document-this

Generate multi-audience documentation from any codebase — workflows for non-technical readers, architecture for developers, and AI orientation for agents. Deterministic JS scripts handle structural extraction; the agent writes the prose. Project-agnostic and self-orienting. Use when the user asks to "document this project", runs `/document-this`, runs `/document-this <file-path>`, runs `/document-this --focus "<Feature Name>"` for a deep-dive on one subsystem in a named subfolder, or wants fresh documentation reflecting the current codebase state.

Quality

81%

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

Quality

Content

63%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.

A well-structured, actionable skill body with clear phased workflows and real bundled scripts, but it is let down by repeated slug/path rules that bloat the token budget and by references to a templates/ directory that is not actually shipped with the skill.

Suggestions

Consolidate the slug-derivation rules into one canonical section and reference it elsewhere (e.g., 'see Slug derivation') instead of restating defaults, shorter-form, and collision rules three or four times.

Ship the referenced templates/ directory (README.template.md, workflow-entry.template.md, architecture.template.md, ai-orientation.template.md, focus-workflows.template.md, focus-architecture.template.md, workflows.template.md) or remove the template references and inline the minimal scaffolds needed.

Add an explicit validate→fix→retry feedback loop for the overwrite-prone regeneration step (e.g., 'regenerate, run git diff generated-docs/, review and re-run affected scripts if output is stale') to push workflow clarity to the top anchor.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and does not explain concepts Claude already knows, but the slug-derivation rules are restated three to four times (Invocation, Output, 'Slug derivation', and Quality Rules) and the 'no README/ai-orientation in the subfolder' and '../ path' rules are repeated, which could be tightened into a single canonical statement.	3 / 5
Actionability	Provides executable commands (the scripts table plus per-phase 'node skills/document-this/scripts/*.mjs' invocations) and a clear file-output map; minor gaps remain in that template placeholder filling is referenced rather than shown with concrete examples.	4 / 5
Workflow Clarity	Phases 1–5 and F1–F4 are clearly sequenced with explicit checkpoints (empty-scope halt, 'refuse to invent the feature', ripple check, 'when scripts disagree with disk, trust disk'), though it stops short of a formal validate→fix→retry feedback loop and the 'git diff' review is only suggested.	4 / 5
Progressive Disclosure	Section structure is good and the seven scripts are properly externalized into a real scripts/ bundle, but the body references seven template files under templates/ that do not exist in the bundle — broken references that would dead-end an agent following the skill.	3 / 5
	Total	14 / 20 Passed

Description

100%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.

A strong, third-person description that concretely states what the skill does across three audiences and gives explicit, natural trigger phrases including multiple slash-command forms. It is comprehensive, distinct, and free of vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across three distinct audiences — 'workflows for non-technical readers, architecture for developers, and AI orientation for agents' — plus 'Deterministic JS scripts handle structural extraction; the agent writes the prose', giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (generate multi-audience documentation from a codebase) and 'when' (an explicit 'Use when...' clause listing concrete trigger phrases and slash-command forms), matching the anchor for clear what-and-when with concrete triggers.	5 / 5
Trigger Term Quality	Includes natural user phrasings and concrete invocations — 'document this project', '/document-this', '/document-this <file-path>', '/document-this --focus "<Feature Name>"', and 'wants fresh documentation reflecting the current codebase state' — covering the common ways a user would request this.	5 / 5
Distinctiveness Conflict Risk	The multi-audience documentation niche plus the bespoke '/document-this' slash-command triggers and '--focus' deep-dive form carve a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	20 / 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
relative_links	Relative link issues: 1 missing, 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: RoleModel/rolemodel-skills
Path: skills/document-this/SKILL.md
Commit: 6695348

Reviewed: 3 days 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.