CtrlK
BlogDocsLog inGet started
Tessl Logo

technical-design-doc-creator

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).

60

Quality

70%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

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.md
SKILL.md
Quality
Evals
Security

Quality

Content

39%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill has excellent workflow clarity with well-defined steps, validation checklists, and conditional logic for different project types. However, it is severely undermined by extreme verbosity — inlining all 20 section templates, translation tables, anti-pattern examples, and glossary definitions into a single file that far exceeds what's needed in the context window. The content would benefit enormously from splitting templates into separate files and trimming explanations of concepts Claude already understands.

Suggestions

Split section templates (sections 8-20) into a separate TEMPLATES.md reference file, keeping only the mandatory section list and brief descriptions in the main SKILL.md

Remove the translation table and language-specific prompt examples — Claude can translate natively; a single instruction 'Generate TDD in the user's language' suffices

Remove the glossary template that defines basic acronyms like 'API' and 'PII' — Claude knows these; keep only domain-specific term guidance

Consolidate the 'High-Level vs Implementation Details' section to just the guideline question ('Will this change if we switch frameworks?') and one good/bad example pair, removing the redundant tables and multiple examples

DimensionReasoningScore

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 glossary template literally defines 'API' as 'Application Programming Interface'. Much of this content could be condensed to 20% of its size without losing actionable value.

1 / 3

Actionability

Provides concrete templates with markdown structure, table formats, and example content for each section. However, the AskQuestion JSON schema may not correspond to an actual tool, the Confluence integration references an unspecified skill, and the guidance is more template-oriented than executable. The interactive workflow steps are clear but rely on assumed tooling.

2 / 3

Workflow Clarity

The 6-step interactive workflow is clearly sequenced (gather info → validate mandatory → check critical sections → offer suggested → generate → offer publishing). Validation checklists are explicit with checkboxes for mandatory and critical sections. The decision logic for which sections to include based on project type and size is well-defined with clear tables.

3 / 3

Progressive Disclosure

This is a monolithic wall of text with no bundle files or external references. All 20 section templates are fully inlined, making the skill enormous. The translation tables, anti-pattern examples, and full template content for optional sections should be split into separate reference files. There is no progressive disclosure structure whatsoever.

1 / 3

Total

7

/

12

Passed

Description

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 the right skill from a large pool.

DimensionReasoningScore

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 adds further completeness.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms users would say: 'write a design doc', 'create a TDD', 'technical spec', 'architecture document', 'RFC', 'design proposal', and 'document a technical decision before implementation'. These are all natural phrases users would 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

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1485 lines); consider splitting into references/ and linking

Warning

Total

10

/

11

Passed

Repository
tech-leads-club/agent-skills
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.