spec-requirements
Generate comprehensive requirements definition documents with technology selection and improvement suggestions
Install with Tessl CLI
npx tessl i github:sc30gsw/claude-code-customes --skill spec-requirements62
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description provides a basic understanding of the skill's purpose but lacks the explicit trigger guidance required for Claude to reliably select it from a large skill library. It uses appropriate third-person voice and mentions the domain, but the absence of a 'Use when...' clause and limited trigger term coverage significantly weakens its effectiveness for skill selection.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user asks for requirements documents, PRDs, system specifications, or needs help defining project requirements'
Include common user terminology variations such as 'specs', 'PRD', 'product requirements', 'system requirements', 'tech stack selection'
Specify concrete deliverables or document sections (e.g., 'functional requirements, non-functional requirements, architecture recommendations, technology stack analysis')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (requirements definition documents) and mentions some actions (generate, technology selection, improvement suggestions), but lacks concrete specifics about what types of requirements, what format, or what the improvement suggestions entail. | 2 / 3 |
Completeness | Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance. Per rubric guidelines, missing explicit trigger guidance caps completeness at 2, and this has no trigger guidance at all. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'requirements definition documents' and 'technology selection', but misses common variations users might say such as 'specs', 'requirements doc', 'tech stack', 'system requirements', or 'PRD'. | 2 / 3 |
Distinctiveness Conflict Risk | Somewhat specific to requirements documents, but 'comprehensive' and 'improvement suggestions' are vague enough to potentially overlap with general documentation or technical writing skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is well-structured and concise, effectively using tables to present options and templates. However, it lacks executable implementation details showing how Claude should actually generate the requirements documents, and the workflow for complex operations like reverse engineering needs explicit validation steps.
Suggestions
Add executable code or detailed steps showing how Claude should generate the actual requirements document content, not just the CLI interface
Include validation checkpoints in the reverse engineering workflow (e.g., 'Verify component discovery found expected patterns before proceeding')
Add a concrete example of a generated output section showing the expected format and content structure
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using tables for options and templates, avoiding unnecessary explanations. Every section serves a clear purpose without padding or explaining concepts Claude already knows. | 3 / 3 |
Actionability | Provides concrete CLI examples and option tables, but lacks executable code showing how to actually generate the requirements document. The EARS format examples are patterns rather than complete executable guidance. | 2 / 3 |
Workflow Clarity | Reverse engineering mode lists steps (1-3) but lacks validation checkpoints. The output structure is listed but there's no clear workflow for how to proceed through the generation process or handle errors. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and tables, but everything is inline in one file. For a skill of this complexity with multiple modes, templates, and tool integrations, some content could be split into separate reference files. | 2 / 3 |
Total | 9 / 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.
- 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.