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.
71
88%
Does it follow best practices?
Impact
—
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 domain (computer architecture/EDA), lists concrete actions in the exploration loop, and provides an explicit 'Use when' clause with multiple natural trigger terms. It uses proper third-person voice throughout and is concise without being vague.
| 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', and 'iterative parameter tuning' — these are terms users in the computer architecture/EDA domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — 'computer architecture and EDA' combined with 'design space exploration' is very specific. The term 'optimize' could overlap with generic optimization skills, but the domain-specific context and other trigger terms make conflicts unlikely. | 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 strong, highly actionable skill for autonomous design space exploration with excellent workflow clarity and concrete guidance. Its main weakness is length—at ~250 lines it pushes token budget limits, and some content (like the full report template and extensive use-case table) could be extracted to supporting files. The safety rules, state recovery mechanism, and stopping conditions demonstrate thoughtful design for autonomous operation.
Suggestions
Extract the DSE_REPORT.md template, CSV format specification, and parameter inference table into separate bundle files (e.g., REPORT_TEMPLATE.md, FORMATS.md) to reduce the main skill's token footprint.
Trim the 'Typical Use Cases' table to 3-4 representative examples instead of 7, or move it to a separate EXAMPLES.md file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~250 lines) with some sections that could be tightened—the 'Typical Use Cases' table, while useful, is extensive, and the inferred parameter ranges table in Phase 0 is very detailed. However, most content is domain-specific knowledge Claude wouldn't inherently know (EDA-specific parameter ranges, search strategies), so it largely earns its place. Some redundancy exists between the workflow description and the key rules section. | 2 / 3 |
Actionability | The skill provides highly concrete, executable guidance: specific file paths, CSV formats, JSON state structures, exact commands, parsing script requirements, and complete report templates. The parameter inference table with specific ranges (powers of 2, geometric sequences) and the search strategy selection criteria are directly actionable. | 3 / 3 |
Workflow Clarity | The four-phase workflow is clearly sequenced with explicit validation checkpoints: baseline run before exploration, constraint checking at each iteration, patience counters, timeout checks before starting new iterations, crash detection with 3-strike rule, and state recovery via DSE_STATE.json. The feedback loop (run → analyze → pick next → repeat) with six explicit stopping conditions is well-defined. | 3 / 3 |
Progressive Disclosure | The skill is a monolithic document with no references to supporting files despite being quite long. The detailed report template, CSV format, JSON state structure, and parameter inference tables could be split into separate reference files. However, for a standalone skill with no bundle files, the internal organization with clear phase headers and tables provides reasonable navigability. | 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 | |
a425a71
Table of Contents
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.