Test grab system (distance grab, one-hand grab, two-hand grab) against the grab example using the iwsdk CLI.
56
63%
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 ./.claude/skills/test-grab/SKILL.mdQuality
Discovery
50%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 specific about the concrete actions and tools involved, and occupies a clear niche that is unlikely to conflict with other skills. However, it completely lacks a 'Use when...' clause, which significantly hurts completeness and makes it harder for Claude to know when to select this skill. The trigger terms are domain-specific and may not match how users naturally phrase requests.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to test or validate grab interactions, run grab tests, or use the iwsdk CLI for grab system verification.'
Include natural language variations users might say, such as 'test grabs', 'grab testing', 'VR interaction testing', or 'run grab example'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'distance grab, one-hand grab, two-hand grab' testing against a grab example using a specific CLI tool ('iwsdk CLI'). | 3 / 3 |
Completeness | Describes what it does (test grab system against grab example using iwsdk CLI) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric should cap completeness at 2, and the 'when' is entirely missing, placing it at 1. | 1 / 3 |
Trigger Term Quality | Includes relevant domain-specific terms like 'grab system', 'distance grab', 'one-hand grab', 'two-hand grab', 'iwsdk CLI', but these are fairly technical. Missing common variations a user might say like 'test grabs', 'grab testing', 'VR grab', or 'interaction system'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche: testing a grab system with the iwsdk CLI. The combination of 'grab system', specific grab types, and 'iwsdk CLI' makes it highly unlikely to conflict with other skills. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and well-structured test procedure with excellent workflow clarity, explicit validation checkpoints, and recovery procedures. The main weakness is its length as a single monolithic file — the 5 detailed test suites could benefit from being split into referenced files. The content is mostly efficient but has minor redundancies in explanations (trigger vs squeeze mentioned in multiple places).
Suggestions
Consider splitting individual test suites into separate referenced files (e.g., SUITE_1_DISTANCE_GRAB.md) to improve progressive disclosure and keep the main SKILL.md as a concise overview with navigation links.
Remove the duplicate explanation of trigger vs squeeze — keep it in the Component Reference table and reference that section from Known Issues instead of restating it.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~300+ lines) but most content is necessary executable commands and assertions. Some sections like the Component Reference table and Known Issues are valuable. However, there's mild redundancy (e.g., the trigger vs squeeze distinction is explained both in the Component Reference table and again in Known Issues). The overall length is justified by the complexity of 5 test suites, but could be tightened slightly. | 2 / 3 |
Actionability | Every step provides exact CLI commands with concrete JSON arguments, specific assertions to check, and clear expected outcomes. Commands are copy-paste ready (with placeholder substitution), and the skill specifies exact component names, button indices, positions, and timeout values. The distinction between trigger and squeeze is made explicit with the exact CLI subcommands. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced from install → start server → verify connectivity → run test suites → cleanup. Each test has explicit validation assertions, snapshots before/after for diffing, and sleep commands for timing. The Recovery section provides a clear retry loop for transient failures. Pre-test setup includes validation (checking for error logs). The skill explicitly states to run commands one at a time and verify before proceeding. | 3 / 3 |
Progressive Disclosure | The content is a single monolithic file with no references to external documentation. For a skill of this length and complexity, splitting detailed test suites into separate files or at least having a concise overview section with links to suite details would improve navigability. However, the use of clear headers, numbered steps, and suite separation provides reasonable internal organization. | 2 / 3 |
Total | 10 / 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 | |
3a08b40
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.