dbengoa42-star/edgeclaw/memory-orchestrator
Claude Code and agent skill by dbengoa42-star/edgeclaw
- community
Checking that the SKILL.md file is still in the repository.
Orchestrate ClawXMemory retrieval using memory_search first and memory_get for exact record reads. Use when the user asks for historical context, project progress, timeline, or profile facts.
Install
npx vskill@latest install dbengoa42-star/edgeclaw/memory-orchestratorSKILL.md
The same SKILL.md was published earlier as dbengoa42-star/edgeclaw/memory-orchestrator.
Memory Orchestrator
Use this skill when the task depends on conversation history, project status, timeline, or user profile facts.
Primary Path (Tool-first)
- If the user is asking what memory exists or what ClawXMemory currently remembers, use
memory_overviewormemory_listinstead of retrieval. - Otherwise call
memory_searchwith the user's question. - Read
intent,enoughAt, returnedcontext, andrefs. - If the returned context is sufficient, answer from it directly.
- If you need exact verification, call
memory_getwith the smallest relevant id set fromrefs. - If
memory_searchreturns weak or empty evidence, say so clearly and ask a targeted follow-up question.
Fallback Strategy
- Time-oriented question: prefer
refs.l2entries whoselevelisl2_time, then verify withmemory_get({ level: "l2_time", ids }). - Project-oriented question: prefer
refs.l2entries whoselevelisl2_project, then verify withmemory_get({ level: "l2_project", ids }). - Fact/profile question: start with
memory_search, then inspect only the most relevantl1orl0ids if the answer needs precise support.
Tool Usage Notes
- Prefer concise query strings; avoid copying the entire user prompt unless necessary.
- Keep
limitsmall, usually4to8, unless the user asks for exhaustive history. - For browse-only questions, use
memory_overview/memory_listrather thanmemory_search. - Use
memory_getonly aftermemory_searchhas given you the ids worth reading. - If evidence conflicts, prefer the newest verified
l1/l0record and say that the history appears inconsistent.
Minimal Example
Example User Requests
- "What do you remember?"
Use memory_overview or memory_list, not memory_search.
- "What project memory entries exist?"
Use memory_overview or memory_list, not memory_search.
- "What is the latest progress on this project?"
Start with memory_search, then verify the most relevant l2_project entry with memory_get if needed.
Guardrails
- Do not fabricate details not supported by retrieved memory.
- Prefer newer verified entries over older ones when there is conflict.
- Do not call
memory_getwith guessed ids. - If retrieval is empty, state uncertainty clearly and ask a targeted follow-up question.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingextensions/openbmb-clawxmemory/agent-skills/memory-orchestrator/SKILL.md
Popularity
- 7-day trend score
- 0
Refreshed 10 Sep 2026, 2 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/dbengoa42-star/edgeclaw/memory-orchestrator)