cub-mutate
Use whenever the user wants to change data inside a ConfigHub Unit — update an image, adjust replicas, set environment variables, add labels/annotations, change a resource field, apply defaults, or make a bulk edit across many units. This skill enforces the "prefer a function over a hand-edit" rule, composes a proper change description that captures the user's prompt and clarifications, and chooses between `cub function set` (single function, targeted or bulk) and `cub unit update` (whole-unit replacement or restore). Load proactively any time the user says "update the image", "bump the replicas", "change the env var", "set the annotation", "apply defaults", "edit this unit", or any natural request that will end in a write to ConfigHub. Do not load for: creating a brand-new Unit (use config-as-data), reading/inspecting config (use cub-query), or setting up validation (use triggers-and-applygates).
92
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Quality
Discovery
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.
This is an excellent skill description that excels across all dimensions. It provides specific concrete actions, rich natural trigger terms, explicit 'when to use' and 'when not to use' guidance, and clear boundaries distinguishing it from related skills. The inclusion of negative triggers referencing alternative skills is a particularly strong practice for avoiding conflicts.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: update an image, adjust replicas, set environment variables, add labels/annotations, change a resource field, apply defaults, bulk edit. Also names specific commands like `cub function set` and `cub unit update`. | 3 / 3 |
Completeness | Clearly answers both 'what' (change data inside a ConfigHub Unit with specific actions and commands) and 'when' (explicit 'Use whenever...' and 'Load proactively any time the user says...' clauses with concrete triggers). Also includes explicit 'Do not load for' negative triggers, which further strengthens completeness. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would say: 'update the image', 'bump the replicas', 'change the env var', 'set the annotation', 'apply defaults', 'edit this unit'. These are natural, varied, and cover common user language. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit negative boundaries ('Do not load for: creating a brand-new Unit, reading/inspecting config, setting up validation') and references to specific alternative skills (config-as-data, cub-query, triggers-and-applygates). This makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that provides highly actionable CLI guidance with clear workflow sequencing, explicit validation checkpoints, and appropriate progressive disclosure to reference files. The decision tree and function mapping table are particularly effective. The main area for improvement is conciseness — the ChangeSets section and some inline explanations could be trimmed or offloaded to references, though the verbosity is relatively minor given the complexity of the domain.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining basic concepts, but it's quite long (~200+ lines) with some sections that could be tightened — e.g., the ChangeSets section is extensive and could reference an external file more aggressively, and the deprecated functions list and some explanatory asides ('it's the same diff that will show up...') add marginal tokens. | 2 / 3 |
Actionability | Highly actionable throughout: concrete CLI commands with exact flags, a function-to-change mapping table, copy-paste-ready bash snippets for every workflow path (single mutation, bulk, whole-unit replacement, restore, ChangeSet lifecycle), and explicit flag usage like `-o mutations` and `--dry-run`. | 3 / 3 |
Workflow Clarity | The numbered loop (clarify → pick function → scope → compose description → run → verify) is clearly sequenced with explicit validation checkpoints (verify chain with `cub unit get`, `cub revision list`, and vet functions). Stop conditions provide clear guardrails, and the decision tree gives an unambiguous branching path. The ChangeSet lifecycle is also clearly sequenced with numbered steps. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled references to external files (functions-catalog.md, cub-cli.md, changesets.md, filters-and-queries.md, yaml-patterns.md) and external docs. Content is appropriately split — the main file covers the workflow and decision-making while deferring catalog details and deep-dives to reference files. No nested reference chains. | 3 / 3 |
Total | 11 / 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.
Validation — 9 / 11 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 |
Total | 9 / 11 Passed | |
- Repository
- confighub/confighub-skills
- Commit
59ea831
- 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.