iwsdk-planner

IWSDK project planning and best practices guide. Use when planning new IWSDK features, designing systems/components, reviewing IWSDK code architecture, or when the user asks about IWSDK patterns, ECS design, signals, or reactive programming in this codebase.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

A highly actionable, well-organized reference guide with strong code examples and clear planning workflows, undermined by verbosity/duplication and a monolithic structure with no progressive disclosure into separate reference files.

Suggestions

Split the long API reference (Core Components table, Core Systems table, component/system sections, enum listings) into files under references/ and keep SKILL.md as an overview that links to them one level deep.

De-duplicate content that appears twice — asset loading (section 14 vs 'Asset Loading (AssetManager)'), locomotion config, and component-design patterns — keeping a single canonical version.

Trim or relocate low-density prose (e.g. 'Tag component (no data, just marks entities)') that restates ECS concepts Claude already knows.

Dimension	Reasoning	Score
Conciseness	The ~1480-line body is mostly domain-specific reference Claude would not know, but it is padded with duplication — asset loading appears in section 14 and again under 'Asset Loading (AssetManager)', locomotion config and component-design examples recur, and the 'Reinvention Risk Table' / 'Built-in Visuals' overlap earlier sections — so it could be tightened considerably.	2 / 3
Actionability	Provides extensive copy-paste-ready TypeScript examples (component definitions, system patterns, query filters, World.create config) with concrete enum values and option objects.	3 / 3
Workflow Clarity	Includes clearly sequenced workflows — the 11-step 'When Planning a New Feature' checklist and the ordered 'Post-Creation Initialization Sequence' with system priorities — plus a feature decision matrix.	3 / 3
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are empty), and the body is a monolithic wall of API reference (component/system tables, enum listings) that the score-2 anchor describes as 'content that should be separate is inline'; the only external pointers are to project assets (Kenney catalog) and another skill, not skill-internal references.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that clearly states both what the skill does and when to use it, with specific domain actions and natural trigger terms. It is concise, distinctive, and avoids over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'planning new IWSDK features, designing systems/components, reviewing IWSDK code architecture' — tied to a specific domain rather than vague language.	3 / 3
Completeness	Explicitly answers what ('IWSDK project planning and best practices guide') and when ('Use when planning... or when the user asks about...') with explicit triggers, so it is not capped at 2.	3 / 3
Trigger Term Quality	Covers natural terms users would say ('IWSDK features', 'IWSDK code architecture', 'IWSDK patterns, ECS design, signals, or reactive programming'), with explicit 'when the user asks about' phrasing.	3 / 3
Distinctiveness Conflict Risk	The IWSDK niche is specific and anchored with 'in this codebase', giving distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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
skill_md_line_count	SKILL.md is long (1480 lines); consider splitting into references/ and linking	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.