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.
89
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines a specific niche (design space exploration for computer architecture/EDA), lists concrete actions the skill performs, and provides an explicit 'Use when...' clause with excellent trigger term coverage. The description is concise, uses third person voice, and would be easily distinguishable from other skills in a large collection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout.' These are specific, actionable steps describing the skill's behavior. | 3 / 3 |
Completeness | Clearly answers both 'what' (autonomous design space exploration loop that runs programs, analyzes results, tunes parameters, iterates) and 'when' (explicit 'Use when...' clause with specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'DSE', 'design space exploration', 'sweep parameters', 'optimize', 'find best config', 'iterative parameter tuning'. These cover both acronyms and natural phrases users would say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche targeting computer architecture and EDA design space exploration. The domain-specific terms like 'DSE', 'EDA', 'sweep parameters', and 'design space exploration' make it very unlikely to conflict with other skills. The word 'optimize' could overlap slightly, but the surrounding context anchors it well. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted, highly actionable skill for autonomous design space exploration with excellent workflow clarity, concrete data formats, and robust error handling. Its main weakness is length — at ~300 lines it pushes token budget limits and could benefit from splitting detailed templates and reference tables into separate files. The content is domain-appropriate and avoids explaining concepts Claude already knows, though some sections (like the full report template) could be more concise.
Suggestions
Extract the DSE_REPORT.md template, parameter inference domain knowledge table, and typical use cases table into separate referenced files (e.g., REPORT_TEMPLATE.md, PARAM_INFERENCE.md) to reduce the main skill's token footprint.
Tighten the Phase 2 'Directed Search' section by consolidating the strategy selection into a more compact decision tree rather than listing all strategies with bullets.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~300 lines) with some sections that could be tightened. The 'Typical Use Cases' table, while useful, is verbose. The inferred parameter ranges table and domain knowledge table add value but contribute to length. Some sections like the full DSE_REPORT.md template could be more concise. However, most content is genuinely instructive rather than explaining things Claude already knows. | 2 / 3 |
Actionability | Highly actionable with concrete file paths, CSV formats, JSON state structures, specific commands, executable examples, and detailed parameter inference strategies with exact ranges. The workflow is copy-paste ready with specific file names, directory structures, and data formats throughout. | 3 / 3 |
Workflow Clarity | Excellent multi-phase workflow (Phase 0-4) with clear sequencing, explicit stopping conditions (timeout, max_iterations, patience, success criteria), state recovery mechanism via DSE_STATE.json, error handling (crash detection with 3-strike rule), and validation checkpoints (baseline run first, constraint checking, never re-running identical configs). Feedback loops are well-defined. | 3 / 3 |
Progressive Disclosure | The skill is monolithic — all content is in a single file with no references to external files for detailed content. The DSE_REPORT.md template, parameter inference tables, and detailed phase descriptions could be split into referenced files. However, the internal structure with clear phase headers and tables provides reasonable navigation within the single file. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
700fbe2
- Reviewed
Table of Contents
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.