CtrlK
BlogDocsLog inGet started
Tessl Logo

docs-architect

Creates comprehensive technical documentation from existing codebases. Analyzes architecture, design patterns, and implementation details to produce long-form technical manuals and ebooks.

43

Quality

44%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/docs-architect/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

35%Scale 1-5

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

This skill reads more like a persona description or role prompt than an actionable skill. It extensively describes what a documentation architect does and what good documentation looks like, but provides almost no concrete, executable guidance on how to actually produce it. Claude already knows these general principles; the skill should instead provide specific templates, commands for codebase analysis, example outputs, and validation steps.

Suggestions

Replace the abstract 'Core Competencies' section with concrete examples: provide a sample documentation template or skeleton that Claude can fill in, with actual markdown structure and placeholder content.

Add actionable, executable steps to the Discovery Phase—e.g., specific commands or tool invocations to analyze codebase structure, list dependencies, or extract architecture patterns.

Include at least one concrete input/output example showing a small codebase snippet and the expected documentation output for it.

Add validation checkpoints to the workflow—e.g., 'After Discovery, verify you can answer these 5 questions about the codebase before proceeding to Structuring' with specific questions listed.

DimensionReasoningScore

Conciseness

The content extensively explains concepts Claude already knows well—technical writing principles, system thinking, documentation architecture, what an executive summary is, etc. The 'Core Competencies' section describes Claude's own capabilities back to it. Much of this is padding that doesn't add actionable value.

2 / 5

Actionability

The skill is almost entirely abstract guidance and high-level descriptions. There are no concrete code examples, no executable commands, no specific templates, and no copy-paste-ready content. Instructions like 'Analyze codebase structure and dependencies' and 'Create logical chapter/section hierarchy' are vague directions rather than actionable steps.

2 / 5

Workflow Clarity

There is a three-phase process (Discovery, Structuring, Writing) with sub-steps listed, providing a rough sequence. However, there are no validation checkpoints, no feedback loops, no verification steps to confirm documentation accuracy, and no concrete criteria for when to move between phases.

3 / 5

Progressive Disclosure

There is one reference to 'resources/implementation-playbook.md' for detailed examples, which is good. However, the bulk of the content is inlined as a monolithic document with sections that could be split out (e.g., the 'Key Sections to Include' checklist, 'Best Practices'). No bundle files are provided to verify the referenced path exists.

3 / 5

Total

10

/

20

Passed

Description

53%Scale 1-5

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 communicates a clear domain (generating technical documentation from code) and distinguishes itself with the long-form manual/ebook angle. However, it lacks a 'Use when...' clause which limits its effectiveness for skill selection, and the specific capabilities listed are somewhat high-level without covering the full range of actions the skill likely performs.

Suggestions

Add an explicit 'Use when...' clause with trigger phrases like 'when the user asks to document a codebase, generate technical documentation, create a developer guide, or produce an ebook from code'.

Include more natural user-facing trigger terms such as 'generate docs', 'code documentation', 'API reference', 'developer guide', or 'document my project'.

Expand the list of concrete actions, e.g., 'generates table of contents, API references, architecture diagrams descriptions, and chapter-organized content'.

DimensionReasoningScore

Specificity

Names the domain (technical documentation from codebases) and a couple of concrete actions (analyzes architecture/design patterns, produces manuals/ebooks), but lacks detail on specific outputs or steps like generating table of contents, API references, diagrams, etc.

3 / 5

Completeness

Has a clear 'what' (creates technical documentation from codebases, analyzes architecture and patterns, produces manuals/ebooks) but completely lacks a 'when' clause or explicit trigger guidance for when Claude should select this skill.

3 / 5

Trigger Term Quality

Includes some relevant keywords like 'technical documentation', 'codebases', 'architecture', 'ebooks', and 'technical manuals', but misses natural user phrases like 'document my code', 'generate docs', 'API documentation', 'README', or 'code documentation'.

3 / 5

Distinctiveness Conflict Risk

The focus on long-form technical manuals and ebooks from codebases is fairly distinctive and unlikely to overlap with general documentation or code analysis skills. However, it could overlap with simpler code documentation or README generation skills.

4 / 5

Total

13

/

20

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.