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 listeners, streams, sandboxes, and configuration storage.

66

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/iii-engine-config/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tightly written, highly actionable reference with executable YAML and command examples covering both engine modes, plus clear security, lifecycle, and boundary guidance. Its only weakness is the absence of an explicit validate-then-retry feedback loop for the restart/migration operations, which keeps workflow clarity at 4.

Suggestions

Add an explicit validation gate before destructive/lifecycle actions (e.g., run `iii compose --namespace ... compose::status` to confirm ownership before restarting after an `engine:` change), with a fix-and-retry loop, to lift workflow clarity to 5.

Trim the `${VAR:default}` materialization mechanics note to the essential rule to push conciseness toward the 5-anchor.

Consider extracting the per-worker configuration reference (the allowed base names and `#instance` rules) into a short separate reference file referenced from the overview, which would let progressive disclosure reach 5 without losing actionability.

DimensionReasoningScore

Conciseness

The body is lean with no padding or explanations of concepts Claude already knows; each section earns its place, though a couple of mechanics sentences (e.g. the `${VAR:default}` materialization note) could be trimmed, matching the 'efficient; minor instances of over-explanation' anchor rather than the 5-anchor's every-token-earns-its-place bar.

4 / 5

Actionability

Provides complete, copy-paste-ready YAML blocks for both engine modes plus exact `iii compose`/`iii --config` commands with flags, the `compose::add` trigger invocation, the allowed worker base-name list, and the concrete `UNSUPPORTED_CONFIG_WORKERS` failure mode — fully executable guidance covering the common cases, matching the 5-anchor.

5 / 5

Workflow Clarity

Each mode is clearly sequenced (config then start command) with concrete checkpoints (`compose::status`, `engine::workers::list`) and explicit failure behavior, but restart/clean-shutdown operations lack an explicit validate-before-act feedback loop, capping it at 4 rather than the 5-anchor's explicit error-recovery loop.

4 / 5

Progressive Disclosure

The body is well-organized into clearly headed sections (Managed Compose, Directly supervised, Security and operations, When to Use, Boundaries) with no nested or buried references and content appropriately contained in one file; it sits at 4 rather than 5 because it is a single dense file rather than an overview pointing outward, though nothing genuinely needs splitting.

4 / 5

Total

17

/

20

Passed

Description

75%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 focused, well-scoped description that states both what it configures and when to use it with concrete, third-person trigger terms. It is slightly short of the top anchor because the action list and trigger synonyms could be marginally more comprehensive.

DimensionReasoningScore

Specificity

Names the two concrete configuration modes (managed via worker-compose.yaml, supervised via config.yaml) and lists specific targets (ports, RBAC listeners, streams, sandboxes, configuration storage), matching the 'lists several specific actions; minor gaps' anchor rather than the 5-anchor's maximal action list.

4 / 5

Completeness

Provides a clear 'what' (configure managed or supervised engines through the named files) and an explicit 'Use for ...' trigger list answering 'when', but the 'when' clause could be more specific/explicit, placing it at 4 rather than the 5-anchor's maximally explicit trigger phrases.

4 / 5

Trigger Term Quality

Includes natural user-facing terms like 'engine ports', 'RBAC listeners', 'streams', 'sandboxes', and the two file names, giving good keyword coverage with only a few synonyms/variations missing, so it sits at 4 rather than the 5-anchor's comprehensive synonym set.

4 / 5

Distinctiveness Conflict Risk

The iii-engine niche plus specific file names and components (RBAC listeners, sandboxes) make it mostly distinct with only minor overlap risk against related iii/compose skills, so 4 rather than 5 (some sibling-skill overlap remains) and clearly above 3.

4 / 5

Total

16

/

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.

Validation16 / 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.