CtrlK
BlogDocsLog inGet started
Tessl Logo

verify-apply

Post-apply verification and close-out. Confirm ConfigHub published/applied the Unit (Completed vs Failed), then confirm ArgoCD/Flux pulled the OCI artifact and the cluster converged (read-only argocd/flux/kubectl). Use right after cub-apply, or for: did it actually deploy, is it live, did argo pick it up, close this release out. Not for authoring (use cub-mutate).

71

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

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 executable commands, a clear two-stage workflow, preflight gates, and error-recovery loops. Its weaknesses are minor framing repetition that hurts conciseness, and a References section that points to bundle files that are not actually present.

Suggestions

Create the missing bundle files under references/ (cub-cli.md, filters-and-queries.md, revisions.md) or remove the References section so signaled paths resolve to real files.

Collapse the repeated statement of the two-stage ConfigHub-vs-cluster model into a single place; let Stage 1 and Stage 2 sections reference it rather than restating the framing.

Consider moving the optional three-way agreement table into a reference file to keep the core verify workflow lean.

DimensionReasoningScore

Conciseness

Mostly efficient and free of generic concept explanations, but the two-stage model is restated across 'The two questions', 'Stage 1', and 'Stage 2' preambles, and the optional three-way table adds length that could be tightened — matching the score-2 anchor 'mostly efficient but could be tightened'.

2 / 3

Actionability

Throughout, commands are concrete and copy-paste ready — 'cub unit get <slug> --space <s> -o jq=.UnitStatus', 'cub unit-event get <slug> <num> --space <s>', 'argocd app get <app-name>', 'kubectl logs <pod> -n <namespace> --previous' — with exact flags and jq paths, matching the score-3 anchor.

3 / 3

Workflow Clarity

Two clearly sequenced stages with explicit preflight gates, a 'Failed — read the error' recovery loop, and close-out gated on 'Only when Stage 1 is Completed'; the skill is read-only yet still includes validation checkpoints, so the destructive-ops cap does not apply — matching the score-3 anchor.

3 / 3

Progressive Disclosure

Sections are well organized and the References section signals one-level-deep files with descriptions, but the referenced files (references/cub-cli.md, references/filters-and-queries.md, references/revisions.md) do not exist in the bundle, so the navigation promise is broken — dropping it from the score-3 anchor to score-2.

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 specific, complete, and distinctive: it states concrete actions, gives natural trigger phrasings, answers both what and when, and explicitly disambiguates from sibling skills. It is written in the required third-person voice with no fluff.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'Confirm ConfigHub published/applied the Unit (Completed vs Failed)', 'confirm ArgoCD/Flux pulled the OCI artifact and the cluster converged', 'close this release out' — matching the score-3 anchor listing several specific actions.

3 / 3

Completeness

Explicitly answers what ('Post-apply verification and close-out. Confirm ConfigHub published/applied the Unit...') and when with explicit triggers ('Use right after cub-apply, or for...'), satisfying the score-3 anchor for both what and when.

3 / 3

Trigger Term Quality

'Use right after cub-apply, or for: did it actually deploy, is it live, did argo pick it up, close this release out' gives good coverage of natural phrasings a user would say, matching the score-3 anchor.

3 / 3

Distinctiveness Conflict Risk

A narrow post-apply GitOps-verification niche with distinct triggers plus an explicit disambiguator ('Not for authoring (use cub-mutate)') makes it unlikely to trigger for the wrong skill, matching the score-3 anchor.

3 / 3

Total

12

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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: 3 missing

Warning

Total

13

/

16

Passed

Repository
confighub/confighub-skills
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.