validate

Name: validate
Availability: InStock
Author: Ether

Create validation manifests and update work item statuses via state-commit.

Updated Mar 9, 2026

Search Tags:#validation #orchestration #evidence #manifest #state-management #work-items

Ready to run

npx skills add https://github.com/ether-moon/agent-atelier --skill validate-ether-moon

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: validate
Source: https://github.com/ether-moon/agent-atelier/tree/main/plugins/agent-atelier/skills/validate
Command: npx skills add https://github.com/ether-moon/agent-atelier --skill validate-ether-moon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Validation recording enables formalization of outcomes by creating manifests that capture a validation run's results and link them to the relevant work items.

Core Features & Use Cases

Create a validation manifest for a run, including id, candidate_set_id, work_item_ids, candidate_branch, candidate_commit, and timing.
Update work item statuses based on the validation outcome and drive orchestration transitions.
Attach evidence references and handle environment_error as a non-code failure path.

Quick Start

Record a completed validation run by supplying a manifest that includes id, candidate_set_id, work_item_ids, candidate_branch, candidate_commit, started_at, finished_at, status, checks, and optional evidence refs.

Frequently Asked Questions about validate

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

FAQPage Schema

How do I record validation results and attach evidence for a candidate set?▼

To record validation results, you create a manifest capturing the run's id, candidate_set_id, work_item_ids, candidate_branch, candidate_commit, timing, status, and checks, with optional evidence references attached to formalize the outcome.

What is a validation run manifest and when do I need to create one?▼

A validation run manifest is a record that captures a validation run's results and links them to relevant work items. You need to create one when validators finish checks or when the orchestrator needs to record results for candidate sets.

How do I update work item status after a validation check finishes?▼

You update work item status by applying the validation outcome to drive orchestration transitions. This requires a two-phase write workflow that writes the manifest first and then updates the orchestration state via state-commit.

How does environment_error differ from a failed validation status?▼

Environment_error is handled as a non-code failure path, distinguishing infrastructure or environment issues from a failed status which indicates the validation checks themselves did not pass for the candidate set.

What prerequisites are needed before recording validation outcomes?▼

Recording validation outcomes requires an initialized orchestration, an active candidate set, and a two-phase write workflow that writes the manifest first and then updates the orchestration state via state-commit, with optional evidence verification.

Can I verify evidence references before updating the orchestration state?▼

Yes, evidence verification is optional during the two-phase write workflow. You write the validation manifest first, verify the attached evidence references, and then update the orchestration state via state-commit.