recall

GitHub

通过混合搜索检索过往会话记忆与观察结果,提供上下文。适用于用户查询历史决策、代码细节或项目背景时调用,确保信息源自工具而非虚构。

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

Trigger Scenarios

用户询问过去做过的事情 需要历史上下文以辅助当前任务

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

  1. Call memory_smart_search with the user's text as query and limit: 10. Pass project when the user scopes to a specific repo.
  2. Group results by session. Records carry a provenance channel (user, agent, tool, import, shared); when results conflict, prefer user over agent inference, and flag shared records as another teammate's write.
  3. For each observation show its type, title, and narrative.
  4. Lead with the high-signal observations (importance >= 7).
  5. If zero results, suggest 2-3 alternative search terms and stop. Do not guess.

Anti-patterns

WRONG: results are empty, so you write "We probably discussed token expiry last week" from assumption.

RIGHT: "No memories matched that query. Try refresh token, session expiry, or auth rotation."

Checklist

  • Every observation shown came from the tool response.
  • Results grouped by session, high-importance first.
  • Empty results trigger alternative-term suggestions, not invention.
  • No session id or score was paraphrased or rounded.

See also

  • remember: the write side; recall retrieves what it stores.
  • recap, handoff, session-history: session-scoped views of the same data.
  • memory-discipline: when to run this search unprompted.

Troubleshooting

See ../_shared/TROUBLESHOOTING.md if memory_smart_search is not available.

Version History

  • 2d38daf Current 2026-08-19 18:52

    新增记录来源通道(user/agent/tool等)的处理逻辑及冲突偏好说明;增强空结果时的替代词建议指引。

  • a8e7d19 2026-07-24 11:39

Same Skill Collection

plugin/skills/agentmemory-architecture/SKILL.md
plugin/skills/agentmemory-config/SKILL.md
plugin/skills/agentmemory-hooks/SKILL.md
plugin/skills/agentmemory-mcp-tools/SKILL.md
plugin/skills/agentmemory-rest-api/SKILL.md
plugin/skills/commit-context/SKILL.md
plugin/skills/commit-history/SKILL.md
plugin/skills/forget/SKILL.md
plugin/skills/handoff/SKILL.md
plugin/skills/lesson/SKILL.md
plugin/skills/memory-discipline/SKILL.md
plugin/skills/recap/SKILL.md
plugin/skills/remember/SKILL.md
plugin/skills/session-history/SKILL.md
plugin/skills/write-agentmemory-skill/SKILL.md
plugin/skills/agentmemory-agents/SKILL.md

Metadata

Files
0
Version
2d38daf
Hash
430a2527
Indexed
2026-07-24 11:39

- 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-22 10:30
浙ICP备14020137号-1 $방문자$