CtrlK
BlogDocsLog inGet started
Tessl Logo

iii-engine-config

Configure a managed iii engine through worker-compose.yaml or a directly supervised engine through config.yaml. Use for engine ports, RBAC via the rbac-proxy worker, streams, sandboxes, and configuration storage.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

90%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.

An excellent, lean reference: complete executable YAML and CLI examples for both engine modes, hard operational rules, and a well-signaled external schema link. The only real improvement areas are weaving the verification commands (compose::status, engine::workers::list) into the workflows as explicit checkpoints and moving the inline rbac-proxy settings reference to a bundle file.

DimensionReasoningScore

Conciseness

The body is dense, imperative iii-specific fact ("The presence of `engine:` means that Compose owns the engine process"; "Do not mix them"; expansion syntax, state-dir layout, injected workers) with no padding and nothing that explains concepts Claude already knows. Not 4 because there is no identifiable over-explanation to trim — every token carries skill-specific information.

5 / 5

Actionability

Fully executable, copy-paste-ready guidance: complete YAML blocks for both managed and directly supervised modes, exact commands ("iii compose --namespace orders-daemon --up --file worker-compose.yaml", "iii trigger -n orders-daemon compose::add worker=rbac-proxy"), and a concrete rbac-proxy settings block. Not 4 because the examples are complete and runnable rather than concrete-with-minor-gaps.

5 / 5

Workflow Clarity

Mode selection is unambiguous ("Do not mix them"), each mode has a clear config-then-start sequence, and verification commands exist ("Use `compose::status` for process ownership and `engine::workers::list` for live connections"). Not 5 because those checks sit in a bullet list rather than being woven into the workflows as explicit validate-then-proceed steps with a fix-and-retry loop; not 3 because sequence and checkpoints are both present, just not integrated.

4 / 5

Progressive Disclosure

Well-organized sections with a clearly signaled one-level external pointer ("Full schema: https://workers.iii.dev/workers/rbac-proxy") and no nested references; the skill is self-contained with no bundle files. Not 5 because at ~140 lines the full rbac-proxy settings reference is inlined bulk material that could live in a separate reference file; not 3 because structure is good and nothing is buried.

4 / 5

Total

18

/

20

Passed

Description

87%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 states both configuration modes concretely, includes an explicit 'Use for...' clause with concrete trigger topics, and occupies a well-delineated niche with file-name-based triggers. The only gaps are mild: a single action verb and no synonym coverage in the trigger terms.

DimensionReasoningScore

Specificity

Names both configuration modes with their exact files ("through worker-compose.yaml or a directly supervised engine through config.yaml") and concrete capability areas ("engine ports, RBAC via the rbac-proxy worker, streams, sandboxes, and configuration storage"). Not 5 because the only action verb is "Configure" — the enumeration is of topics rather than a comprehensive list of concrete actions.

4 / 5

Completeness

Explicitly answers both what ("Configure a managed iii engine through worker-compose.yaml or a directly supervised engine through config.yaml") and when ("Use for engine ports, RBAC via the rbac-proxy worker, streams, sandboxes, and configuration storage") with concrete trigger phrases, matching the anchor-5 pattern. Not 4 because the 'when' clause is fully explicit rather than weakly implied.

5 / 5

Trigger Term Quality

Good natural keyword coverage: "engine ports", "RBAC", "rbac-proxy", "streams", "sandboxes", "configuration storage", plus the file names users would actually mention. Not 5 because it lacks synonyms or variations beyond this single phrasing (e.g., engine setup, worker configuration, compose file).

4 / 5

Distinctiveness Conflict Risk

Clear niche (iii engine configuration) with triggers tied to proprietary file and worker names ("worker-compose.yaml", "config.yaml", "rbac-proxy worker"), giving minimal conflict risk with generic skills. Not 4 because these name-level triggers make it clearly distinguishable rather than merely mostly distinct.

5 / 5

Total

18

/

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.