4/map-field-taxonomy

Verbatim source criteria excerpts

  • merge-candidates line 18: If search returns another concept with score > 7.0, flag as merge candidate.
  • merge-candidates line 25: Must scan at least 10 concepts (or all concepts if fewer than 10 exist).
  • alias-resolution line 29: Before merging, verify the pages truly refer to the same concept (not related but distinct concepts).

Preserved source criteria ledger

sourcephysical linekindsource criterion
knowledge-structuring/merge-candidates22numericScan at least 10 concepts, or all if fewer than 10; score >7.0 flags a merge candidate.
knowledge-structuring/alias-resolution28gateVerify semantic identity before merging; related-but-distinct concepts must not merge.

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