skill-examples-bootstrap
Use when the user wants a working ConfigHub playground to exercise the other skills against — phrases like "set up the skill-examples space", "bootstrap the examples", "give me a Unit to tinker with", "walk me through with a real example", "I'm new to ConfigHub, show me something I can poke at", or "reset the examples". Creates (or refreshes) a `skill-examples` Space with seed Units covering common Kubernetes resource types — Deployment, StatefulSet, DaemonSet, Job, CronJob, Ingress, NetworkPolicy, RBAC, HPA, PDB — and applies the canonical defaults-function chain so the end state demonstrates config-as-data with provenance intact. Other skills (like `kubernetes-resources`) pull from these live examples in preference to hardcoded YAML. Idempotent: re-running is safe. Do not load for creating real application Spaces (use config-as-data + space setup directly) or for bootstrapping triggers/policy (use triggers-and-applygates).
89
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
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 rich trigger phrases that match natural user language, clearly specifies what the skill does with concrete details (specific Kubernetes resource types, idempotency guarantee), and explicitly delineates when to use it versus when to use alternative skills. The negative triggers ('Do not load for...') are a particularly strong feature for reducing skill selection conflicts.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creates/refreshes a 'skill-examples' Space, seeds Units covering specific Kubernetes resource types (Deployment, StatefulSet, DaemonSet, etc.), applies canonical defaults-function chain, demonstrates config-as-data with provenance. Very detailed and concrete. | 3 / 3 |
Completeness | Clearly answers both 'what' (creates a skill-examples Space with seed Units for Kubernetes resources, applies defaults-function chain) and 'when' (explicit 'Use when' clause with multiple trigger phrases). Also includes explicit 'Do not load' guidance for disambiguation, which goes above and beyond. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases: 'set up the skill-examples space', 'bootstrap the examples', 'give me a Unit to tinker with', 'walk me through with a real example', 'I'm new to ConfigHub', 'reset the examples'. These are realistic phrases users would actually say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche (bootstrapping a specific 'skill-examples' playground Space). Explicitly disambiguates from related skills like 'config-as-data + space setup' for real application Spaces and 'triggers-and-applygates' for policy bootstrapping, minimizing conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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, highly actionable skill with excellent workflow clarity — clear branching logic, preflight gates, verification steps, and idempotent design. The main weaknesses are moderate redundancy between the 'What gets created' bullets and the step 3 table, and the inability to verify referenced bundle files. Overall it serves as a solid operational runbook.
Suggestions
Consolidate the 'What gets created' bullet list and the step 3 upload table into a single location to reduce redundancy and save tokens.
Ensure the referenced bundle files (examples/*.yaml, references/cub-cli.md, references/yaml-patterns.md, references/functions-catalog.md) are actually present in the bundle so progressive disclosure references are verifiable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly efficient for its complexity — the table of Units and the step-by-step commands earn their place. However, the 'What gets created' section duplicates information that reappears in the step 3 table, and the 'Do not load for' section restates frontmatter metadata. Some tightening is possible. | 2 / 3 |
Actionability | Every step has fully executable, copy-paste-ready bash commands with correct flags, arguments, and --change-desc templates. The for-loops, branching logic, and specific cub CLI invocations leave no ambiguity about what to run. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (detect → create space → upload units → apply defaults → show next steps) with explicit branching based on existing state, preflight gates (auth check, user confirmation), a detailed verify chain with specific assertions (e.g., checking for resources.requests, probes, securityContext in YAML output), and stop conditions for error cases. | 3 / 3 |
Progressive Disclosure | References to companion skills and reference files are clearly signaled at the end, and the content is well-sectioned. However, no bundle files were provided, so the referenced paths (skills/skill-examples-bootstrap/examples/, references/cub-cli.md, etc.) cannot be verified. The skill is also quite long inline — the Unit descriptions table and the 'What gets created' bullet list could potentially be split out. | 2 / 3 |
Total | 10 / 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.