一键导入
recall
Search memories and decisions to answer questions about past learnings, choices, and context
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Search memories and decisions to answer questions about past learnings, choices, and context
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | recall |
| description | Search memories and decisions to answer questions about past learnings, choices, and context |
| triggers | ["what did we","what was","what is the","do you remember","did we decide","recall","from memory","previously"] |
Recommended model tier: balanced (sonnet) - this skill performs straightforward operations
Search stored memories and decisions to answer questions about past learnings, architectural choices, patterns, and project context.
| Tool | Purpose |
|---|---|
mcp__plugin_aide_aide__memory_search | Full-text search (fuzzy, prefix, substring matching) |
mcp__plugin_aide_aide__memory_list | List memories, optionally filtered by category |
| Tool | Purpose |
|---|---|
mcp__plugin_aide_aide__decision_get | Get specific decision by topic |
mcp__plugin_aide_aide__decision_list | List all decisions |
mcp__plugin_aide_aide__decision_history | Get all versions of a decision |
mcp__plugin_aide_aide__memory_search with relevant keywordsmcp__plugin_aide_aide__decision_get with the topic, or mcp__plugin_aide_aide__decision_listWhen the user asks about previous context:
For architectural/design questions (testing, auth, database, etc.):
mcp__plugin_aide_aide__decision_get with topic (e.g., "testing")mcp__plugin_aide_aide__decision_listFor learnings/patterns/gotchas:
mcp__plugin_aide_aide__memory_search with query (e.g., "ESM imports")When answering:
User: "What testing framework did we decide on?"
→ Use mcp__plugin_aide_aide__decision_get with topic="testing"
→ Answer with the decision and rationale
User: "What was the issue with ESM imports?"
→ Use mcp__plugin_aide_aide__memory_search with query="ESM imports"
→ Answer with the learning
User: "What approach did we take for auth?"
→ Use both mcp__plugin_aide_aide__decision_get (topic="auth") and mcp__plugin_aide_aide__memory_search (query="auth")
→ Combine both sources in answer
If no results found:
mcp__plugin_aide_aide__memory_list to browse all memoriesExplore codebase structure, entry points, tech stack, hotspots, and call graphs
Search code symbols, find function calls, and analyze codebase
Run the instinct parser catalogue against this session's observe events to surface candidate patterns for promotion to memories. Two-pass: gather candidates, judge intent, write proposals.
Parallel agents with SDLC pipeline per story
Inspect a running swarm — show the agent tree, current tools, halts/pauses, and recent task/message activity for the orchestrator's own swarm.
Systematic debugging workflow for tracking down bugs and issues