openclaw-skills

Resolves and loads the canonical orama-system skill from a verified repository path.

Updated Mar 22, 2026
One-click install
npx skills add https://github.com/diazMelgarejo/orama-system --skill openclaw-skills-diazmelgarejo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openclaw-skills
Source: https://github.com/diazMelgarejo/orama-system/tree/main/.agents/skills/openclaw-skills
Command: npx skills add https://github.com/diazMelgarejo/orama-system --skill openclaw-skills-diazmelgarejo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It prevents agents from loading stale or wrong copies of a skill by acting as a thin, read-only wrapper that locates the canonical orama-system repository and delegates to its authoritative SKILL.md. ## Core Features & Use Cases - Canonical Path Resolution: Searches environment variables, the current git repository root, and sibling checkouts to find the verified canonical skill file. - Read-Only Loading: Reads and follows the canonical SKILL.md without fetching, pulling, installing, or modifying anything during load. - Explicit Refresh Workflow: Supports a separately authorized git fetch and fast-forward pull only when the user explicitly requests a refresh. - Use Case: An agent in any workspace needs the openclaw-skills instructions; the wrapper locates the sibling orama-system checkout and loads its canonical skill card without duplicating content. ## Quick Start Ask the agent to load the openclaw-skills skill so it resolves the canonical orama-system repository and follows its SKILL.md.

Frequently Asked Questions about openclaw-skills

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I load the canonical openclaw-skills skill?

The wrapper resolves the canonical repository root by checking ORAMA_SYSTEM_ROOT or ORAMA_SYSTEM_PATH, then the current git toplevel, then sibling checkouts at depth two. Once found, it reads bin/orama-system/skills/openclaw-skills/SKILL.md and follows it.

What is a thin wrapper skill in a multi-repo setup?

A thin wrapper skill contains no operational logic itself and instead points to a canonical skill file in another repository. It keeps one authoritative source of instructions while letting agents in any workspace discover and load it.

Does loading this skill modify the canonical repository?

No, loading is strictly read-only and marker-verified. Fetching, pulling, pruning, installing, or modifying anything is forbidden during load; synchronization only happens as a separate, explicitly authorized refresh action.

What happens if the canonical skill path cannot be resolved?

If no candidate path contains the canonical SKILL.md file, the wrapper reports the skill as unavailable. It never guesses, hardcodes a workstation path, or falls back to a different repository's copy.

How do I refresh the canonical skill repository safely?

Run git fetch with prune, check status, and pull with --ff-only only when the worktree is clean and the branch tracks origin. If the worktree is dirty or fast-forward is impossible, report the drift instead of overwriting local work.