sdd-explore
Evaluate implementation options before coding changes. Creates comparison matrices, pros/cons analysis, risk assessment, and a recommended approach for architecture, feature planning, refactors, and debugging strategy decisions. Use when the user wants to compare multiple approaches before implementation. Trigger: "explore", "investigar", "think through", "analizar", "research", "sdd explore", "evaluar opciones", "/sdd:explore".
94
92%
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 well-crafted skill description that excels across all dimensions. It clearly articulates specific deliverables, provides comprehensive trigger terms in multiple languages, explicitly states both what the skill does and when to use it, and occupies a distinct niche in the pre-implementation evaluation space.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Creates comparison matrices, pros/cons analysis, risk assessment, and a recommended approach' with clear domains: 'architecture, feature planning, refactors, and debugging strategy decisions'. | 3 / 3 |
Completeness | Clearly answers both what ('Creates comparison matrices, pros/cons analysis, risk assessment, and a recommended approach') and when ('Use when the user wants to compare multiple approaches before implementation') with explicit trigger terms. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms including English and Spanish variations: 'explore', 'investigar', 'think through', 'analizar', 'research', 'evaluar opciones', plus command triggers like 'sdd explore' and '/sdd:explore'. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on pre-implementation evaluation and comparison of options. The specific deliverables (comparison matrices, risk assessment) and explicit command triggers ('/sdd:explore') make it highly distinguishable from general coding or planning skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%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-structured skill with clear workflow, good progressive disclosure, and actionable guidance. The main weakness is moderate verbosity - some sections explain concepts that could be assumed or condensed. The skill effectively handles multiple persistence modes and provides comprehensive error recovery guidance.
Suggestions
Condense the 'What to Do' step descriptions - the framing questions in Step 1 and investigation checklist in Step 2 could be more compact
Remove or shorten the 'Domain focus' and 'Purpose' explanations that describe what exploration means - Claude understands this context
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundant explanations (e.g., explaining what exploration means, listing obvious domain focuses). The ASCII tree diagram and some procedural descriptions could be tightened. | 2 / 3 |
Actionability | Provides concrete, specific guidance with clear steps, explicit file paths, structured output requirements, and references to templates. The error recovery table and rules section give executable direction. | 3 / 3 |
Workflow Clarity | Clear 6-step sequence with explicit validation checkpoints (time-boxing guidance, persistence conditions, error recovery table). The workflow includes decision points and conditional branching based on mode and change name presence. | 3 / 3 |
Progressive Disclosure | Appropriately references external files (TEMPLATES.md, persistence-contract.md, engram-convention.md, openspec-convention.md) with clear one-level-deep navigation. Core content stays in the skill while detailed templates and conventions are externalized. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- Yoizen/dev-ai-workflow
- Commit
d9bf9a4
- 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.