aris-meta-optimize

Analyze ARIS usage logs and propose optimizations to SKILL.md files, reviewer prompts, and workflow defaults. Outer-loop harness optimization inspired by Meta-Harness (Lee et al., 2026). Use when user says "优化技能", "meta optimize", "improve skills", "分析使用记录", or wants to optimize ARIS's own harness components based on accumulated experience.

Quality

88%

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

81%Weight 40%Scale 1-5

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

A well-structured, actionable multi-step workflow with strong validation and feedback loops. The main weaknesses are minor: some prose padding, an unscripted analysis step, and a monolithic single-file layout where some reference material could be externalized.

Suggestions

Provide a runnable script or concrete commands for Step 1's usage-pattern analysis (frequency, failure, convergence counts) instead of only listing what to compute, matching the executability of Step 0.

Trim conceptual padding such as the Meta-Harness 'key insight' explanation and condense the Triggering mechanism to the essential hook behavior.

Move the Event Schema Reference and detailed triggering/hook setup into a separate reference file (e.g. references/event-schema.md) referenced one level deep from the body, improving progressive disclosure for this longer skill.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense and operational (executable bash, diffs, report templates), with only minor over-explanation such as the Meta-Harness 'key insight' prose and the detailed triggering mechanism that could be trimmed.	4 / 5
Actionability	Step 0's bash and Step 3's diff and Step 4's MCP call are concrete and executable, but Step 1 ('Analyze Usage Patterns') only describes the analyses to compute rather than giving a runnable script, leaving a minor gap.	4 / 5
Workflow Clarity	Steps 0–6 are clearly sequenced with explicit validation checkpoints (data-availability check, cross-model reviewer score gate with needs-more-data feedback loop, backup before apply) and a Key Rules checklist, satisfying the top anchor for a destructive/batch operation.	5 / 5
Progressive Disclosure	Well-organized into clear sections with no nested/deep references and no missing bundle files, but it is a single monolithic file where content like the Event Schema Reference and Triggering detail could be split into separate reference files.	4 / 5
	Total	17 / 20 Passed

Description

95%Weight 40%Scale 1-5

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

A strong, specific description that clearly states what the skill does and when to invoke it, with natural multilingual trigger phrases and minimal conflict risk. The only minor gap is that the stated actions are essentially two verbs (analyze, propose) rather than a fuller action inventory.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Analyze ARIS usage logs', 'propose optimizations') across several specific targets (SKILL.md files, reviewer prompts, workflow defaults), but the action verbs are limited to analyze/propose rather than a comprehensive action list.	4 / 5
Completeness	Explicitly answers both what ('Analyze ARIS usage logs and propose optimizations...') and when ('Use when user says...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Provides multiple natural trigger phrases users would actually say, including English synonyms ('meta optimize', 'improve skills') and Chinese equivalents ('优化技能', '分析使用记录'), giving comprehensive coverage.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (ARIS harness self-optimization) with distinct, narrow triggers, so conflict risk with other skills is minimal.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/aris-meta-optimize/SKILL.md
Commit: d51b64e

Reviewed: 6 hours 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.