CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

deploy-qm

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

Quality

80%

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 ./cli/templates/deployment/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 tight, well-structured orchestrator body that gives concrete commands, clear guardrails, and explicit completion criteria while deferring detail to one-level-deep references. The main improvements are naming the provider reference files explicitly and consolidating the duplicated email.md read triggers.

Suggestions

Name the provider reference files explicitly (e.g., "Read `references/fly.md` or `references/aws.md` for the selected provider") so navigation does not depend on inference.

Consolidate the two `references/email.md` read triggers into a single conditional instruction to remove the redundancy.

DimensionReasoningScore

Conciseness

The ~25-line body is lean and dense with no concept explanations Claude already knows (e.g., "Use the repository's installed `@yc-software/qm` dependency through `npm exec qm -- <command>`"). Not 5: `references/email.md` is pointed to twice with different triggers ("before collecting email secrets" and "once the operator has chosen the broker") — a redundancy that could be consolidated.

4 / 5

Actionability

Concrete commands (`npm exec qm -- <command>`, `qm admin-login`), a concrete config key (`modelProvider`), named broker options, and a concrete acceptance criterion ("A web response without a generated sidebar title is not a completed deployment"). Not 5: no copy-paste-ready example command for the main flow, which is delegated to `deployment.md`.

4 / 5

Workflow Clarity

A clear sequence is present (`deployment.md` as authoritative workflow → selected provider reference → collect model key and sign-in "in the same pass" → conditional email/Slack references → acceptance checks) with explicit checkpoints ("Do not stop at infrastructure health: complete the acceptance checks"). Not 5: steps are not enumerated in the body and the fix/retry feedback loop lives in the delegated file rather than here.

4 / 5

Progressive Disclosure

All references are one level deep with well-signaled conditional read triggers ("Read `references/slack.md` only when Slack is requested"), and the referenced files (email.md, slack.md) exist in the bundle. Not 5: "Read only the selected provider reference" never names `references/fly.md`, `aws.md`, or `porter.md`, leaving a minor navigation gap the reader must infer.

4 / 5

Total

16

/

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 specific, distinctive description with concrete actions and named platforms, but it omits any explicit "Use when..." trigger guidance, capping its completeness. Adding a trigger clause with natural synonyms would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when deploying or setting up QM, onboarding a QM administrator, or when the user mentions Fly.io, AWS, or QM deployment."

Include natural synonym variations ("set up", "install", "launch") alongside "deploy" to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Lists four concrete actions — deploy to named platforms ("to Fly.io or AWS"), "onboard an administrator", "configure connectors", "optionally activate Slack" — with comprehensive coverage of the deployment lifecycle. Not 4: the only mildly generic item is "configure connectors", but the action list itself is complete rather than gapped.

5 / 5

Completeness

The "what" is clearly and concretely stated, but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4: any "when" is only weakly implied by the domain.

3 / 5

Trigger Term Quality

Good natural keywords users would say: "deploy", "Fly.io", "AWS", "Slack", "administrator", "onboard". Not 5: common synonyms and variations such as "set up", "install", or "launch" are missing.

4 / 5

Distinctiveness Conflict Risk

"QM package", "organization-owned deployment repository", and the named platforms ("Fly.io or AWS") establish a clear niche with distinct triggers and minimal overlap risk with generic deploy or setup skills.

5 / 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

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.