mirror of
https://github.com/outbackdingo/optimclaw.git
synced 2026-08-25 07:20:19 +00:00
Full rename of all identifiers, filenames, and references: ironclaw → optimclaw IronClaw → OptimClaw IRONCLAW → OPTIMCLAW ironclaw_common → optimclaw_common ironclaw_safety → optimclaw_safety Upstream: nearai/ironclaw
1.8 KiB
1.8 KiB
paths
| paths | ||
|---|---|---|
|
Skills System
SKILL.md files extend the agent's prompt with domain-specific instructions. Each skill is a YAML frontmatter block (metadata, activation criteria, required tools) followed by a markdown body injected into the LLM context.
Trust Model
| Trust Level | Source | Tool Access |
|---|---|---|
| Trusted | User-placed in ~/.optimclaw/skills/ or workspace skills/ |
All tools available to the agent |
| Installed | Downloaded from ClawHub registry (~/.optimclaw/installed_skills/) |
Read-only tools only (no shell, file write, HTTP) |
SKILL.md Format
---
name: my-skill
version: 0.1.0
description: Does something useful
activation:
patterns:
- "deploy to.*production"
keywords:
- "deployment"
exclude_keywords:
- "rollback"
tags:
- "devops"
max_context_tokens: 2000
metadata:
openclaw:
requires:
bins: [docker, kubectl]
env: [KUBECONFIG]
---
# Skill instructions here...
Selection Pipeline
- Gating -- Check binary/env/config requirements; skip skills whose prerequisites are missing
- Scoring -- Deterministic scoring: keywords (10/5 pts, cap 30) + patterns (20 pts, cap 40) + tags (3 pts, cap 15).
exclude_keywordsveto (score = 0 if any present) - Budget -- Select top-scoring skills within
SKILLS_MAX_TOKENSprompt budget - Attenuation -- Minimum trust across active skills determines tool ceiling; installed skills lose dangerous tools
Skill Tools
skill_list-- List all discovered skills with trust level and statusskill_search-- Search ClawHub registry for available skillsskill_install-- Download and install a skill from ClawHubskill_remove-- Remove an installed skill