sdd-init
Initialize Spec-Driven Development context in any project. Detects stack, conventions, and bootstraps the active persistence backend. Trigger: When user wants to initialize SDD in a project, or says "sdd init", "iniciar sdd", "openspec init".
85
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
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 solid skill description with excellent trigger terms and completeness, clearly specifying both what the skill does and when to use it. The main weakness is that the capability descriptions could be more concrete—terms like 'detects stack' and 'bootstraps the active persistence backend' are somewhat abstract and could benefit from more specific action language. Overall, it performs well for skill selection purposes due to its distinctive and explicit trigger guidance.
Suggestions
Make the capabilities more concrete by specifying what 'detects stack' means in practice (e.g., 'Detects project language, framework, and package manager') and what 'bootstraps the active persistence backend' produces (e.g., 'creates SDD configuration files and spec templates').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Spec-Driven Development initialization) and some actions ('Detects stack, conventions, and bootstraps the active persistence backend'), but the actions are somewhat vague—'detects stack' and 'bootstraps the active persistence backend' are not fully concrete or comprehensive. | 2 / 3 |
Completeness | Clearly answers both 'what' (initialize SDD context, detect stack/conventions, bootstrap persistence backend) and 'when' (explicit 'Trigger:' clause with specific phrases like 'sdd init', 'iniciar sdd', 'openspec init'). | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would actually say: 'sdd init', 'iniciar sdd', 'openspec init', and 'initialize SDD'. These are specific command-like phrases that cover multiple language variations and are highly likely to match user input. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with very specific trigger terms ('sdd init', 'openspec init', 'iniciar sdd') that are unlikely to conflict with other skills. The niche of Spec-Driven Development initialization is narrow and well-defined. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%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 initialization skill with strong actionability — concrete commands, exact file paths, and specific parameter values make it easy to execute. Its main weaknesses are moderate redundancy across sections (persistence logic is stated multiple times) and the lack of validation/error-handling checkpoints in the workflow, which is notable given it performs file system writes and external persistence calls.
Suggestions
Add validation checkpoints after key steps — e.g., verify directory creation succeeded in Step 2, confirm mem_save returned successfully in Step 5, and define error recovery if detection finds no recognizable stack in Step 1.
Consolidate the persistence logic: the mode-dependent behavior is explained in the Execution and Persistence Contract, then partially repeated in Steps 2, 3, and 5. Consider a single decision table or matrix instead of scattering mode conditionals across multiple sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some redundancy — the persistence contract is explained in the execution section and then repeated in Steps 2, 3, and 5. The return summary templates for each mode are verbose and could be condensed. However, it mostly avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides concrete, executable guidance: specific mem_save calls with exact parameters, exact directory structures to create, a complete YAML config template, specific glob paths for skill scanning, and specific file names to check. The instructions are copy-paste ready and leave little ambiguity. | 3 / 3 |
Workflow Clarity | The 6-step sequence is clearly numbered and logically ordered. However, there are no validation checkpoints — no step verifies that detection was accurate, that directory creation succeeded, or that mem_save completed successfully. For operations involving file creation and persistence writes, the absence of feedback loops caps this at 2. | 2 / 3 |
Progressive Disclosure | The skill appropriately references external convention files (engram-convention.md, openspec-convention.md, skill-registry/SKILL.md) for detailed specifications rather than inlining them. References are one level deep and clearly signaled. The content is well-structured with clear section headers. | 3 / 3 |
Total | 10 / 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
- Gentleman-Programming/agent-teams-lite
- Commit
6901875
- 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.