aris-dse-loop

Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout. Use when user says "DSE", "design space exploration", "sweep parameters", "optimize", "find best config", or wants iterative parameter tuning.

Quality

90%

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 thorough, well-sequenced autonomous-loop skill with strong validation feedback loops and concrete templates. It loses points only on conciseness/progressive-disclosure (some inline content is bulky and could be externalized) and minor actionability gaps around the result-parsing script.

Suggestions

Move the large DSE_REPORT.md template and the parameter-inference strategy table into a reference file (e.g. references/report_template.md) and link to it from SKILL.md to improve progressive disclosure and reduce inline tokens.

Provide a concrete, copy-paste parse_result.py skeleton (argparse + a regex/yaml extraction example) instead of describing it as 'or similar'.

Give one concrete example of modifying parameters (e.g., a sed/Edit command updating a config key) rather than the abstract 'edit config file, command-line args, or source constants'.

Dimension	Reasoning	Score
Conciseness	Largely efficient and domain-specific with concrete templates (CSV format, state JSON, report markdown) and no basic-concept padding, but the full report template and several example blocks are heavier than strictly necessary.	4 / 5
Actionability	Provides concrete templates and exact example invocations, but the parse_result.py step is only described ('or similar') and parameter modification is stated abstractly rather than with copy-paste commands — minor gaps.	4 / 5
Workflow Clarity	Clear five-phase sequence with explicit checkpoints: baseline-as-target, enumerated stopping conditions, dedup check against dse_log.csv, crash-retry feedback loop, and a 'Key Rules' checklist.	5 / 5
Progressive Disclosure	Well-organized into clear sections with no bundle files, but bulky inline content (the report template, the inference-strategy table) could be split into one-level-deep reference files to lighten SKILL.md.	4 / 5
	Total	17 / 20 Passed

Description

100%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 description: third-person voice, concrete actions, explicit 'Use when' triggers with natural synonyms, and a well-scoped niche. No meaningful gaps; the only minor risk is the generic 'optimize' trigger overlapping with general optimization skills.

Dimension	Reasoning	Score
Specificity	Names the domain (computer architecture and EDA) and lists multiple concrete actions — 'Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout' — matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers what (an autonomous DSE loop that runs/analyzes/tunes/iterates) and when ('Use when user says ...'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including the acronym 'DSE', the full 'design space exploration', and synonyms 'sweep parameters', 'optimize', 'find best config', plus 'iterative parameter tuning'.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear EDA/architecture-DSE niche with domain-anchored triggers; the 'optimize'/'sweep' terms are generic but the framing keeps conflict risk minimal.	5 / 5
	Total	20 / 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-dse-loop/SKILL.md
Commit: 4b35756

Reviewed: 5 days 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.