Orientation skill — load when the user is new to ConfigHub, asks "what is a Unit / Space / Target / Worker / Trigger / Filter / Link", needs to understand how entities relate, wants a quick tour before diving into specific operations, or asks "how do I do X in ConfigHub" without enough context to route yet. Also covers Delete Gates and Destroy Gates — phrases like "protect this Space from accidental deletion", "stop anyone from destroying the prod Unit", "add a delete gate", "why can't I delete this?", "how do I lock down critical infra?". Explains the core vocabulary, the Read vs Write tool boundary, the change-description + -o mutations conventions, gate semantics, and routes to the right dedicated skill for each kind of task. Do not load when the user's intent is already concrete enough to route (e.g., "add a trigger that blocks :latest" → triggers-and-applygates; "bump the image" → cub-mutate; "find Deployments using v1.2.3" → cub-query).
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 clearly defines its role as an orientation and routing skill within the ConfigHub ecosystem. It provides rich natural-language trigger phrases, explicitly states both when to load and when NOT to load (with concrete counter-examples referencing other skills), and covers specific capabilities like Delete/Destroy Gates. The description is thorough without being padded, and the disambiguation guidance is particularly strong.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: explains core vocabulary, Read vs Write tool boundary, change-description + -o mutations conventions, gate semantics, Delete Gates and Destroy Gates, and routing to dedicated skills. Very detailed about what it covers. | 3 / 3 |
Completeness | Clearly answers both 'what' (explains core vocabulary, gate semantics, routes to dedicated skills) and 'when' (explicit 'load when' clause with multiple trigger scenarios, plus a 'Do not load when' clause with concrete counter-examples for disambiguation). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would say: 'what is a Unit / Space / Target / Worker / Trigger / Filter / Link', 'how do I do X in ConfigHub', 'protect this Space from accidental deletion', 'why can't I delete this?', 'how do I lock down critical infra?', 'add a delete gate'. These are realistic user utterances. | 3 / 3 |
Distinctiveness Conflict Risk | Exceptionally distinctive — explicitly defines its niche as an orientation/routing skill and includes 'Do not load when' examples that name specific other skills (triggers-and-applygates, cub-mutate, cub-query), making conflict boundaries very clear. | 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 well-crafted orientation skill that clearly defines ConfigHub's entity model, provides actionable CLI examples for gates, and includes an effective routing table. Its main weakness is that the Delete/Destroy Gates section is quite detailed for what is supposed to be an orientation/routing skill, making the overall document heavier than ideal. The references section is well-organized but cannot be verified without bundle files.
Suggestions
Consider extracting the Delete Gates and Destroy Gates section into a dedicated reference file (e.g., references/gates.md) and keeping only a brief summary with a pointer in the main SKILL.md, to better match the orientation/routing purpose of this skill.
Tighten entity definitions — for example, the Target and Worker descriptions include long parenthetical lists of provider types that could be moved to the functions-catalog or a dedicated reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient for an orientation/routing skill covering many entities, but some entity descriptions could be tighter (e.g., the Target and Worker definitions include parenthetical lists that add bulk). The Delete/Destroy Gates section is thorough but somewhat lengthy for an orientation skill — it reads more like a dedicated skill than a routing overview. | 2 / 3 |
Actionability | The gates section provides fully executable, copy-paste-ready CLI commands for adding and removing gates across multiple entity types. The routing table gives concrete skill names. The operational invariants give specific, actionable conventions (--change-desc, -o mutations). Even though this is primarily an orientation skill, the concrete guidance is excellent where it matters. | 3 / 3 |
Workflow Clarity | The 'loop' section provides a clear 4-step sequence for the orientation use case. The gates workflow (add → name → remove with sentinel syntax → then delete) is clearly sequenced with the explicit constraint that all gates must be removed before proceeding. Stop conditions and tool boundaries are explicit. For a read-only routing skill, this is well-structured. | 3 / 3 |
Progressive Disclosure | References to external files (references/cub-cli.md, references/functions-catalog.md, etc.) are clearly listed, and the routing table effectively points to dedicated skills. However, no bundle files were provided to verify these references exist, and the Delete Gates section is quite substantial inline content that could arguably be its own referenced file rather than embedded in an orientation skill. The balance between overview and inline detail is slightly off. | 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 | |
59ea831
Table of Contents
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.