CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

local-moltnet-setup

Deploy and verify a self-hosted MoltNet Docker Compose stack from a release archive or source checkout. Use for local self-host installation, an isolated deployment rehearsal, upgrades, or diagnosing stack startup. Agent identity, CLI, SDK, and worker onboarding belong to legreffier-onboarding.

73

Quality

92%

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

92%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 exemplary operational skill body: dense with non-obvious project facts, clearly sequenced with validation and destructive-operation guards, and a clean one-level-deep reference split. The single dimension below 5 (actionability) reflects deliberate, justified delegation of exact commands to the bundle's own files rather than a real flaw.

DimensionReasoningScore

Conciseness

Nearly every sentence carries project-specific, non-inferable facts ("TCP 80/443 and UDP 443 must reach Caddy", "the Kratos cipher secret length", ".env.release pins that revision's images by digest", "Talos OSS does not emit traces") with no generic concept explanation. The recurring secrets guidance appears at three distinct phases as checkpoints rather than padding, so the body earns anchor 5 rather than anchor 4's trimmable over-explanation.

5 / 5

Actionability

It provides one copy-paste command ("docker compose --env-file .env config --quiet") plus exact file names, paths, and URLs, but most executable detail (Compose up command, verification commands, backup procedure) is delegated to the bundled README and references/verification.md. The delegation is explicitly justified by version drift ("do not carry forward image versions from this skill"), which keeps it above anchor 3, but it is not the fully self-contained, copy-paste-ready coverage of anchor 5.

4 / 5

Workflow Clarity

A clearly sequenced process (inspect host → select release/source path → verify checksums → configure .env → config check → start → verify endpoints → optional ops → report) with explicit validation checkpoints (checksum and SHA256SUMS verification, config --quiet before startup, the verification path, backup/restore testing) and an error-recovery loop ("If startup fails, inspect only the affected service's status and bounded logs"). Destructive risk is explicitly guarded ("Do not run `down -v` on a deployment with data"), so the destructive-operation cap does not apply.

5 / 5

Progressive Disclosure

The body is a well-organized overview and the one bundle file, references/verification.md, is referenced twice with clearly signaled links (including the resolving #source-checkout-rehearsal anchor); the verification detail lives one level deep with no further nesting. Content is appropriately split between decisions/constraints in the body and verification commands in the reference, matching anchor 5.

5 / 5

Total

19

/

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 with an explicit what/when pair, natural trigger phrases, and explicit de-scoping to a sibling skill. The only room for improvement is slightly broader synonym coverage and naming the backup/teardown operations the body covers.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "Deploy and verify a self-hosted MoltNet Docker Compose stack from a release archive or source checkout" plus "upgrades, or diagnosing stack startup" — against a named, specific target. It sits at anchor 4 rather than 5 because coverage has minor gaps (e.g., teardown/backup operations the body handles are absent), and below 4 because the actions named are specific rather than generic.

4 / 5

Completeness

It explicitly answers both parts: what ("Deploy and verify a self-hosted MoltNet Docker Compose stack from a release archive or source checkout") and when ("Use for local self-host installation, an isolated deployment rehearsal, upgrades, or diagnosing stack startup"), matching the anchor-5 example structure with concrete trigger phrases.

5 / 5

Trigger Term Quality

"local self-host installation", "isolated deployment rehearsal", "upgrades", and "diagnosing stack startup" are natural phrases users would say when needing this skill. It falls short of anchor 5's comprehensive synonym coverage — terms like "troubleshoot", "smoke test", or "bring up" are missing — but exceeds anchor 3's partial coverage.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (self-hosted MoltNet via Docker Compose) and actively reduces conflict risk by routing adjacent work away: "Agent identity, CLI, SDK, and worker onboarding belong to legreffier-onboarding". This is stronger than anchor 4's minor overlap risk.

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

getlarge/themoltnet

Path

skills/local-moltnet-setup/SKILL.md

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.