triggers

MUST use when configuring triggers.

Quality

68%

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

87%

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

The body is a lean, highly actionable reference packed with Windmill-specific, non-obvious details and executable code, organized into clear sections. Its main gap is the lack of a post-deploy verification step for the destructive sync push operation, which is the one place a feedback loop would materially reduce risk.

Suggestions

Add a verification step after 'wmill sync push' (e.g., check the trigger appears in the workspace / list triggers) so the destructive deploy has a validate→fix→retry loop, lifting workflow clarity to 3.

Confirm the referenced AGENTS.wml.md 'Deploying' section actually exists and is reachable from the bundle, or inline the essential deploy wiring detail so the reference is self-contained.

Dimension	Reasoning	Score
Conciseness	The body is dense with Windmill-specific details (file naming patterns, payload shapes, S3 fallback behavior, the parquet feature flag) that Claude would not already know, with no padding of basic concepts; every section earns its place, matching 'Lean and efficient; assumes Claude's competence'.	3 / 3
Actionability	Provides concrete file-naming examples, fully spelled-out payload objects, and executable TypeScript and Python snippets plus real CLI commands (wmill sync push/pull, --dry-run), matching 'Fully executable code/commands; copy-paste ready'.	3 / 3
Workflow Clarity	The destructive deploy operation has an explicit consent gate ('only when the user explicitly asks to deploy/publish/push') and a dry-run preview for pull, but there is no verification step confirming the pushed trigger deployed correctly; per the destructive-operations guideline this caps workflow clarity at 2.	2 / 3
Progressive Disclosure	A single well-organized file with clear sections (File Naming, Email Triggers, Payload, Attachments, CLI Commands) and one clearly signaled one-level external reference ('see the Deploying section in AGENTS.wml.md'), matching 'Clear overview with well-signaled one-level-deep references'.	3 / 3
	Total	11 / 12 Passed

Description

50%

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 is terse and provides an explicit trigger condition, but it is thin on concrete capabilities and lacks natural keyword variations, making it generic and weak on the 'what'. It is borderline-vague and would benefit from naming the specific trigger types it covers and the platform it targets.

Suggestions

Name the concrete actions the skill supports (e.g., 'Configure Windmill webhook, email, Kafka, Postgres CDC, and other event triggers') to lift specificity.

Add natural trigger keywords users would actually say — 'webhook', 'email trigger', 'event trigger', 'Windmill trigger' — rather than the generic 'triggers'.

Include the platform ('Windmill') so the skill is distinguishable from generic trigger-configuration skills and reduces conflict risk.

Dimension	Reasoning	Score
Specificity	Quotes the domain and a single action ('configuring triggers') but lists no concrete sub-actions, matching 'Names domain and some actions, but not comprehensive'; not 3 because it lacks multiple specific concrete actions.	2 / 3
Completeness	Provides an explicit 'when' clause ('MUST use when configuring triggers') but the 'what does this do' side is weak/vague, so it does not clearly answer both; not 3 because the 'what' is not spelled out, not 1 because an explicit trigger is present.	2 / 3
Trigger Term Quality	Contains the relevant keyword 'triggers' but no common variations a user would naturally say (webhook, email trigger, event trigger), matching 'Some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	Scoped to 'triggers' but generic (no mention of Windmill or specific trigger types), so it could overlap with other trigger-related skills; matches 'Somewhat specific but could still overlap'.	2 / 3
	Total	8 / 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: system_prompts/auto-generated/skills/triggers/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.