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

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, highly actionable autonomous-loop skill with strong validation and error-recovery feedback loops. Main weaknesses are a slightly abstract parsing-script step, a large inline report template, and a dead external reference.

Suggestions

Provide a concrete, minimal parse_result.py skeleton (e.g., argparse + a regex/float-extraction stub) rather than only instructing the agent to 'write a parameter extraction script... or similar', so the most execution-critical step is copy-paste ready.

Externalize the large DSE_REPORT.md template (lines 200-245) into a references/REPORT_TEMPLATE.md and link to it, keeping SKILL.md as a leaner overview and improving progressive disclosure.

Fix or remove the broken shared-references/external-cadence.md links (no such bundle file exists); either ship the referenced file or inline the essential cadence guidance so the skill is self-contained.

Dimension	Reasoning	Score
Conciseness	Mostly lean and free of concept-explanation padding (no explanations of what gem5/yosys are), but the full report-template block and a few mildly redundant Key Rules passages add length that could be trimmed, keeping it at 4 rather than a clean 5.	4 / 5
Actionability	Concrete file paths, CSV/JSON schemas, a parameter-inference strategy table, and copy-paste example invocations give mostly executable guidance; the one gap is that the metric-parsing script (the most execution-critical piece) is left abstract ("write a parameter extraction script... or similar") rather than provided as executable code.	4 / 5
Workflow Clarity	Four phases with numbered steps plus explicit validation checkpoints (constraint-met checks, "check dse_log.csv before each run", metric-comparability re-validation after a parser rewrite) and feedback loops for error recovery (crash→log→skip→continue; repeated crash→discard & reimplement→re-validate), so the destructive/batch cap of 3 does not apply.	5 / 5
Progressive Disclosure	Well-organized into clear sections with headers and one clearly-signaled one-level-deep reference; held to 4 because the skill is monolithic (large inline templates like the report block could be externalized) and the referenced shared-references/external-cadence.md is a broken external link with no bundle file present.	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 description: it states concrete capabilities, gives comprehensive natural trigger phrases, and is scoped to a clear niche. The only minor gap is that the action verbs are somewhat generic rather than maximally concrete.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("Runs a program, analyzes results, tunes parameters, and iterates"), clearly above the 1-2-action anchor 3, but the verbs are slightly generic compared to the fully concrete anchor-5 example, so it sits at 4 rather than 5.	4 / 5
Completeness	Explicitly answers both what (an autonomous run-analyze-tune-iterate loop until objective met or timeout) and when ("Use when user says..." with concrete trigger phrases), matching the anchor-5 example precisely.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including the acronym ("DSE"), full phrase ("design space exploration"), and synonyms users actually say ("sweep parameters", "optimize", "find best config", "iterative parameter tuning"); the file-extension criterion is N/A for a non-file skill.	5 / 5
Distinctiveness Conflict Risk	Scoped to "computer architecture and EDA" with a distinct niche (design space exploration) and domain-specific triggers ("DSE", "design space exploration") that minimize overlap with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	13 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/dse-loop/SKILL.md
Commit: f4f20f9

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.