triggers

MUST use when configuring triggers.

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./system_prompts/auto-generated/skills/triggers/SKILL.md

Quality

Content

83%Weight 40%Scale 1-5

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

The body is lean, dense, and highly actionable with concrete commands and copy-paste code covering the common Windmill trigger cases. Its main gap is the lack of an explicit validation/verification feedback loop for the destructive deploy operation, which caps workflow clarity.

Suggestions

Add a validation checkpoint for the destructive 'wmill sync push', e.g. recommend running 'wmill sync push --dry-run' (or equivalent) first and only proceeding when the preview matches intent.

Provide a brief verify step after push (e.g. 'wmill sync pull' afterward or checking the trigger status) to close the feedback loop around destructive deploys.

Clarify how to surface the referenced AGENTS.wmill.md 'Deploying' section so navigation stays within the skill bundle.

Dimension	Reasoning	Score
Conciseness	The body is dense and Windmill-specific with no padding or explanation of concepts Claude already knows (no definition of email, S3, or triggers). Every line carries novel detail, matching anchor 5 ('every token earns its place'); it does not include the minor qualifier language of anchor 4.	5 / 5
Actionability	Copy-paste-ready TypeScript and Python snippets for reading S3 attachment bytes, concrete file-naming patterns, exact JSON shapes, and specific commands ('wmill sync push', 'wmill sync pull --dry-run') cover the common cases. This matches anchor 5 for fully executable, copy-paste-ready guidance.	5 / 5
Workflow Clarity	The destructive-operation guideline is present (only deploy when explicitly asked, with a safe 'sync pull' alternative), but there is no explicit validation/verification feedback loop around the destructive 'sync push'. The rubric caps destructive/batch skills without validation at 3, so this fits anchor 3 (steps present but validation checkpoints missing) rather than anchor 4.	3 / 5
Progressive Disclosure	No bundle files exist, and the ~68-line body is well-organized with clear section headers (File Naming, Email Triggers, Payload, Attachments, CLI Commands). It appropriately fits inline without needing external files, matching anchor 4; it stops short of 5 because the one external reference (AGENTS.wmill.md) is outside the skill bundle and slightly weakens self-contained navigation.	4 / 5
	Total	17 / 20 Passed

Description

28%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description provides only a trigger condition ('MUST use when configuring triggers') with no statement of what the skill does and no concrete actions, leaving it vague and weakly distinctive. It functions as a routing hint but fails to answer the 'what' half of a complete description.

Suggestions

State what the skill does in third person, e.g. 'Configures Windmill triggers (webhook, email, kafka, postgres, schedule) by authoring {path}.{type}_trigger.yaml files'.

Add concrete trigger-type keywords users would naturally say ('webhook', 'email trigger', 'kafka', 'postgres CDC', 'cron/schedule') to improve trigger-term coverage.

Add an explicit 'Use when...' phrase listing concrete situations so both the 'what' and 'when' are present.

Dimension	Reasoning	Score
Specificity	The phrase 'configuring triggers' names the trigger domain but lists no concrete actions (no create, deploy, sync, or route). It is not entirely vague, yet the actions are minimal/generic, matching anchor 2; it falls short of anchor 3 which requires naming 1-2 concrete actions.	2 / 5
Completeness	A 'when' clause is present ('MUST use when configuring triggers') but the 'what' is entirely absent — the description never says what the skill does. Anchor 2 covers 'only when is present without what'; anchor 3 requires a clear 'what', which is missing.	2 / 5
Trigger Term Quality	Only 'triggers' is a natural keyword; the natural phrases users say ('webhook', 'email trigger', 'kafka trigger', 'schedule', 'cron') are absent. This matches anchor 2 (one or two generic keywords missing common phrases) rather than anchor 3 which expects relevant coverage.	2 / 5
Distinctiveness Conflict Risk	'triggers' is a moderately specific niche, but 'configuring triggers' is broad enough to overlap with several trigger-type or config skills. It is somewhat specific yet still overlaps with related skills, matching anchor 3.	3 / 5
	Total	9 / 20 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: system_prompts/auto-generated/skills/triggers/SKILL.md
Commit: 74af4ed

Reviewed: about 19 hours 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.