promote-release

Promote a release to the next environment or across the fleet, and manage variant spaces — cub variant create / promote to reconcile a variant with its upstream, or a ChangeSet-wrapped bulk upgrade for partial / cross-space scopes. Phrases: promote to staging, roll forward to prod, which Units are behind upstream, push the base to every downstream. Not for rollback (use rollback-revision).

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete commands and a well-sequenced, validated workflow including feedback loops for batch/destructive operations. Its main weaknesses are length/redundancy affecting conciseness and references that point to files absent from the bundle.

Suggestions

Remove redundancy to tighten conciseness: the Rollback section and the Tool boundary list (which restates the frontmatter allowed-tools) could be trimmed or consolidated.

Provide the missing references/ files (changesets.md, filters-and-queries.md, cub-cli.md, revisions.md) in the bundle, or drop the references to files that are not shipped so progressive disclosure is completable.

Consider moving the detailed preflight A-E recipes into a reference file to keep SKILL.md as a lean overview, leaving the core decision flow inline.

Dimension	Reasoning	Score
Conciseness	Information-dense and avoids explaining domain concepts Claude already knows, but the ~200-line body is voluminous with some redundancy (rollback restated, the Tool boundary duplicating frontmatter allowed-tools), so it could be tightened.	2 / 3
Actionability	Fully executable, copy-paste-ready commands throughout — 'kustomize build overlays/base \| cub variant upload ...', 'cub variant create prod web-base ...', 'cub variant promote web-prod --dry-run -o mutations', preflight and changeset commands with real flags.	3 / 3
Workflow Clarity	Clear sequencing (variant lifecycle steps 1-3; preflight A-E then open/upgrade/close) with explicit validation checkpoints (--dry-run preview, go/no-go preflight, Stop conditions, Verify chain) and feedback loops (no-go routes to remediation; merge conflicts resolved in cub-mutate then re-diffed).	3 / 3
Progressive Disclosure	References are well-signaled and one level deep in a dedicated References section, but the referenced paths (references/changesets.md, filters-and-queries.md, cub-cli.md, revisions.md) are not present in the bundle, so the disclosure cannot actually be followed.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 strong across the board: concrete actions, explicit natural-language trigger phrases, clear what/when coverage, and a distinct niche with an explicit exclusion to avoid conflict. Voice is third person with no first/second person.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Promote a release to the next environment or across the fleet', 'cub variant create / promote to reconcile a variant with its upstream', 'ChangeSet-wrapped bulk upgrade for partial / cross-space scopes' — rather than vague language.	3 / 3
Completeness	Answers both what (promote/release/variant management) and when via the explicit 'Phrases:' trigger guidance, which is equivalent to a 'Use when' clause and avoids the cap at 2.	3 / 3
Trigger Term Quality	Explicit 'Phrases: promote to staging, roll forward to prod, which Units are behind upstream, push the base to every downstream' gives good coverage of natural terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Highly niche (ConfigHub cub CLI, variant spaces, ChangeSets) with an explicit 'Not for rollback (use rollback-revision)' exclusion, making it clearly distinguishable and unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 7 missing, 1 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: confighub/confighub-skills
Commit: 82d0282

Reviewed: 1 day 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.