triggers-and-applygates
Use when the user wants validation to be enforced (not just advisory) on ConfigHub Units, is setting up a new Space and wants policy to apply automatically, asks about ApplyGates, says "block bad config from being deployed", "wire up schema validation", "enforce a policy", "require approval", or needs to diagnose why a Unit is blocked from applying. This skill installs the platform-Space + Filter + TriggerFilterID pattern — centralized Triggers that run on every Mutation and attach ApplyGates when validation fails. Do not load for: running validators one-off without installing them (use cub-mutate with vet-* functions instead), or for authoring the YAML itself.
92
92%
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 hits all the marks. It provides specific concrete actions, rich natural trigger terms including quoted user phrases, explicit 'Use when' and 'Do not load for' clauses, and highly distinctive domain-specific terminology that minimizes conflict risk. The description is thorough without being padded, and uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: installs the platform-Space + Filter + TriggerFilterID pattern, centralized Triggers that run on every Mutation, attaches ApplyGates when validation fails. Also specifies what it does NOT do, adding further specificity. | 3 / 3 |
Completeness | Clearly answers both 'what' (installs the platform-Space + Filter + TriggerFilterID pattern for centralized validation enforcement) and 'when' (explicit 'Use when' clause with multiple trigger scenarios). Also includes explicit 'Do not load for' exclusions, which further strengthens completeness. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would say: 'block bad config from being deployed', 'wire up schema validation', 'enforce a policy', 'require approval', plus domain-specific terms like ApplyGates, ConfigHub Units, and Space. These are realistic user utterances. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with domain-specific terminology (ConfigHub Units, ApplyGates, TriggerFilterID, platform-Space) and explicit exclusion boundaries ('Do not load for: running validators one-off... use cub-mutate with vet-* functions instead'). 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-crafted skill that provides highly actionable, executable guidance for setting up enforced validation via Triggers and ApplyGates. The workflow is clearly sequenced with verification steps and stop conditions. The main weakness is some verbosity in explanatory sections (particularly the `--where-trigger` rationale and `--change-desc` boundary), which could be condensed without losing essential information.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining basic concepts, but some sections are verbose — particularly the lengthy explanation of why `--where-trigger "-"` is needed and the detailed `--change-desc` boundary section. These could be tightened while preserving clarity. | 2 / 3 |
Actionability | Excellent actionability throughout: every step has concrete, copy-paste-ready CLI commands with real flag names and arguments. The custom policy section provides multiple executable `vet-cel` examples with both simple and structured return forms, and the diagnostic workflow gives specific commands for each step. | 3 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced (create Space → create Triggers → create Filter → attach to Spaces → verify), with explicit validation checkpoints in the 'Verify chain' section including a deliberate-violation test. The 'Diagnosing a blocked apply' section provides a clear troubleshooting sequence, and stop conditions prevent destructive mistakes like bypassing gates. | 3 / 3 |
Progressive Disclosure | The skill is well-structured with clear sections progressing from setup to customization to diagnosis. References to `references/triggers-recipes.md`, `references/functions-catalog.md`, and `references/cub-cli.md` are one level deep and clearly signaled with context about what each contains. Advanced details like CEL return shapes are summarized inline with pointers to the full reference. | 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.