CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-examples-bootstrap

Create or refresh a skill-examples Space with seed Units covering common Kubernetes resource types — a playground to exercise the other skills against. Use for "set up the skill-examples space", "bootstrap the examples", "give me a Unit to tinker with", "reset the examples". Not for creating real application Spaces (use confighub-core).

76

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Risky

Do not use without reviewing

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.

A well-structured, highly actionable bootstrap procedure: concrete commands, explicit validation checkpoints, and a clear end-to-end loop. The main weakness is that the body advertises reference files (references/cub-cli.md, yaml-patterns.md, functions-catalog.md) that are not present in the bundle, so the progressive-disclosure structure is signposted but undelivered.

Suggestions

Add the missing referenced files (references/cub-cli.md, references/yaml-patterns.md, references/functions-catalog.md) so the signposted progressive-disclosure structure is actually delivered, or remove the dead references from the References section.

Consider folding the 'What gets created' prose list and the file/unit/contents table into a single view to reduce the triple enumeration of the 11 Units (prose, table, bash slug loops).

Make the Verify chain an explicit validate→fix→retry loop (e.g. 'if a Unit is missing or YAML lacks the expected fields, re-run the corresponding create/function set step') rather than a terminal checklist.

DimensionReasoningScore

Conciseness

The body is command-dense and assumes Claude's competence — no PDF-style conceptual explanations of Kubernetes or the CLI. Non-obvious asides (e.g. "cub space create does not accept --change-desc; Spaces aren't versioned data") earn their tokens. Minor redundancy across the prose unit list, the mapping table, and the bash slug loops keeps it just short of flawless but firmly lean.

3 / 3

Actionability

Provides fully executable, copy-paste-ready `cub` commands with real flags (e.g. `cub unit create --space ... --merge-external-source ... --change-desc ...`, `cub function set ... -- set-container-resources-defaults`). Concrete examples throughout rather than vague direction.

3 / 3

Workflow Clarity

Clear five-step loop with a preflight auth gate (with explicit failure action: ask user to run `cub auth login`), branch logic on existing state, idempotent re-runs as the recovery mechanism for the batch operations, and a five-point Verify chain with concrete assertions (resources.requests, probes, securityContext, clusterIP: None). Validation checkpoints are explicit, not implicit.

3 / 3

Progressive Disclosure

The References section signposts one-level-deep files with clear descriptions (references/cub-cli.md, references/yaml-patterns.md, references/functions-catalog.md), and example YAML is externalized rather than inlined — good signaling. However, the referenced `references/*.md` bundle files do not exist, so the disclosure structure is promised but not actually delivered, capping this below 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.

A concise, third-person description that crisply states what the skill does, gives explicit natural-language triggers, and draws a clear boundary against the sibling confighub-core skill. It hits all four anchors at the top of the scale without padding or over-claiming.

DimensionReasoningScore

Specificity

Names concrete actions — "Create or refresh a skill-examples Space" and "seed Units covering common Kubernetes resource types" — rather than vague language. Not a 2 because it specifies the domain and concrete operations, not just a domain plus partial actions.

3 / 3

Completeness

Explicitly answers both what ("Create or refresh a skill-examples Space with seed Units...") and when ("Use for..." with explicit triggers plus a "Not for..." boundary). Has the required explicit 'Use when...' style trigger guidance.

3 / 3

Trigger Term Quality

Provides four natural trigger phrases a user would say: "set up the skill-examples space", "bootstrap the examples", "give me a Unit to tinker with", "reset the examples". Good coverage of natural terms rather than technical jargon.

3 / 3

Distinctiveness Conflict Risk

Clear niche (playground/sandbox) with an explicit boundary — "Not for creating real application Spaces (use confighub-core)" — making it unlikely to trigger for the wrong skill. Distinct triggers further reduce conflict.

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.