Skip to content
Agent Memory
Skill

/remnic-recall

Search Remnic memories by natural-language query. Trigger phrases include "what do you remember about", "recall anything on", "have we discussed".

BOOST
From plugin
remnic
2256 skills1 agent1 MCP
Install
$ npx -y skills add joshuaswarren/remnic --skill remnic-recall --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/remnic-recall

Context preview

The summary Claude sees to decide when to auto-load this skill.

Search Remnic memories by natural-language query. Trigger phrases include "what do you remember about", "recall anything on", "have we discussed".

SKILL.md

remnic-recall.SKILL.md
name: remnic-recall
description: Search Remnic memories by natural-language query. Trigger phrases include "what do you remember about", "recall anything on", "have we discussed".
allowed-tools:
  - remnic_recall

When to use

Use when the user or the current task needs prior context from Remnic. This is the default first step for any non-trivial Claude Code turn that could benefit from memory.

Triggers:

  • "What do you remember about …"
  • "Have we talked about …"
  • `/remnic:recall <query>` slash command invocation.
  • A new task begins and the agent wants background.

Inputs

  • `query` (required) — natural-language question or topic string.
  • Optional: caller-supplied budget hint (brief, deep).

Procedure

1. Build a concise natural-language query from the user's message. Prefer the user's own wording. 2. Call `remnic_recall` with that query; request 3–8 results unless the caller specified otherwise. 3. Filter results for topical relevance. 4. Present 1–5 bullet points summarizing the relevant memories, attributed when useful. 5. If nothing relevant came back, say so plainly and suggest `remnic-remember` if there is something worth storing now.

Efficiency plan

  • One broad recall beats several narrow ones.
  • Reuse recall results within the same turn — do not re-query the same topic.
  • Skip recall for trivially local tasks.

Pitfalls and fixes

  • **Pitfall:** Quoting irrelevant recalls just because they came back. **Fix:** Filter for relevance before surfacing.
  • **Pitfall:** Over-narrowing the query. **Fix:** Start broad; refine only when the first pass was noisy.
  • **Pitfall:** Showing raw memory payloads. **Fix:** Summarize in the user's own terms.

Verification checklist

  • [ ] `remnic_recall` was called with a natural-language query.
  • [ ] Results were filtered for relevance before being shown.
  • [ ] Summary is ≤ 5 bullets unless the user asked for more.
  • [ ] Canonical `remnic_recall` was used over legacy `engram_recall`.

> Tool names: canonical name is `remnic_recall`. The legacy `engram_recall` alias remains accepted during v1.x.

Read more
Ships withremnic

Open-source, local-first memory and context for AI agents. One memory store, every agent. Website: remnic.ai - guide library, comparisons, benchmarks, and changelog. Your files, your machine.

Get the whole plugin

Other skills on remnic.