CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

66

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/iii-getting-started/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

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

A well-structured, highly actionable getting-started guide with a clear step sequence and verification checkpoints. It falls short of excellent mainly on the missing error-recovery loop, the non-executable Rust snippet, and some redundant closing sections.

Suggestions

Wrap the Rust example in a runnable function (e.g., a `main()` returning `Result`) so all three language examples are copy-paste executable.

Add a brief troubleshooting step to the workflow (e.g., what to check if the worker fails to connect or the curl call returns an error) to create a validate-then-recover feedback loop.

Consolidate the redundant 'When to Use', 'Boundaries', 'Recommended Next Steps', and 'Pattern Boundaries' sections, which largely repeat the description and each other.

DimensionReasoningScore

Conciseness

The six-step guide is efficient and assumes competence, but the full Rust example and the 'When to Use'/'Boundaries' sections (which restate the description) plus redundancy between 'Recommended Next Steps' and 'Pattern Boundaries' could be trimmed.

4 / 5

Actionability

Commands and TypeScript/Python examples are copy-paste ready with an expected response shown, but the Rust block is a fragment (top-level `let` and `?` operator with no enclosing function), a minor executability gap.

4 / 5

Workflow Clarity

A clearly sequenced Steps 1-6 flow with explicit checkpoints (`iii --version`, expected JSON response for the curl test), but no error-recovery feedback loop (e.g., what to do if a worker fails to register or connect).

4 / 5

Progressive Disclosure

No bundle files exist; deeper material is delegated one level deep via clearly signaled sibling skills and doc URLs, with a 'Pattern Boundaries' routing section. Good structure, though the three inline language examples are detail-heavy content that could live in per-language references.

4 / 5

Total

16

/

20

Passed

Description

83%Weight 40%Scale 1-5

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 description that clearly states concrete capabilities and provides an explicit, multi-trigger 'Use when' clause in third person. Its only weaknesses are modest: missing common synonym phrasings and minor overlap with sibling iii skills.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Install the iii engine', 'set up your first worker') though 'get a working backend running' is outcome-generic rather than a specific action, leaving minor gaps in coverage.

4 / 5

Completeness

Explicitly answers both what (install engine, set up first worker, get a backend running) and when, with an explicit 'Use when' clause naming three concrete trigger scenarios.

5 / 5

Trigger Term Quality

Natural user phrasings like 'start a new iii project', 'install the SDK', and 'initial setup and configuration' are present, but common synonyms such as 'getting started', 'quickstart', or 'hello world' are missing.

4 / 5

Distinctiveness Conflict Risk

The iii-specific niche and setup-scoped triggers are distinct, but 'install the SDK' minorly overlaps sibling skills like iii-sdk-reference in the same skill family.

4 / 5

Total

17

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
iii-hq/iii
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.