Create a new QA test procedure for a feature
Install with Tessl CLI
npx tessl i github:jpoutrin/product-forge --skill create-qa-test60
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
22%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 description is too brief and lacks the detail needed for effective skill selection. It fails to specify concrete actions, omits trigger guidance entirely, and doesn't differentiate itself from other potential testing-related skills. The description reads more like a task title than a skill description.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user asks to create test cases, write QA procedures, document testing steps, or needs a test plan for a new feature'
Expand the capabilities with specific actions: 'Creates structured QA test procedures including test steps, expected results, preconditions, and acceptance criteria'
Include natural trigger terms users would say: 'test case', 'test plan', 'manual testing', 'QA documentation', 'acceptance testing'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language with only one abstract action ('Create'). It doesn't specify what kind of test procedure, what format, what steps are involved, or what the output looks like. | 1 / 3 |
Completeness | Only partially answers 'what' (create a test procedure) and completely missing 'when' - there's no 'Use when...' clause or explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords ('QA', 'test procedure', 'feature') that users might say, but missing common variations like 'test case', 'test plan', 'testing', 'quality assurance', or file format mentions. | 2 / 3 |
Distinctiveness Conflict Risk | Somewhat specific to QA testing domain, but could overlap with other testing-related skills (unit tests, integration tests, test automation). The term 'feature' is generic and doesn't help distinguish it. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides excellent actionable guidance with clear workflows and validation steps, making it highly usable for Claude. However, it suffers from poor progressive disclosure - the 300+ line document includes full templates and detailed procedures that should be split into separate reference files. The content is valuable but the structure makes it token-inefficient.
Suggestions
Move the full file template to a separate `QA-TEST-TEMPLATE.md` file and reference it with a single link
Extract the 'Final Review: Screenshot Integration' section (50+ lines) to a separate `QA-SCREENSHOT-VALIDATION.md` file
Create a concise overview section at the top (under 30 lines) covering: command syntax, basic example, and links to detailed references
Consolidate the repeated screenshot path examples into a single reference table in a separate file
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes significant verbosity. The full file template (~60 lines) and extensive screenshot integration sections could be moved to separate reference files. Some sections repeat information (e.g., screenshot paths mentioned multiple times). | 2 / 3 |
Actionability | Provides fully executable guidance with concrete examples, specific file paths, exact command syntax, and copy-paste ready templates. The validation checklist and auto-fix sections give precise steps Claude can follow. | 3 / 3 |
Workflow Clarity | Clear numbered sequences throughout (5-step execution instructions, 6-step validation checklist). Includes explicit validation checkpoints ('VERIFY: All image paths are valid') and feedback loops ('IF missing references... Add... VERIFY... REPORT'). | 3 / 3 |
Progressive Disclosure | Monolithic structure with everything inline. The full file template, screenshot integration details, and validation steps should be in separate reference files. Related commands/skills are mentioned but the main content is a wall of text with no clear separation of overview vs. detailed reference material. | 1 / 3 |
Total | 9 / 12 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
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.