How do I install the Openclaw Mem Graph skill?

Run npx skillmds@latest add phenomenoner/openclaw-mem-graph in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Openclaw Mem Graph skill do?

Operate graph readiness, topology lookup, synthesis-aware routing, and symbolic evidence canvases. Use for project ownership, impact, dependency, or idea-to-project questions. It is listed under Coding & Dev Tools on SkillMD.

Is Openclaw Mem Graph safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Openclaw Mem Graph?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Openclaw Mem Graph free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Openclaw Mem Graph?

phenomenoner (@phenomenoner) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Openclaw Mem Graph by phenomenoner — Agent Skill

Name: Openclaw Mem Graph
Rating: 4.666666666666667 (3 reviews)
Author: phenomenoner

File contents

Graph Governance

Workflow

Check readiness before using graph output as a router.
Query or match the narrowest scope.
Preserve synthesis coverage and raw-reference receipts.
Fail open to docs, recall, or repository inspection when graph evidence is stale or unavailable.

openclaw-mem graph readiness --json
openclaw-mem graph query subgraph <node-id> --json
openclaw-mem graph match <query> --json
openclaw-mem route auto <query> --json
openclaw-mem routing resolve <query> --workspace-root <workspace> --json

Synthesis cards are derived artifacts, not durable memory. Require preferredCardRefs and coveredRawRefs when one card replaces multiple raw hits. Use graph synth recommend before explicit refresh.

Build a symbolic canvas only as a compact evidence map. Duplicate IDs fail closed; missing refs remain warnings; the canvas does not write durable memory.

Verify

openclaw-mem graph readiness --json
openclaw-mem route auto <query> --json
python -m pytest tests/test_graph_match_cli.py tests/test_autonomous_default_routing_cli.py -q

Frequently asked questions

Openclaw Mem Graph