triggers-and-applygates

Make validation enforced or advisory, via the platform-Space + Filter + TriggerFilterID pattern — Triggers that attach a blocking ApplyGate, or a non-blocking ApplyWarning (--warn), when validation fails. Use for "block bad config from being deployed", "wire up schema validation", "enforce a policy", "warn but don't block", "why is this Unit blocked?", "what warnings does this Unit have?". Not for one-off validator runs (use cub-mutate).

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An actionable, well-sequenced skill body with concrete commands, real feedback loops, and strong workflow clarity. Its weaknesses are some tightenable prose and a progressive-disclosure gap: three referenced files are not bundled, so the skill leans on material that isn't shipped with it.

Suggestions

Ship the referenced bundle files (references/triggers-recipes.md, references/functions-catalog.md, references/cub-cli.md) so the inline pointers resolve, or fold the essential content directly into SKILL.md.

Tighten the --where-trigger "-" explanation and the change-description appendix into a short rule plus a one-line rationale to reduce token load.

Consider moving the long CEL vet-cel examples into references/functions-catalog.md and keeping only the bool form inline, since the catalog is already cited for the full shape.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no general explanations of YAML/CEL/Kubernetes), but several rationale paragraphs — notably the long --where-trigger "-" explanation and the change-description appendix — could be tightened without losing the genuinely non-obvious gotchas they convey.	2 / 3
Actionability	Fully executable, copy-paste-ready cub commands throughout, complete CEL validator examples (bool and structured failed_attributes forms), and concrete jq query expressions; nothing is pseudocode.	3 / 3
Workflow Clarity	Clear multi-step sequences with explicit validation checkpoints — Preflight gates, the platform-Space pattern, a numbered blocked-apply diagnosis loop, and a Verify chain that includes deliberately violating then confirming the gate attaches and releases.	3 / 3
Progressive Disclosure	The body is well-structured and signals one-level-deep references inline (references/triggers-recipes.md, functions-catalog.md, cub-cli.md), but none of those bundle files actually exist on disk, so the detailed material the body depends on is promised but absent — a real navigation gap that caps this dimension.	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 strong, specific description with concrete actions, natural trigger phrases, and explicit when-to-use guidance plus disambiguation against sibling skills. It uses third person and avoids vague fluff throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — making validation enforced vs advisory, attaching a blocking ApplyGate or a non-blocking ApplyWarning (--warn), via the platform-Space + Filter + TriggerFilterID pattern — rather than vague language.	3 / 3
Completeness	Explicitly answers both what it does (enforce/advisory validation via the pattern) and when to use it, with an explicit "Use for..." trigger list plus a "Not for..." exclusion. Third person throughout.	3 / 3
Trigger Term Quality	Good coverage of natural phrases a user would actually say: "block bad config from being deployed", "wire up schema validation", "enforce a policy", "warn but don't block", "why is this Unit blocked?", "what warnings does this Unit have?".	3 / 3
Distinctiveness Conflict Risk	Clear niche (Triggers/ApplyGates/ApplyWarnings enforcement) with distinct triggers, and it explicitly disambiguates from adjacent skills (cub-mutate for one-off runs, confighub-core for YAML authoring), making wrong-skill activation unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 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
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	13 / 16 Passed

Repository: confighub/confighub-skills
Commit: 82d0282

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.