adding-a-trigger

Checklist for adding a new TriggerCrud-based trigger type to Windmill (Azure, GCP, Kafka, etc.). Use when wiring a new trigger kind across backend, frontend, CLI, and capture infrastructure.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%

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

An exceptionally actionable, well-sequenced checklist that captures project-specific gotchas without generic padding, with strong validation checkpoints. Its main weakness is structure: it is a large monolithic file with no progressive disclosure into bundle files.

Suggestions

Split the large inline reference material (e.g. the §1 RLS wrapping detail, §6.5 hardcoded-arrays list, §12 Common pitfalls) into a REFERENCES.md or per-topic files in ./references/ and link to them one level deep, leaving SKILL.md as a tighter overview.

Move the per-file code templates (§3 wiring, §9 frontend components) into scripts/ or reference snippets so the main body stays a navigable checklist rather than embedded code blocks.

Consider extracting the §11 validation commands and §14 final checklist into a single ./scripts/validate.sh that the body invokes, reducing inline command sprawl.

Dimension	Reasoning	Score
Conciseness	Every section is dense, project-specific knowledge (exact files, structs, footguns like the RLS GUC wrapping and fork mode-forcing) with no generic concept explanations Claude already knows, so tokens earn their place despite the length.	3 / 3
Actionability	Provides executable commands ('cargo sqlx migrate add -r add_{kind}_trigger', './update_sqlx.sh', 'npm run generate-backend-client'), exact file paths, and copy-paste-ready Rust/Svelte snippets rather than pseudocode.	3 / 3
Workflow Clarity	Sequenced top-to-bottom across numbered sections 1–14 with an explicit Validation section (cargo check variants, frontend checks) and a Final checklist, supplying checkpoints for these destructive/batch operations.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the ~280-line body is entirely inline with no one-level-deep references; sections are well-organized, but content that could be split (code blocks, pitfalls) stays monolithic, and the under-50-line simple-skill exception does not apply.	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 tight, third-person description that pairs an explicit capability statement with a 'Use when' trigger and concrete provider keywords. It cleanly answers what, when, and for whom without fluff.

Dimension	Reasoning	Score
Specificity	States a concrete action ('adding a new TriggerCrud-based trigger type to Windmill') and enumerates the specific wiring layers — 'backend, frontend, CLI, and capture infrastructure' — matching the multiple-specific-actions anchor rather than the partial anchor at 2.	3 / 3
Completeness	Explicitly answers both what ('Checklist for adding a new TriggerCrud-based trigger type to Windmill') and when ('Use when wiring a new trigger kind across backend, frontend, CLI, and capture infrastructure'), satisfying the explicit 'Use when...' requirement.	3 / 3
Trigger Term Quality	Surfaces natural terms a user would actually say — 'Azure, GCP, Kafka', 'trigger', 'Windmill' — giving good coverage of provider-name variations instead of bare technical jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (TriggerCrud-based Windmill triggers) with named providers, and the body scopes it against native triggers, making conflict with unrelated skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: windmill-labs/windmill
Path: .agents/skills/adding-a-trigger/SKILL.md
Commit: 33d2845

Reviewed: 2 days 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.