Apothem vs raw Open-Claw config

Open-Claw reads ~/.openclaw/openclaw.json. Apothem installs shared command and skill cohorts under ~/.openclaw/.apothem/support/skills/ and authors one key there, skills.load.extraDirs, which lists that directory so OpenClaw loads the skills. Its agents.defaults.skills is a name allowlist you own and MCP is a CLI surface, so Apothem authors neither.

StatusCopy Anchor Link

Preview. The Open-Claw adapter targets the current documented config file and extra skill-directory surface. Non-skill cohorts remain Apothem support material.

Effort comparisonCopy Anchor Link

What Apothem managesCopy Anchor Link

The Open-Claw adapter writes openclaw.json, wraps Apothem slash commands as skills, copies Apothem skills into the referenced support directory, and keeps rules, templates, agents, and hook material under the Apothem support subtree. OpenClaw reads skills.load.extraDirs at the lowest precedence of its skill sources, so a skill of the same name in your workspace, ~/.agents/skills, or ~/.openclaw/skills is used instead of the Apothem copy.

Migration pathCopy Anchor Link

1. Run apothem profile init to create the shared profile if you have not yet.
2. Move reusable Open-Claw skills or command prompts into the shared corpus.
3. Run apothem install --harness open-claw to render the native config and support skill directory.
4. Run apothem verify --harness open-claw to confirm the config landed.

Read nextCopy Anchor Link

• Open-Claw adapter reference
• Comparison overview