test-grab

Test grab system (distance grab, one-hand grab, two-hand grab) against the grab example using the iwsdk CLI.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and concise with excellent workflow sequencing and validation checkpoints. Its only weakness is progressive disclosure: everything is inline in one long file with no reference files to offload detail.

Suggestions

Extract the command/component reference table and per-suite assertions into a referenced file (e.g. references/suites.md) and signal it from the body, keeping SKILL.md as a lean overview.

List bundle files under references/ so progressive disclosure can be scored against an actual file structure rather than an inline monolith.

Dimension	Reasoning	Score
Conciseness	The body is dense with executable commands, assertions, and sleeps, with no padding or explanation of concepts Claude already knows; every token earns its place despite the length, which is justified by the 5-suite scope.	3 / 3
Actionability	Provides fully executable `npx iwsdk` commands with concrete JSON inputs and exact assertions, copy-paste ready with no pseudocode.	3 / 3
Workflow Clarity	Steps 1-5 are clearly sequenced with explicit validation checkpoints ("Assert:" statements, server-failure FAIL paths) and a Recovery section giving a feedback loop for transient errors.	3 / 3
Progressive Disclosure	Well-organized into sections and suites but the entire workflow plus the inline component reference table lives in a single monolithic file with no reference layer; content that could be split (e.g. command/component reference) is inline rather than signaled one level deep.	2 / 3
	Total	11 / 12 Passed

Description

82%

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 and distinctive with strong natural trigger terms, but it omits explicit "Use when..." guidance, capping completeness at 2. Adding a trigger clause would raise it to a top score.

Suggestions

Append an explicit trigger clause, e.g. "Use when testing grab interactions in an IWSDK example, or when the user asks to verify distance/one-hand/two-hand grab behavior."

Keep the concrete action list but pair it with the when-to-use context to fully answer both 'what' and 'when'.

Dimension	Reasoning	Score
Specificity	Names three concrete grab variants ("distance grab, one-hand grab, two-hand grab") and the exact tool ("iwsdk CLI"), matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	It states what the skill does ("Test grab system ... using the iwsdk CLI") but lacks any "Use when..." clause or equivalent trigger guidance, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Includes natural terms a user would say ("grab", "distance grab", "one-hand grab", "two-hand grab", "iwsdk CLI") with good coverage of likely trigger phrasings.	3 / 3
Distinctiveness Conflict Risk	The niche is narrow (testing a specific grab example via the iwsdk CLI) with distinct triggers unlikely to overlap with unrelated skills.	3 / 3
	Total	11 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: facebook/immersive-web-sdk
Commit: 42af866

Reviewed: 6 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.