Creates comprehensive Technical Design Documents (TDD) with mandatory and optional sections through interactive discovery. Use when user asks to "write a design doc", "create a TDD", "technical spec", "architecture document", "RFC", "design proposal", or needs to document a technical decision before implementation. Do NOT use for README files, API docs, or general documentation (use docs-writer instead).
70
63%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./packages/skills-catalog/skills/(creation)/create-technical-design-doc/SKILL.mdQuality
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 an excellent skill description that hits all the marks. It provides specific capabilities, comprehensive trigger terms covering multiple natural phrasings, explicit 'Use when' and 'Do NOT use' clauses, and clear disambiguation from related skills. The description is concise yet thorough, making it easy for Claude to select this skill correctly from a large pool.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists concrete actions ('Creates comprehensive Technical Design Documents') and specifies the approach ('mandatory and optional sections through interactive discovery'). It also clarifies what it does NOT do, adding further specificity. | 3 / 3 |
Completeness | Clearly answers both 'what' (creates TDDs with mandatory/optional sections through interactive discovery) and 'when' (explicit 'Use when' clause with multiple trigger phrases). Also includes a 'Do NOT use' clause for disambiguation, which is a bonus. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'write a design doc', 'create a TDD', 'technical spec', 'architecture document', 'RFC', 'design proposal', and 'document a technical decision before implementation'. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary-setting via the 'Do NOT use for README files, API docs, or general documentation (use docs-writer instead)' clause. This directly addresses potential conflicts with similar documentation skills and provides a clear niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is comprehensive in coverage but severely undermined by its verbosity - it's essentially an entire TDD handbook inlined into a single file. The core workflow and decision logic (project size adaptation, critical section detection, interactive gathering) are sound, but they're buried under hundreds of lines of full section templates, translation tables, and explanations of well-known standards. The skill would be dramatically more effective at 20-30% of its current length with templates split into a separate reference file.
Suggestions
Extract all 20 section templates into a separate TEMPLATES.md file and reference it from SKILL.md, keeping only the workflow logic, decision rules, and key principles inline.
Remove the language translation table and anti-pattern examples - replace with a single directive like 'Match the user's language for all content; keep technical terms in English' and one brief good/bad example.
Remove explanations of industry standards (what PCI DSS is, what OWASP is, what ADR means) - Claude already knows these. Keep only the mapping of which standards apply to which project types.
Add explicit validation checkpoints within each workflow step (e.g., 'After Step 2, confirm all mandatory fields are collected before proceeding to Step 3') rather than only having a final checklist.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~800+ lines. Contains massive translation tables, extensive anti-pattern examples, full template content for all 20 sections, and explanations of concepts Claude already knows (what PCI DSS is, what a webhook is, what GDPR means). The language adaptation section alone with its translation table is unnecessary padding. Most section templates could be reduced to structural outlines rather than fully fleshed-out examples with placeholder data. | 1 / 3 |
Actionability | Provides concrete templates and structured workflows with specific JSON for the AskQuestion tool, clear section templates with markdown examples, and validation checklists. However, much of it is template/placeholder content rather than executable guidance - the templates show what a TDD looks like but the actual generation logic relies on Claude filling in blanks. The AskQuestion JSON is actionable but the rest is more descriptive than instructive. | 2 / 3 |
Workflow Clarity | The 6-step interactive workflow (Initial Gathering → Validate Mandatory → Check Critical → Offer Suggested → Generate → Confluence) is clearly sequenced. However, validation checkpoints are limited to a final checklist rather than being embedded at each step. There's no explicit feedback loop for when the user provides incomplete information mid-workflow, and the validation rules at the end feel disconnected from the step-by-step process. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with all 20 section templates fully inline. The content would benefit enormously from splitting section templates into a separate reference file (e.g., TEMPLATES.md) and keeping SKILL.md as an overview with the workflow, decision logic, and key principles. No external file references are used despite the document being extremely long. | 1 / 3 |
Total | 6 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (1485 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
906a57d
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.