iii-browser-sdk
Browser SDK for connecting to the iii engine from web applications via WebSocket. Use when building browser-based clients that register functions, invoke triggers, or consume streams from the frontend.
90
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is a strong skill description that clearly identifies a specific domain (browser SDK for the iii engine), lists concrete actions (register functions, invoke triggers, consume streams), and provides explicit trigger guidance via a 'Use when' clause. The description is concise, uses third-person voice, and includes natural keywords developers would use when working with browser-based WebSocket clients.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'connecting to the iii engine from web applications via WebSocket', 'register functions', 'invoke triggers', 'consume streams from the frontend'. These are distinct, concrete capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (Browser SDK for connecting to the iii engine via WebSocket, registering functions, invoking triggers, consuming streams) and 'when' (explicit 'Use when building browser-based clients that register functions, invoke triggers, or consume streams from the frontend'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords a developer would use: 'Browser SDK', 'WebSocket', 'web applications', 'browser-based clients', 'register functions', 'invoke triggers', 'consume streams', 'frontend'. Good coverage of terms a user building browser clients would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: browser-specific SDK for the iii engine via WebSocket. The combination of 'Browser SDK', 'iii engine', 'WebSocket', and 'frontend' creates a very specific scope unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 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.
A solid browser SDK skill with a clear, executable quick start and a useful API reference table. The main weaknesses are some redundancy between sections (Common Patterns overlaps Quick Start) and boilerplate meta-sections (When to Use, Boundaries) that don't add actionable value for Claude. Overall it's functional and well-structured for its purpose.
Suggestions
Remove or significantly trim the 'When to Use' and 'Boundaries' sections — these are meta-instructions Claude can infer and they consume tokens without adding actionable guidance.
Consolidate 'Common Patterns' into the Quick Start or remove duplicated content (e.g., registerWorker, trigger calls appear in both sections).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with a good API table and quick start example, but includes unnecessary sections like 'When to Use' and 'Boundaries' that explain meta-concerns Claude can infer, and 'Common Patterns' partially duplicates the quick start. The 'Pattern Boundaries' section is useful but could be tighter. | 2 / 3 |
Actionability | The quick start provides fully executable TypeScript code showing connection, function registration, and trigger invocation with different action modes. The API table gives concrete function signatures, and common patterns show specific connection URLs and usage. | 3 / 3 |
Workflow Clarity | This is a simple SDK skill (connect, register, invoke) without destructive or batch operations. The quick start demonstrates the natural sequence clearly: connect → register function → trigger. No multi-step validation is needed for this use case. | 3 / 3 |
Progressive Disclosure | References to related skills (iii-node-sdk, iii-realtime-streams, etc.) and external docs are present, but there are no bundle files to support deeper content. The inline content is reasonably sized but the API reference link is the only external documentation pointer, and some sections like 'Common Patterns' could be split or better organized. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- iii-hq/iii
- Commit
d51a06d
- Reviewed
Table of Contents
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.