write-workflow-as-code

MUST use when writing or modifying Windmill Workflow-as-Code scripts using workflow, task, step, sleep, approvals, taskScript, taskFlow, task_script, or task_flow.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./system_prompts/auto-generated/skills/write-workflow-as-code/SKILL.md

Quality

Content

55%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 actionable and well-sequenced with strong validation guidance for CLI operations, but it is bulkier than necessary due to an inlined dual-language API reference. Splitting the API reference into bundled reference files would materially improve both conciseness and progressive disclosure.

Suggestions

Move the TypeScript and Python API reference blocks (lines ~244-534) into separate bundled files (e.g. references/typescript-api.md, references/python-api.md) and link to them from a short overview section, reducing the inlined bulk.

Trim the verbose error-handling paragraph to a concise rule plus a short example, since the surrounding sections already convey the checkpoint/replay model.

Keep one canonical end-to-end runnable WAC example near the top so the common authoring case is executable without scanning both language API sections.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and avoids explaining basics Claude knows, but the ~290-line dual TypeScript/Python API reference duplicates concepts already shown in examples and the dense error-handling paragraph adds notable bulk.	3 / 5
Actionability	Provides concrete, copy-paste-ready code in both languages for tasks, steps, parallelism, and approvals, plus specific CLI commands, with only minor gaps in a full end-to-end example.	4 / 5
Workflow Clarity	Clear intent-based decision rules sequence preview → generate-metadata → deploy with gated validation (offer to test, diff regenerated locks and report version bumps, --dry-run inspection) and an explicit deploy gate.	4 / 5
Progressive Disclosure	No bundle files exist; the large dual-language API reference that clearly belongs in separate reference files is inlined in the single SKILL.md with only section headers for structure.	2 / 5
	Total	13 / 20 Passed

Description

95%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 is specific, trigger-rich, and clearly distinguishes the skill via concrete Windmill WAC API names. It answers both what and when explicitly and uses appropriate third-person/infinitive voice.

Dimension	Reasoning	Score
Specificity	Names the domain ('Windmill Workflow-as-Code scripts') and enumerates many concrete SDK constructs (workflow, task, step, sleep, approvals, taskScript, taskFlow, task_script, task_flow), listing several specific items with only minor gaps in distinct action verbs.	4 / 5
Completeness	Explicitly answers what (writing/modifying Windmill WAC scripts) and when ('MUST use when writing or modifying... using [these APIs]') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including synonyms and both casing variants (taskScript/task_script, taskFlow/task_flow) plus 'writing or modifying' and 'approvals', which a user would naturally say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (Windmill Workflow-as-Code) with highly specific SDK function names as triggers, giving minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (535 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: windmill-labs/windmill
Path: system_prompts/auto-generated/skills/write-workflow-as-code/SKILL.md
Commit: 74af4ed

Reviewed: about 18 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.