click-target

Find and click a target object in XR. Use when testing UI interactions, clicking buttons, or verifying interactable elements work correctly.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%Weight 40%Scale 1-3

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

The body is a well-structured, highly actionable XR click workflow with explicit verification and retry feedback loops at every fragile step. It is token-efficient, uses concrete tool calls with specific parameters, and is appropriately organized as a single-file skill.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: each step is a concrete tool call with tight bullet sub-points and no explanatory filler about XR, controllers, or ECS basics. It is not a 2 because there is no padded explanation or unnecessary context to tighten.	3 / 3
Actionability	Every step names a specific, callable MCP tool (e.g., `mcp__iwsdk-dev-mcp__scene_get_runtime_hierarchy`, `xr_select`) with concrete parameters and numeric offsets like "offset x by +0.25". It is not a 2 because the guidance is fully executable rather than pseudocode or abstract direction.	3 / 3
Workflow Clarity	The 8 numbered steps are clearly sequenced with explicit verification checkpoints (screenshot in step 4, console-log verification in step 8) and feedback loops ("If not visible... moveToDistance", "If no logs match... adjust target position and retry"). It is not a 2 because validation and retry loops are explicit rather than implicit or missing.	3 / 3
Progressive Disclosure	The skill is a single, cohesive workflow organized into clear sections (Arguments, Workflow, Tips, Example) with no nested references and no content that needs splitting into separate files. It is not a 2 because the structure is well-signaled and there is no inline bulk that belongs in a referenced file.	3 / 3
	Total	12 / 12 Passed

Description

75%Weight 40%Scale 1-3

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 concise, third-person, and answers both what and when with an explicit trigger clause, anchoring it clearly in an XR niche. Its main weakness is limited trigger-term variation and only modest action specificity (find and click).

Suggestions

Broaden trigger terms to include natural variations a user might say, e.g., "tap", "press", "select", or "interact with UI in VR/XR".

Add one or two more concrete capabilities to the what clause (e.g., position the controller and verify the click via console logs) to lift specificity.

Dimension	Reasoning	Score
Specificity	"Find and click a target object in XR" names the XR domain and two concrete actions (find, click), matching the score-2 anchor of naming a domain with some actions. It is not a 3 because it does not list multiple distinct concrete actions like extract/fill/merge, only find-and-click.	2 / 3
Completeness	It explicitly states what it does ("Find and click a target object in XR") and includes an explicit "Use when..." trigger clause, satisfying both the what and the when. It is not a 2 because the trigger guidance is present and explicit rather than merely implied.	3 / 3
Trigger Term Quality	"testing UI interactions, clicking buttons, or verifying interactable elements" provides several natural trigger phrases a user might say, but coverage is narrow and misses common variations (e.g., tap, press, select, VR). It is not a 3 because the term set lacks the broad synonym coverage of the score-3 example.	2 / 3
Distinctiveness Conflict Risk	The XR-scoped niche ("in XR", controller-based clicking) and distinct triggers make it unlikely to fire for non-XR UI skills. It is not a 2 because the XR qualifier gives it a clear, non-overlapping niche rather than a generic UI scope.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: facebook/immersive-web-sdk
Path: .claude/skills/click-target/SKILL.md
Commit: 0fb2195

Reviewed: 7 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.