raw-app

MUST use when creating raw apps.

Quality

67%

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

Fix and improve this skill with Tessl

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

Quality

Content

77%

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

The body is highly actionable with strong, validated workflows and concrete executable examples, but it is long and monolithic, merging two guides with overlapping content and no bundle-file-based progressive disclosure. Splitting the two guides or extracting reference material into bundle files would raise the structure scores.

Suggestions

Split the two merged H1 guides (CLI workflow vs platform/authoring) into separate bundle files referenced from SKILL.md to improve progressive disclosure and remove duplication.

De-duplicate the backend-runnable and datatable sections, which currently appear in both halves, to tighten conciseness.

Move the large extension/language table and the per-language code examples into a reference file, keeping SKILL.md as an overview pointing one level deep.

Dimension	Reasoning	Score
Conciseness	The body is dense with genuinely product-specific detail (CLI flags, yaml formats, datatable SDK calls), but it duplicates backend-runnable and datatable content across two merged H1 guides and could be tightened, matching the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	It provides copy-paste-ready commands with explicit flags (`wmill app new --summary ... --path ... --framework react19`), complete yaml configs, SQL examples, and runnable code in multiple languages, matching the 'fully executable code/commands' anchor.	3 / 3
Workflow Clarity	The 'Creating a Raw App' flow is sequenced into Steps 1–3 with explicit validation checkpoints (ask rather than guess, confirm before `--overwrite`, check the regenerated `.lock` diff), and the SQL migration workflow is similarly staged, matching the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a single monolithic document merging two distinct guides (CLI workflow and platform/authoring), where content that could be split is inline with only prose mentions of a 'companion authoring guide', matching the 'content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 concise and distinct but minimal: it supplies a clear trigger and a recognizable niche without describing the skill's concrete capabilities. It reads more as a trigger clause than a capability statement.

Suggestions

Expand the description to list concrete capabilities, e.g. 'Scaffold raw apps via `wmill app new`, configure on-disk layout, backend runnables, and datatable access. Use when creating Windmill raw apps.'

Add natural trigger variations a user might say (e.g. 'raw app', 'Windmill frontend', 'custom app scaffold') to improve keyword coverage.

Keep the explicit 'Use when' clause but pair it with a 'what' statement so both halves of completeness are satisfied.

Dimension	Reasoning	Score
Specificity	"MUST use when creating raw apps" names a concrete domain (raw apps) and a concrete action (creating), but lists only a single action rather than multiple specific capabilities, matching the 'names domain and some actions' anchor.	2 / 3
Completeness	The explicit trigger "Use when creating raw apps" satisfies the 'when' clause, but the 'what' is only the bare phrase "creating raw apps" with no enumeration of what the skill actually does (scaffolding, layout, datatable config), so it falls short of the full what-and-when anchor.	2 / 3
Trigger Term Quality	"creating raw apps" includes a relevant product-native keyword a Windmill user might say, but offers no coverage of common variations or related phrasings, matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	"raw apps" is a specific Windmill niche distinct from scripts, flows, and schedules, making it unlikely to trigger for the wrong skill, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	9 / 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/raw-app/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.