CtrlK
BlogDocsLog inGet started
Tessl Logo

documentation-criteria

Determines which of PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires, and where each is stored. Use when deciding documentation scope, or when creating or reviewing a technical document.

68

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 instruction-only skill: the body handles routing decisions while all document content is properly delegated to one-level-deep reference templates. The main improvement room is tightening a few ornate criterion sentences and deduplicating the template link listings.

Suggestions

Tighten the abstract criterion language (e.g. "one evident repository-supported implementation within one responsibility boundary") with a concrete example or two, since these determine the Small/Medium/Large classification that drives the whole routing decision.

Deduplicate the template links — the Storage Locations table and the References section both link all six templates; keeping one clearly-signaled index would trim tokens without losing navigation.

Add a brief validation or re-classification step for edge cases (e.g. what to do when repository evidence contradicts the initially chosen Structural Scale), which would close the workflow-clarity gap.

DimensionReasoningScore

Conciseness

The body is dense and purpose-built — no explanation of concepts Claude already knows — but phrases like "An unfilled section becomes a guess made later by the consumer named below, with no record of what was assumed" and "Counts of files, consumers, nesting levels, states, steps, and asynchronous operations are supporting evidence rather than ADR criteria" are more ornate than needed, and the six template links appear twice (Storage Locations table and the References section). Mostly lean with minor trims available, so it fits the 4 anchor rather than the every-token-earns-its-place 5.

4 / 5

Actionability

Concrete, executable guidance throughout: an exact creation decision matrix, numbered path construction ("1. Select the base path from Structural Scale. 2. Insert an applicable UI Spec immediately before the Design Doc."), two explicit ADR filters, and a storage table with literal paths and naming conventions ("ADR-[4-digits]-[title].md"). It stays at 4 rather than 5 because judgment criteria like "one evident repository-supported implementation within one responsibility boundary" require interpretation rather than being fully copy-paste decidable.

4 / 5

Workflow Clarity

The multi-step process is clearly sequenced — base path selection, UI Spec insertion, ADR batch insertion — with an explicit approval checkpoint ("Continue after PRD approval") and a check-first step ("check existing ADRs first"). It misses the 5 anchor because there are no validation/feedback steps (e.g. how to re-classify scale when evidence is ambiguous), though the skill is non-destructive so no cap applies.

4 / 5

Progressive Disclosure

The body is a pure routing overview and every detail document lives in a bundle file referenced exactly one level deep via clearly signaled links (Storage Locations table plus a consolidated References section listing all six verified templates in references/). Content is appropriately split with easy navigation, matching the top anchor.

5 / 5

Total

17

/

20

Passed

Description

87%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 description: third person, concise, with an explicit "Use when..." clause and concrete named document types. It clearly communicates both capability and trigger conditions with minimal conflict risk.

DimensionReasoningScore

Specificity

"Determines which of PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires, and where each is stored" names the domain plus two concrete actions (deciding required documents, and their storage locations). It falls short of the comprehensive anchor because it omits other capabilities the body actually covers, such as routing/creation order and ADR decision filtering.

4 / 5

Completeness

It explicitly answers what ("Determines which of PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires, and where each is stored") and when ("Use when deciding documentation scope, or when creating or reviewing a technical document") with concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Natural keywords include "PRD, ADR, UI Spec, Design Doc, and Work Plan", "documentation scope", "creating or reviewing a technical document" — phrases a user would plausibly say. A few common variations are missing (e.g. "requirements doc", "architecture decision record", "spec"), keeping it below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

The five named document types (PRD, ADR, UI Spec, Design Doc, Work Plan) give it a clear niche with distinct triggers. The only mild overlap is with generic technical-writing skills via "creating or reviewing a technical document", which is too weak to reduce it below the top anchor.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
shinpr/claude-code-workflows
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.