CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

deploy-qm

Deploy the QM package from an organization-owned deployment repository to Fly.io, AWS, or Render, onboard an administrator, configure connectors, and optionally activate Slack.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

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 tight, well-structured overview that delegates detail appropriately and includes concrete commands, config keys, and an explicit acceptance criterion. The main gaps are that the full executable workflow and validation loops are externalized to deployment.md, and the provider reference files are not individually named.

DimensionReasoningScore

Conciseness

The ~200-word body is lean and assumes Claude's competence — no explanations of what Fly.io, OIDC, or email transports are; every sentence is operational ("Collect both in the same pass", "Do not require or clone the QM source repository"). The two mentions of `references/email.md` give distinct timing cues rather than padding, so nothing reads as trimmable over-explanation.

5 / 5

Actionability

Provides concrete, executable anchors: `npm exec qm -- <command>`, `qm admin-login`, the `modelProvider` config key, and an explicit acceptance criterion ("A web response without a generated sidebar title is not a completed deployment"). Not 5 because the full command workflow is deferred to `deployment.md` and `npm exec qm -- <command>` is a template with a placeholder; comfortably above anchor 3 since real commands and precise file pointers are given.

4 / 5

Workflow Clarity

Sequencing is clear: read `deployment.md` as the authoritative workflow, read only the selected provider reference, collect the base model key and sign-in method in the same pass, read `references/email.md` before collecting email secrets, read `references/slack.md` only when Slack is requested, then complete acceptance checks. An explicit checkpoint exists ("Do not stop at infrastructure health") with the sidebar-title criterion, but the full acceptance checklist and error-recovery loops live in the external `deployment.md`, which keeps it below anchor 5.

4 / 5

Progressive Disclosure

Good structure against the actual bundle: the body is a lean overview, `references/email.md` and `references/slack.md` are explicitly named with clear load conditions, and the six reference files (aws, email, fly, porter, render, slack) sit one level deep. Not 5 because the body says "Read only the selected provider reference" without ever naming the provider files (fly.md, aws.md, render.md, porter.md), and porter.md is never mentioned anywhere — minor navigation gaps that require listing the directory to map provider to file.

4 / 5

Total

17

/

20

Passed

Description

70%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 specific, distinctive description with concrete actions and natural trigger terms, but it omits any "when to use" guidance, which caps its completeness. Adding an explicit trigger clause would lift the weakest dimension.

Suggestions

Add an explicit 'Use when...' clause, e.g., "Use when deploying or updating the QM package, onboarding a QM administrator, or activating QM's Slack integration" — its absence currently caps completeness at 3.

Make "configure connectors" concrete by naming which connectors (e.g., email/Slack/OIDC) so the capability list is comprehensive rather than partially generic.

The bundle contains references/porter.md, but the description lists only Fly.io, AWS, and Render — either mention Porter as a target or clarify the supported provider set to keep triggers aligned with the actual skill.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Deploy the QM package from an organization-owned deployment repository to Fly.io, AWS, or Render", "onboard an administrator", "configure connectors", "optionally activate Slack" — with named platforms. Not 5 because "configure connectors" is generic and coverage has minor gaps (no mention of validation/handoff); well above the 1-2-action level of anchor 3.

4 / 5

Completeness

The "what" is clear and multi-part (deploy to a named platform, onboard admin, configure connectors, activate Slack), but there is no "Use when..." clause or equivalent explicit trigger guidance anywhere, capping completeness at 3 per the judging guidelines. This matches anchor 3 exactly: clear what, when missing entirely rather than weakly implied.

3 / 5

Trigger Term Quality

Good natural keyword coverage: "Deploy", "QM package", "Fly.io", "AWS", "Render", "Slack", "onboard an administrator" — terms a user would naturally say ("deploy QM to Fly"). Not 5 because synonyms and variations (e.g., "hosting", "set up", "Render.com") and the Porter option are absent; clearly better than the sparse keyword coverage of anchor 3.

4 / 5

Distinctiveness Conflict Risk

"QM package" plus the specific deployment scope (org-owned repo, Fly.io/AWS/Render, admin onboarding, Slack activation) carves out a clear niche with minimal conflict risk — no generic skill would collide with a QM-specific deployment trigger. Platform names act as qualifiers of the QM deployment, not standalone triggers, so this fits anchor 5 better than the minor-overlap anchor 4.

5 / 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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

yc-software/qm

Path

cli/templates/deployment/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.