AugmentClaude

Remnic Entities

Look up facts and relationships for people, projects, and concepts in a knowledge graph.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.

    This copies the whole skill folder into ~/.claude/skills/remnic-entities-joshuaswarren/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Browse entities in the Remnic knowledge graph and surface their facts and relationships. Trigger phrases include "tell me about the entity", "look up", "what do we know about".

What this skill does

When to use

Use when the user names a specific project, person, service, or concept and asks what is known about it. Entities are the structured graph view of memory — facts and relationships rather than free text.

Triggers:

  • "Tell me about the entity …"
  • "Look up …"
  • /remnic:entities <name> slash command invocation.
  • Any reference to a named thing that could have linked facts.

Inputs

  • name (required) — canonical entity name, ideally as the user wrote it.
  • Optional: entity type hint (project, person, service, tool).

Procedure

  1. Extract the entity name from the user's message. Preserve capitalization.
  2. Call remnic_entity_get with that name.
  3. If found, present facts, relationships, and a last-updated timestamp in a compact block.
  4. If missing, say so and offer to create it via remnic-remember with the user's permission.
  5. If multiple candidates match, list them briefly and ask which the user meant.

Efficiency plan

  • Do not fetch speculatively for every proper noun — only when the user asks or the task depends on it.
  • Cache the entity payload within the current turn.
  • Pair with remnic-recall when unstructured context would round out the view.

Pitfalls and fixes

  • Pitfall: Guessing entity names. Fix: Use the user's wording; disambiguate rather than inventing.
  • Pitfall: Dumping the full payload. Fix: Summarize into facts, relations, last-updated.
  • Pitfall: Treating missing entities as a bug. Fix: Missing just means the graph has not captured it yet.

Verification checklist

  • remnic_entity_get was called with a user-supplied or user-confirmed name.
  • Output shows facts, relationships, and timestamps in a compact view.
  • Missing entities are acknowledged plainly with an offer to create.
  • Canonical remnic_entity_get was used over legacy engram_entity_get.

Tool names: canonical name is remnic_entity_get. The legacy engram_entity_get alias remains accepted during v1.x.

Related skills