docs-architect

Creates comprehensive technical documentation from existing codebases. Analyzes architecture, design patterns, and implementation details to produce long-form technical manuals and ebooks. Use PROACTIVELY for system documentation, architecture guides, or technical deep-dives.

Quality

59%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/docs-architect/SKILL.md

Quality

Content

35%Weight 40%Scale 1-5

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

The content is well-organized at a section level but is almost entirely abstract guidance with no executable detail, templates, or concrete examples, and it inlines everything rather than pointing to reference files. It reads as a generic competency list rather than actionable skill instructions.

Suggestions

Replace abstract instructions ('Apply relevant best practices', 'Provide actionable steps') with concrete, executable guidance: an actual documentation skeleton template, specific commands for extracting structure from a codebase, or worked examples.

Add explicit validation/verification checkpoints in the Documentation Process (e.g., 'Confirm each diagram maps to real code paths before drafting prose', 'Verify terminology consistency across sections').

Move the long 'Key Sections to Include' and 'Output Characteristics' lists into a separate reference file (e.g., references/structure.md) and keep SKILL.md as a concise overview that links to it, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly readable but padded with generic abstract guidance ('Always explain the why', 'Use concrete examples', 'Create mental models') that adds little Claude does not already know; it could be tightened considerably. It avoids the severe over-explanation of basic concepts that would score 2.	3 / 5
Actionability	The instructions are entirely abstract — 'Clarify goals', 'Apply relevant best practices', 'Provide actionable steps and verification' — with no concrete code, commands, templates, or specific steps; it describes rather than instructs.	1 / 5
Workflow Clarity	A clear sequenced process exists (Discovery, Structuring, Writing phases), but there are no explicit validation checkpoints or feedback loops, and the steps remain high-level.	3 / 5
Progressive Disclosure	Section headers give some structure, but with no bundle files present the entire body is a single inlined document; nothing is split into separate referenced files, and the body exceeds the 50-line simple-skill exception.	3 / 5
	Total	10 / 20 Passed

Description

83%Weight 40%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 is strong: it covers both what the skill does and when to use it with concrete trigger phrases, and stays in appropriate third person. Its main weakness is trigger term coverage missing the casual phrasings users actually say.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Analyzes architecture, design patterns, and implementation details', 'produce long-form technical manuals and ebooks'), but the actions are slightly less granular than the fully enumerated 5-anchor toolkit, so 4 rather than 5.	4 / 5
Completeness	Explicitly states both what it does (creates technical documentation/ebooks from codebases, analyzes architecture and patterns) and when to use it ('Use PROACTIVELY for system documentation, architecture guides, or technical deep-dives') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural terms like 'system documentation', 'architecture guides', and 'technical deep-dives', but misses common phrasings a user would actually say ('write docs', 'document this codebase', 'API docs', 'README'), placing it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The long-form technical-documentation-from-codebases niche is mostly distinct with clear triggers, though it has minor overlap risk with general code-explanation or writing skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/docs-architect/SKILL.md
Commit: 3eff4af

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.