CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

71%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.

A strong, actionable reference for Windmill Workflow-as-Code with excellent executable examples and genuinely non-obvious domain knowledge, but it underuses progressive disclosure by inlining two full API references and carries notable duplication of conceptual explanations across sections. Tightening the repeated prose and splitting the API sections into reference files would cut context cost substantially without losing guidance value.

Suggestions

Move the 'TypeScript Workflow-as-Code API (windmill-client)' and 'Python Workflow-as-Code API (wmill)' sections (~370 lines) into reference files such as references/typescript-api.md and references/python-api.md, keeping only the import lines and 2-3 key signatures inline with clearly signaled links.

State each conceptual rule once instead of repeating it per language: the retry-backoff semantics, cache_ttl keying, single-job/nested-task rule, and approval-key uniqueness each appear nearly verbatim in both API sections and the prose sections.

Add an explicit authoring sequence with a validation loop for the WAC half (scaffold file shape -> wrap side effects in task/step -> wmill script preview -> fix and re-preview -> generate-metadata -> diff locks), mirroring the checkpoint discipline the CLI section already has.

DimensionReasoningScore

Conciseness

Mostly efficient, non-obvious domain knowledge (checkpoint/replay semantics, single-job rule, failure record shape), but several explanations are duplicated nearly verbatim: the retry-backoff paragraph appears in both the TypeScript TaskRetry docstring and the Python task docstring, cache_ttl keying semantics appear twice, the 'a task runs as a single job' rule appears three times, and the preview-vs-deploy distinction is restated at least three times across the CLI sections. Deduplicating these and tightening the dense metadata-sync prose would save well over a hundred lines.

3 / 5

Actionability

Fully executable, copy-paste-ready code throughout: complete file shapes for both Bun TypeScript and Python, exact import lines, working examples for tasks, taskScript/taskFlow, steps, parallelism, approvals, and error handling, plus exact CLI commands (wmill script preview, generate-metadata, generate-metadata rehash, --dry-run) covering the common cases.

5 / 5

Workflow Clarity

The CLI half has a clear sequence with most checkpoints present — preview validates local edits before any deploy, '--dry-run' lists stale items before narrowing with a path, regenerated locks are diffed and version changes reported, and deploys are gated on explicit user request. However, the WAC authoring half is organized as rules and API reference rather than an explicit end-to-end sequence, and there is no articulated fix-and-retry loop for a failed preview.

4 / 5

Progressive Disclosure

Section structure is good and external references that exist are clearly signaled (AGENTS.wmill.md, the preview skill), but roughly 370 lines — about 60% of the file — are inline TypeScript and Python API reference sections that clearly belong in separate reference files (e.g. references/typescript-api.md, references/python-api.md), matching the rubric's example of API reference inlined in SKILL.md.

3 / 5

Total

15

/

20

Passed

Description

70%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.

A solid trigger-focused description with an explicit and well-qualified 'use when' clause covering both SDK naming conventions. Its main weakness is that it is entirely a trigger statement — the skill's actual capabilities are never stated, and a few natural synonyms (WAC, waitForApproval, parallel) are missing.

Suggestions

Lead with a capability statement before the trigger clause, e.g. 'Author Windmill Workflow-as-Code scripts with checkpoint-safe tasks, approvals, and parallel execution. MUST use when...' — this explicitly answers 'what' as well as 'when'.

Add the remaining natural trigger terms: 'WAC', 'waitForApproval', 'wait_for_approval', and 'parallel'.

DimensionReasoningScore

Specificity

Names the domain ('Windmill Workflow-as-Code scripts') and two actions ('writing or modifying'), but lists no concrete capabilities of the skill itself — the SDK names that follow (workflow, task, step, sleep, approvals, taskScript...) function as trigger terms, not described actions. Fits anchor 3 (domain plus 1-2 concrete actions, not comprehensive); not 4, which requires several specific listed actions.

3 / 5

Completeness

The 'when' is explicit and strong ('MUST use when writing or modifying Windmill Workflow-as-Code scripts using workflow, task, step...'), but there is no leading capability statement, so the 'what' (what the skill provides — authoring guidance, checkpoint/replay rules, API reference) is only implied by the trigger clause rather than explicitly stated. Sits between anchor 4 and the fully explicit both-parts anchor 5.

4 / 5

Trigger Term Quality

Good keyword coverage with genuine synonym awareness — both naming conventions are included ('taskScript, taskFlow' and 'task_script, task_flow') alongside natural terms like 'workflow', 'task', 'approvals'. A few natural terms are missing: 'WAC', 'waitForApproval'/'wait_for_approval', 'parallel', 'getApprovalUrls'. Not 5, which requires comprehensive coverage including the remaining common variants.

4 / 5

Distinctiveness Conflict Risk

Clear niche: 'Windmill Workflow-as-Code' plus distinctive SDK identifiers (taskScript, taskFlow, task_script, task_flow) are unlikely to fire for unrelated skills. Minor overlap risk remains because the trigger list also includes broadly generic terms ('workflow', 'task', 'step', 'sleep', 'approvals') that appear in many workflow-adjacent contexts (GitHub Actions, Airflow, general automation), fitting anchor 4 rather than 5.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (621 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

Reviewed

Table of Contents

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.