sdd-init
Bootstrap the SDD structure in any project. Detects stack, conventions, and initializes the active persistence backend. Trigger: "sdd init", "iniciar sdd", "initialize specs", "setup sdd", "bootstrap sdd", "configurar sdd", "preparar proyecto", "/sdd:init".
89
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 with excellent trigger term coverage in multiple languages and clear explicit trigger guidance. The main weakness is that the capability description could be more concrete about what specific artifacts or files are created during initialization. The description effectively distinguishes itself from other skills through SDD-specific terminology.
Suggestions
Add more concrete actions describing what is actually created/generated (e.g., 'creates spec files', 'generates configuration', 'sets up directory structure') to improve specificity
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (SDD structure) and some actions ('Detects stack, conventions, initializes the active persistence backend'), but the actions are somewhat abstract - 'bootstrap' and 'initialize' are not as concrete as specific operations like 'creates files', 'generates config'. | 2 / 3 |
Completeness | Clearly answers both what ('Bootstrap the SDD structure, detects stack, conventions, initializes persistence backend') and when (explicit 'Trigger:' clause with multiple specific trigger phrases). The trigger guidance is explicit and comprehensive. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including variations in English and Spanish ('sdd init', 'iniciar sdd', 'initialize specs', 'setup sdd', 'bootstrap sdd', 'configurar sdd', 'preparar proyecto', '/sdd:init'). These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche - SDD initialization with distinct triggers like 'sdd init' and '/sdd:init'. The combination of 'SDD' terminology and initialization-specific triggers makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 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 excellent workflow clarity and actionability. The multi-mode handling is clearly documented with specific outputs for each path. Minor verbosity in the summary templates and some redundancy between mode sections prevent a perfect conciseness score, but overall this skill provides clear, executable guidance.
Suggestions
Consider consolidating the three mode-specific summary templates into a single template with conditional sections to reduce redundancy
The 'What to Do' section could use a brief one-line overview before diving into steps to improve scannability
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy (e.g., repeating mode-specific instructions that could be consolidated, and the summary templates are verbose). The structure is clear but could be tightened. | 2 / 3 |
Actionability | Provides concrete directory structures, specific file paths, exact config file names, and clear markdown templates for outputs. The detection checklist is specific (package.json, go.mod, etc.) and the table for existing installations gives precise actions. | 3 / 3 |
Workflow Clarity | Clear 4-step sequence with explicit handling for edge cases (existing installation, corrupted config, schema migration). The table format for situation/action pairs provides excellent decision guidance and validation checkpoints. | 3 / 3 |
Progressive Disclosure | Appropriately references external files (persistence-contract.md, engram-convention.md, openspec-convention.md) for detailed conventions while keeping the main skill focused on the init workflow. References are one level deep and clearly signaled. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 10 / 11 Passed | |
- 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.