Write specifications with requirements and scenarios (delta specs for changes). Trigger: "spec", "requerimientos", "requirements", "especificaciones", "write specs", "sdd spec", "acceptance criteria", "/sdd:continue (when proposal exists but specs don't)".
86
83%
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 solid skill description with excellent trigger term coverage including bilingual support and explicit trigger guidance. The main weakness is the somewhat limited specificity of capabilities - it could benefit from listing more concrete actions beyond 'requirements and scenarios'. The parenthetical note about delta specs adds useful context for when to apply this skill.
Suggestions
Expand the capabilities list with more specific actions like 'define acceptance criteria', 'document edge cases', 'structure user stories', or 'map dependencies' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (specifications) and some actions ('Write specifications with requirements and scenarios'), but lacks comprehensive detail about concrete actions like 'define acceptance criteria', 'document edge cases', or 'structure requirement hierarchies'. | 2 / 3 |
Completeness | Explicitly answers both what ('Write specifications with requirements and scenarios') and when (clear 'Trigger:' clause with multiple explicit trigger terms and a contextual condition for '/sdd:continue'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including both English and Spanish variations ('spec', 'requerimientos', 'requirements', 'especificaciones', 'write specs', 'sdd spec', 'acceptance criteria'), plus a contextual trigger for workflow continuation. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on specification writing with distinct triggers like 'sdd spec', 'acceptance criteria', and the specific '/sdd:continue' command that differentiate it from general documentation or requirements skills. | 3 / 3 |
Total | 11 / 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-structured skill with excellent actionability and workflow clarity. The step-by-step process is clear, templates are concrete and executable, and error recovery is well-documented. The main weakness is some verbosity in explaining concepts Claude already knows (RFC 2119 keywords, priority level definitions) and inline templates that could be referenced externally.
Suggestions
Remove or significantly condense the RFC 2119 Keywords Quick Reference table - Claude already knows these standard keywords
Consider moving the detailed delta spec and full spec templates to a separate TEMPLATES.md file and referencing it, keeping only a brief example inline
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundant content like the RFC 2119 quick reference table (Claude knows these) and verbose template examples that could be condensed. The priority levels table and error recovery sections add value but could be tighter. | 2 / 3 |
Actionability | Provides fully concrete, copy-paste ready templates with exact markdown formats, specific commands for each persistence mode (mem_search, mem_save, file paths), and detailed structured output formats. Every step has executable guidance. | 3 / 3 |
Workflow Clarity | Clear 5-step sequence with explicit validation through the structured summary output. Error recovery table provides feedback loops for common failure scenarios. The workflow handles branching logic (delta vs full spec, different persistence modes) with clear decision points. | 3 / 3 |
Progressive Disclosure | References external files appropriately (persistence-contract.md, engram-convention.md, openspec-convention.md) but the main content is somewhat monolithic. The extensive template examples inline could potentially be split into a separate reference file, though the current structure is navigable. | 2 / 3 |
Total | 10 / 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 | |
d9bf9a4
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.