iii-getting-started
Install the iii engine, set up your first worker, and get a working backend running. Use when a user wants to start a new iii project, install the SDK, or needs help with initial setup and configuration.
68
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Critical
Do not install without reviewing
Quality
Discovery
89%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 solid skill description that clearly communicates its purpose and when to use it. It benefits from a well-defined niche (iii engine setup) and an explicit 'Use when' clause with natural trigger terms. The main weakness is that the capability description could be slightly more specific about what concrete steps or outputs the skill provides beyond general setup.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (iii engine) and some actions (install, set up worker, get backend running), but the actions are somewhat general setup steps rather than multiple specific concrete operations. | 2 / 3 |
Completeness | Clearly answers both 'what' (install the iii engine, set up first worker, get a working backend running) and 'when' (explicit 'Use when' clause covering new project, SDK installation, initial setup and configuration). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'install', 'new iii project', 'SDK', 'initial setup', 'configuration', 'first worker', 'backend'. Good coverage of terms a user starting out would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to the 'iii engine' ecosystem with distinct triggers like 'iii project', 'SDK', and 'first worker'. Unlikely to conflict with other skills due to the niche domain. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid getting-started skill with excellent actionability — every step is concrete and executable with a clear end-to-end flow from install to test. The main weaknesses are verbosity from including three full language examples inline and overlapping boundary/scope sections, plus the lack of error recovery guidance at intermediate steps. Trimming to one primary language example (with others referenced) and adding troubleshooting hints would significantly improve it.
Suggestions
Consider showing only one language example inline (e.g., TypeScript) and linking to Python/Rust examples in a separate file to reduce token cost.
Add brief troubleshooting guidance after Steps 3 and 6 (e.g., 'If the engine fails to start, check that port 49134 is not in use' or 'If you get a connection refused error, ensure the engine is running').
Consolidate the 'Pattern Boundaries', 'When to Use', and 'Boundaries' sections into a single concise section to reduce redundancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill provides three full language examples (TypeScript, Python, Rust) which is thorough but verbose — most users will only need one. The 'When to Use', 'Boundaries', and 'Pattern Boundaries' sections overlap significantly. The intro sentence explaining what iii replaces is useful context, but sections like 'Install Agent Skills' feel like marketing rather than actionable setup guidance. | 2 / 3 |
Actionability | Every step includes fully executable, copy-paste-ready commands and code. The install, create, start, SDK install, worker code, and test curl command form a complete end-to-end workflow with concrete expected output. | 3 / 3 |
Workflow Clarity | The six steps are clearly sequenced and logically ordered, and the final test step serves as a validation checkpoint. However, there are no error recovery steps — no guidance on what to do if the engine fails to start, if the worker doesn't connect, or if the curl test returns an error. For a setup workflow that can fail at multiple points, explicit validation/troubleshooting at intermediate steps would improve reliability. | 2 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled references to other skills (iii-state-management, iii-queue-processing, etc.) and external documentation links. Content is appropriately scoped to getting started, with explicit pattern boundaries directing users to more specific skills for advanced topics. | 3 / 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
a7ebbbb
- 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.