recall

Agent Skills › rohitg00/agentmemory › recall

recall

GitHub

通过混合搜索检索过往会话中的观察、决策和代码片段。适用于用户询问历史上下文或需要回顾特定主题时的场景，强调基于工具结果呈现，禁止臆造信息。

plugin/skills/recall/SKILL.md rohitg00/agentmemory

Trigger Scenarios

用户明确说 recall 询问 did we ever / have we seen 询问 what did we do about 需要过去会话的上下文

Install

npx skills add rohitg00/agentmemory --skill recall -g -y

More Options

Non-standard path

npx skills add https://github.com/rohitg00/agentmemory/tree/main/plugin/skills/recall -g -y

Use without installing

npx skills use rohitg00/agentmemory@recall

指定 Agent (Claude Code)

npx skills add rohitg00/agentmemory --skill recall -a claude-code -g -y

安装 repo 全部 skill

npx skills add rohitg00/agentmemory --all -g -y

预览 repo 内 skill

npx skills add rohitg00/agentmemory --list

SKILL.md

Frontmatter

{
    "name": "recall",
    "description": "Search agentmemory for past observations, sessions, and learnings about a topic using hybrid BM25 plus vector plus graph search. Use when the user says \"recall\", \"what did we do about\", \"did we ever\", \"have we seen\", or needs context from past sessions.",
    "argument-hint": "[search query]",
    "user-invocable": true
}

The user wants to recall past context about: $ARGUMENTS

Quick start

memory_smart_search { "query": "jwt refresh token rotation", "limit": 10 }

Expected output:

2 results across 2 sessions.
[importance 8] decision · "Rotate refresh tokens on every use" (session 7f3a9c21)
[importance 5] code · "limit.ts counts per-IP" (session b21d004e)

Why

Only surface what the tool returned. Never fabricate an observation, a session id, or an importance score. If nothing comes back, say so.

Workflow

Call memory_smart_search with the user's text as query and limit: 10. Pass project when the user scopes to a specific repo.
Group results by session.
For each observation show its type, title, and narrative.
Lead with the high-signal observations (importance >= 7).
If zero results, suggest 2-3 alternative search terms and stop. Do not guess.