skills.rest
kimprobably
kimprobablyCOMMUNITY
Explore all skills by this author →
GitHub

maestro-skill-governance

Govern Hermes skill promotion with diffs, scenario sets, and approval artifacts.

Updated May 13, 2026
Search Tags:#workflow routing#skill governance#safety validation#approval gating#promptfoo evaluation#evidence-based change control#self-learning policy
One-click install
npx skills add https://github.com/kimprobably/maestro-os --skill maestro-skill-governance
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: maestro-skill-governance
Source: https://github.com/kimprobably/maestro-os/tree/main/hermes/distribution/maestro-operator/skills/maestro-skill-governance
Command: npx skills add https://github.com/kimprobably/maestro-os --skill maestro-skill-governance

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps Hermes decide how to record, evolve, or generate “trusted” procedures while preventing unverified self-learning from accidentally becoming evidence-grade guidance for important or customer-facing work.

Core Features & Use Cases

  • Skill vs Fabro routing guidance: Distinguishes judgment-heavy, repeatable habits from deterministic, approval-gated execution flows.
  • Generated skill governance: Requires diffs/proposals, scenario coverage, deterministic safety checks, and rubric-based evaluation before promotion.
  • Curated-skill protection: Prevents background improvement from rewriting curated Maestro skills without an explicit, evidence-backed promotion path.

Quick Start

Use maestro-skill-governance when you need Hermes to decide whether a candidate procedure belongs as a Hermes skill draft, must route through Fabro for deterministic/approved behavior, or needs an explicit promotion gate.

Frequently Asked Questions about maestro-skill-governance

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

FAQPage Schema
How do I prevent unverified self-learning procedures from becoming trusted skills?▼

Skill governance prevents unverified self-learning by requiring proposal diffs, scenario sets, deterministic forbidden-behavior checks, and optional Promptfoo rubric evaluations before promoting any procedure to a trusted skill.

What is the best way to decide between routing a workflow as a skill or into a deterministic execution flow?▼

Workflow routing guidance distinguishes judgment-heavy, repeatable habits for skill drafts from deterministic, approval-gated execution flows that require routing into Fabro workflows for approved behavior.

How does approval gating work for generated skill candidates?▼

Approval gating requires generated skill candidates to pass a promotion gate with proposal diffs, scenario coverage, deterministic safety checks, optional Promptfoo rubric evaluations, and final human or Fabro approval artifacts.

Can I modify curated skills through background improvement?▼

Curated-skill immutability rules prevent background improvement from rewriting curated Maestro skills without an explicit, evidence-backed promotion path to protect existing trusted procedures.

When should I use evidence-based change control for skill governance?▼

Evidence-based change control is needed when recording, evolving, or generating trusted procedures for important or customer-facing work to prevent accidental promotion of unverified guidance.

Related Skills

Explore More Legal & Compliance Skills→
jacob-balslevjacob-balslev
1

state-machine-modeling

Define lifecycle states, triggers, guards, and invalid-transition rules.

Community
Intermediate
mycelium-hqmycelium-hq
31

evolve

Cluster related instincts into commands, skills, or agents for reuse.

Official
Advanced
sundaiclawsundaiclaw
7

fabro-create-workflow

Convert natural language workflow requirements into Fabro graph and TOML run configuration.

Community
Advanced
insightwavesmithinsightwavesmith

code-analyzer

Analyze code changes to identify those meeting evidence-shape-check criteria.

Community
Intermediate