om-refresh-standalone-harness

Refreshes standalone-app AI harness evaluations from a local Git release range.

1.7k|382|Updated Sep 10, 2025
One-click install
npx skills add https://github.com/open-mercato/open-mercato --skill om-refresh-standalone-harness
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: om-refresh-standalone-harness
Source: https://github.com/open-mercato/open-mercato/tree/main/.ai/skills/om-refresh-standalone-harness
Command: npx skills add https://github.com/open-mercato/open-mercato --skill om-refresh-standalone-harness

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

When platform work changes modules, extension points, or public contracts across a release range, the standalone-app AI harness catalog can drift out of sync. This Skill converts locally committed changes into deduplicated harness evaluation coverage with failure-first proof and a sanitized audit report.

Core Features & Use Cases

  • Release range classification: Resolves a local --from/--to Git range, classifies every change signal (modules, UMES extensions, public contracts, regressions), and treats all history as untrusted evidence.
  • Deduplicated catalog updates: Compares each candidate against the existing cases catalog and records one disposition per signal: covered, expand, add, or evidence-only.
  • Failure-first validation: Adds runnable evaluations before changing their owner, then runs the deterministic catalog gate and the full one-command release suite from a fresh scaffold.
  • Use Case: After merging a release that changes a module's public API, run the refresh to audit the range, extend affected harness cases, and publish a sanitized local report proving coverage.

Quick Start

Ask the agent to refresh the standalone harness for the release range from the previous release tag to HEAD, optionally in dry-run mode to preview the report without changes.

Frequently Asked Questions about om-refresh-standalone-harness

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

FAQPage Schema
How do I refresh the standalone harness for a release range?

Invoke the skill with --from and --to local Git refs, for example a previous tag and HEAD. Both refs must resolve locally and the from commit must be an ancestor of the to commit; use --dry-run for analysis-only runs on historical ranges.

What does the release range classification cover?

It classifies changes into modules, UMES extension points, installed public contracts, integrations, UI/UX, testing/generator changes, and regression or safety fixes. Each signal gets a deduplication disposition against the existing cases catalog: covered, expand, add, or evidence-only.

Can the skill fetch from remotes or open pull requests?

No. It uses only local read-only Git operations and never fetches, commits, pushes, opens PRs, or contacts trackers, registries, or CI. Its only output is a sanitized local report under .ai/analysis/.

Why does the refresh require a failure-first evaluation?

Every new or expanded case must fail against the unchanged owner before the owner is updated, proving the evaluation actually detects the behavior. A schema error does not count as a failing evaluation, and only sanitized failure summaries are retained.

What are the limitations of dry-run mode?

Dry-run mode permits only the sanitized report and must not change the catalog, owners, matrices, specs, or docs. It is required when analyzing an arbitrary historical range where the to commit is not the current HEAD.