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.
85
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 an explicit 'Use when' clause with natural trigger terms and is highly distinctive due to the niche 'iii engine' domain. The main weakness is that the capability description could be slightly more specific about what concrete actions the skill teaches beyond basic installation and 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 distinct concrete capabilities. | 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 install, initial setup and configuration). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'new iii project', 'install the SDK', 'initial setup', 'configuration'. These cover the common ways a user would phrase getting started with the iii engine. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to the 'iii engine' ecosystem with distinct triggers like 'iii project', 'iii SDK', and 'first worker'. Unlikely to conflict with other skills due to the niche technology focus. | 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 has executable code and commands across three languages. The main weaknesses are the lack of validation/error-recovery steps in the workflow (e.g., what if the engine doesn't start or the worker fails to connect) and some redundant meta-sections (When to Use, Boundaries, Pattern Boundaries) that could be trimmed or consolidated.
Suggestions
Add validation checkpoints after Steps 3 and 5 (e.g., 'Verify the engine is running: check console at localhost:3000' and 'Verify worker connected: check engine logs for connection message')
Consolidate or remove the 'When to Use', 'Boundaries', and 'Pattern Boundaries' sections — these are meta-instructions that belong in frontmatter or can be reduced to a single short section
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary sections like 'When to Use', 'Boundaries', and 'Install Agent Skills' which are meta-instructions rather than actionable content. The three full language examples (TypeScript, Python, Rust) add significant length but are justified for a multi-language SDK. The 'Pattern Boundaries' section largely duplicates 'Recommended Next Steps'. | 2 / 3 |
Actionability | Every step includes fully executable, copy-paste ready commands and code. The install commands, SDK setup, worker code in three languages, and the curl test command are all concrete and complete. The expected response is also shown. | 3 / 3 |
Workflow Clarity | The 6-step sequence is clearly numbered and logical, but there are no validation checkpoints beyond the initial version check. There's 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 involves installing software and running services, error recovery guidance is missing. | 2 / 3 |
Progressive Disclosure | The skill provides a clear overview/quickstart inline and then points to specific skills (iii-state-management, iii-queue-processing, etc.) and external documentation links for deeper topics. References are one level deep and well-signaled with descriptive labels. | 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
8921efa
- 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.