deploy-qm

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

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/deploy-qm/SKILL.md

Quality

Content

83%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.

The body is a concise, well-structured overview that delegates detail to real one-level-deep references and specifies concrete qm CLI commands plus an automated release gate. Its main limitation is that the full deployment sequence and error-recovery detail live in deployment.md rather than inline.

Suggestions

Inline a short, numbered high-level deployment sequence so the core workflow is visible without opening deployment.md.

Add an explicit validate -> fix -> retry loop for the qm check --live gate so error recovery is visible in the skill body.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive with no padding or explanation of concepts Claude already knows; every sentence drives an action and earns its place in the context window.	5 / 5
Actionability	Provides concrete executable commands ('npm exec qm -- <command>', 'qm check --live', 'qm admin-login') with minor gaps, but the bulk of the deployment step sequence is delegated to deployment.md rather than given inline.	4 / 5
Workflow Clarity	A clear sequence with explicit validation checkpoints is present (qm check --live as automated release gate plus manual sign-in and web acceptance check), though detailed error-recovery feedback loops live in the external deployment.md.	4 / 5
Progressive Disclosure	Clear overview with well-signaled, one-level-deep references (deployment.md and a selectable set of real provider reference files), including explicit selective-loading guidance ('Read only the selected provider reference', 'Read references/slack.md only when Slack is requested').	5 / 5
	Total	18 / 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.

The description is specific and distinctive, naming concrete deployment actions and target providers, but it omits any explicit 'Use when...' trigger guidance, leaving the 'when' half of completeness unaddressed.

Suggestions

Add a 'Use when...' clause naming natural trigger phrases, e.g. 'Use when deploying the QM package, onboarding a QM administrator, or activating the QM Slack app.'

Slightly expand 'configure connectors' to name which connectors, so the action is more concrete.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('deploy the QM package', 'onboard an administrator', 'configure connectors', 'activate Slack') with named targets Fly.io and AWS, but each action stays high-level so coverage has minor gaps rather than being comprehensive.	4 / 5
Completeness	The 'what' is clearly stated across multiple actions, but there is no 'Use when...' or equivalent explicit trigger guidance for when Claude should use this skill, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('Deploy', 'Fly.io', 'AWS', 'Slack', 'onboard an administrator') with good coverage of named providers, but lacks explicit trigger framing and synonym layering for a 5.	4 / 5
Distinctiveness Conflict Risk	The named QM package plus specific providers (Fly.io, AWS) and Slack create a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: yc-software/qm
Path: .codex/skills/deploy-qm/SKILL.md
Commit: 9745e34

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.