CtrlK
BlogDocsLog inGet started
Tessl Logo

app-config

Turn an app config file (.env, .properties, .yaml, .json, .toml, .ini, text) into a versioned AppConfig Unit and render it to a Kubernetes ConfigMap via an Upsert link + render-configmap Invocation (no worker/Target). For: use my .env with ConfigHub, ConfigMap like configMapGenerator, envFrom injection. Not for raw ConfigMap authoring (use confighub-core).

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.

A well-structured, highly actionable skill body with a clear sequenced loop, validation checkpoints, and concrete commands. Its main weaknesses are mild prose verbosity and, more importantly, references to bundle files (references/*.md) that are not actually present.

Suggestions

Create the referenced bundle files (references/cub-cli.md, references/yaml-patterns.md, references/functions-catalog.md) or remove the dangling references so progressive-disclosure navigation is not broken.

Trim the 'Why this matters' section and per-step prose asides so the body leans fully on commands and flags, raising conciseness to the score-3 anchor.

Consider moving the long format/metadata tables into a reference file to keep SKILL.md a leaner overview.

DimensionReasoningScore

Conciseness

Mostly efficient and command-dense without explaining basic concepts (no 'what is a ConfigMap'), but the 'Why this matters' rationale and several prose asides per step could be tightened; sits at the 'mostly efficient but could be tightened' anchor rather than the lean score-3 example.

2 / 3

Actionability

Fully executable `cub unit create`, `cub function do`, `cub link create`, `cub trigger create` commands with concrete flags and copy-paste-ready YAML snippets — matching the 'fully executable code/commands; copy-paste ready' anchor.

3 / 3

Workflow Clarity

A clearly sequenced 9-step 'The loop' with Preflight gates, explicit Stop conditions, and a 'Verify chain' providing validation checkpoints and error-recovery (e.g. auth failure → 'ask the user to run cub auth login'), satisfying the explicit-checkpoints anchor.

3 / 3

Progressive Disclosure

References are clearly signaled and conceptually one-level-deep (references/cub-cli.md, references/yaml-patterns.md, references/functions-catalog.md), but the references/ directory and those files do not exist on disk, so navigation is broken; the missing bundle prevents a top score despite otherwise good organization.

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.

A high-quality description: specific, third-person, with explicit 'For:'/'Not for' triggers and clear disambiguation against confighub-core. It comprehensively covers what the skill does and when to use it without vague fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions with named mechanisms — 'Turn an app config file (.env, .properties, .yaml, .json, .toml, .ini, text) into a versioned AppConfig Unit and render it to a Kubernetes ConfigMap via an Upsert link + render-configmap Invocation' — far beyond the score-2 'names domain and some actions' anchor.

3 / 3

Completeness

Explicitly answers both what (turn config into a Unit, render a ConfigMap) and when via an explicit 'For:' trigger clause plus a 'Not for raw ConfigMap authoring' exclusion, satisfying the 'both what AND when with explicit triggers' anchor.

3 / 3

Trigger Term Quality

The 'For:' block surfaces natural user phrasings ('use my .env with ConfigHub', 'ConfigMap like configMapGenerator', 'envFrom injection') alongside the format list, giving good coverage of terms a user would actually say; not merely technical jargon.

3 / 3

Distinctiveness Conflict Risk

Clear niche (AppConfig → ConfigMap rendering) with an explicit disambiguator 'Not for raw ConfigMap authoring (use confighub-core)', making it unlikely to trigger for sibling skills.

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: 4 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.