moai-harness-learner

Harness learning subsystem coordinator. Produces Tier 4 auto-update proposal payloads consumed by the orchestrator (which surfaces them via AskUserQuestion) and orchestrates Apply/Rollback flows. Triggers when harness learning proposals are pending or learning lifecycle management is needed.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and actionable with concrete commands and a clear schema, but suffers from verbosity (repeated canonical-contract restatements) and missing validation checkpoints in its destructive apply/rollback workflow.

Suggestions

Add explicit validation/verification steps to the Approve and Rollback flows (e.g. confirm the snapshot exists and re-run 'moai harness status' after apply).

Remove the duplicated '[HARD]' canonical-contract paragraphs — state the orchestrator/AskUserQuestion boundary once and reference it.

Trim or move the large auto-generated annotation comment to a separate notes reference to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but padded with a long auto-generated annotation comment and repeated '[HARD]' canonical-contract restatements of the orchestrator/AskUserQuestion boundary across multiple sections.	2 / 3
Actionability	Provides concrete executable commands ('moai harness status/apply/rollback'), a fully specified payload schema with field definitions, and copy-ready rollback/disable examples.	3 / 3
Workflow Clarity	Steps are clearly sequenced (Quick Reference + Steps 1-5), but destructive/batch operations (apply auto-update, delete proposal file, rollback) lack explicit validation or verification checkpoints, capping the score at 2.	2 / 3
Progressive Disclosure	Single-file skill with well-organized sections (Quick Reference, Implementation Guide, Safety Architecture Reference) and clear navigation; no nested references requiring deeper traversal.	3 / 3
	Total	10 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and complete with explicit trigger guidance, but its trigger terms are dominated by internal/jargon vocabulary rather than phrases a user would naturally say, limiting trigger term quality.

Suggestions

Add plain-language trigger keywords users would naturally say (e.g. 'auto-update proposals', 'apply or rollback learning changes') alongside the internal terms.

Soften or gloss 'Tier 4' jargon so the trigger clause is intelligible without harness-internal context.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'Produces Tier 4 auto-update proposal payloads' and 'orchestrates Apply/Rollback flows' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what it does (produces payloads, orchestrates Apply/Rollback) and when to use it ('Triggers when harness learning proposals are pending...').	3 / 3
Trigger Term Quality	Triggers are present ('Triggers when harness learning proposals are pending or learning lifecycle management is needed') but rely on internal jargon ('Tier 4 auto-update', 'harness learning lifecycle') rather than natural user keywords.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (Harness learning subsystem coordinator, Tier 4 auto-update proposals) with distinct triggers unlikely to overlap with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: modu-ai/moai-adk
Path: .claude/skills/moai-harness-learner/SKILL.md
Commit: 05117b6

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.