Documentation creation criteria including PRD, ADR, Design Doc, and Work Plan requirements with templates. Use when creating or reviewing technical documents, or determining which documents are required.
58
66%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/documentation-criteria/SKILL.mdQuality
Discovery
75%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 a solid description that clearly communicates its purpose and includes an explicit 'Use when' clause with multiple trigger scenarios. Its main weakness is that it could be more specific about the concrete actions it performs (e.g., generating templates, validating completeness, suggesting structure) and could expand its trigger terms to include common synonyms and abbreviation expansions.
Suggestions
Add more concrete actions like 'Generates templates, validates document completeness, and suggests required sections for PRDs, ADRs, Design Docs, and Work Plans'
Expand trigger terms to include full forms and synonyms: 'product requirements document', 'architecture decision record', 'RFC', 'spec', 'technical specification'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (documentation creation) and lists specific document types (PRD, ADR, Design Doc, Work Plan), but doesn't describe concrete actions beyond 'creation criteria' and 'templates'. It doesn't specify what actions are performed on these documents (e.g., generating from templates, validating against criteria, etc.). | 2 / 3 |
Completeness | Clearly answers both 'what' (documentation creation criteria including PRD, ADR, Design Doc, and Work Plan requirements with templates) and 'when' (Use when creating or reviewing technical documents, or determining which documents are required). The 'Use when...' clause is explicit with multiple trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes useful terms like 'PRD', 'ADR', 'Design Doc', 'Work Plan', and 'technical documents', which users might naturally say. However, it misses common variations like 'product requirements document', 'architecture decision record', 'RFC', 'spec', 'specification', or 'documentation template'. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on specific document types (PRD, ADR, Design Doc, Work Plan) and the criteria/templates angle creates a clear niche. It's unlikely to conflict with general writing or coding skills, as it targets a well-defined set of technical documentation artifacts. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive documentation governance skill with strong organizational structure and clear decision criteria for when to create each document type. Its main weaknesses are verbosity in document definitions (explaining what each document type is rather than focusing on what Claude needs to do differently), lack of concrete examples of good vs. bad document outputs, and missing validation/feedback loops in the creation workflow.
Suggestions
Add a concrete before/after example showing a good acceptance criterion or a filled-out section from one of the templates to improve actionability.
Trim the 'Detailed Document Definitions' section by removing scope boundary statements (which repeat what's already implied by the purpose) and reducing explanatory text that Claude can infer from the templates themselves.
Add explicit validation checkpoints to the Creation Process—e.g., 'After creating PRD, verify all acceptance criteria have sequential IDs and measurable conditions before proceeding to Design Doc.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly dense with useful information, but includes some verbose sections that could be tightened—e.g., the detailed 'Detailed Document Definitions' section repeats scope boundaries multiple times and explains concepts (like what a PRD or ADR is) that Claude likely already knows. The YAML-style structural elements and extensive tables add bulk but are mostly justified. | 2 / 3 |
Actionability | The decision matrix and ADR conditions provide concrete, specific guidance for when to create documents. However, the skill lacks executable examples—there are no concrete examples of filled-out documents, no sample commands, and the guidance is largely descriptive ('Include measurable conditions') rather than demonstrating exactly what a good output looks like. Templates are referenced but not provided in the bundle. | 2 / 3 |
Workflow Clarity | The Creation Process section provides a 4-step sequence (Problem Analysis → ADR Option Consideration → Creation → Approval), and the decision matrix gives clear creation order. However, there are no validation checkpoints or feedback loops—no guidance on what to do if a document fails review, no explicit verification steps between document creation stages, and the approval step is vague ('Accepted after review enables implementation'). | 2 / 3 |
Progressive Disclosure | The skill has excellent progressive disclosure structure: a clear overview with decision matrix up front, well-organized sections for detailed definitions, and clear one-level-deep references to six template files with consistent paths. The Templates section at the top provides clear navigation to all referenced files, and the Storage Locations table reinforces the structure. | 3 / 3 |
Total | 9 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
68ecb4a
Table of Contents
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.