CtrlK
BlogDocsLog inGet started
Tessl Logo

cub-mutate

Change data inside an existing ConfigHub Unit, preferring a function over a hand-edit. Use for "update the image", "bump the replicas", "change the env var", "set the annotation", "apply defaults", "edit this unit", or a bulk edit across many units. Not for creating a brand-new Unit (use confighub-core).

76

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

92%

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

The body is lean, highly actionable, and workflow-clear with explicit validation and feedback loops for a mutating operation. Progressive disclosure is the only weak point: the referenced reference files are not actually bundled and some heavy detail is kept inline.

Suggestions

Provide the referenced bundle files (references/functions-catalog.md, changesets.md, filters-and-queries.md, yaml-patterns.md, cub-cli.md) so the signaled progressive-disclosure paths resolve to real content.

Move the full ChangeSet lifecycle and Invocation authoring detail into references/changesets.md (or a dedicated invocations reference), leaving the body a concise pointer plus the canonical open/mutate/close skeleton.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence — a decision tree, a change-to-function table, and copy-paste commands with no padding about what YAML, Kubernetes, or ConfigHub are; every section earns its tokens, matching the lean-and-efficient anchor.

3 / 3

Actionability

Commands are fully executable with concrete flags — the full 'cub function set … -o mutations -- <fn>' invocation, the ChangeSet lifecycle bash block, and restore commands — copy-paste ready rather than pseudocode, matching the top anchor.

3 / 3

Workflow Clarity

A numbered 1–7 loop with a decision tree, preflight gates, stop conditions, and an explicit Verify chain ('cub function vet … vet-schemas, vet-placeholders') provides clear sequencing and validation feedback loops for this mutating/batch context, matching the top anchor.

3 / 3

Progressive Disclosure

Sections are well-organized and one-level-deep references (functions-catalog, changesets, filters-and-queries, etc.) are clearly signaled, but the references/ directory is absent so referenced files are not bundled, and substantial detail (ChangeSet lifecycle, Invocations) is inline that could live in those files — matching the 'some structure, content that should be separate is inline' anchor rather than a clean 3.

2 / 3

Total

11

/

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, trigger-rich, and complete, naming concrete mutation actions with verbatim user phrasings and an explicit what/when structure. A clear negative boundary against a sibling skill keeps conflict risk low.

DimensionReasoningScore

Specificity

Multiple concrete actions are named — 'Change data inside an existing ConfigHub Unit', 'preferring a function over a hand-edit', 'apply defaults', and 'a bulk edit across many units' — matching the anchor for listing several specific concrete actions rather than the partial coverage of a 2.

3 / 3

Completeness

It states both what ('Change data inside an existing ConfigHub Unit, preferring a function over a hand-edit') and when ('Use for …' with an explicit trigger list), plus a negative boundary, matching the anchor that requires explicit answers to both.

3 / 3

Trigger Term Quality

It embeds natural user phrasings verbatim — 'update the image', 'bump the replicas', 'change the env var', 'set the annotation', 'edit this unit', 'bulk edit' — giving strong coverage of terms a user would actually say, matching the top anchor.

3 / 3

Distinctiveness Conflict Risk

The niche (mutating existing Units) is sharply bounded by 'Not for creating a brand-new Unit (use confighub-core)' and is distinct from query/trigger skills, making conflict unlikely and matching the clear-niche 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: 8 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.