CtrlK
BlogDocsLog inGet started
Tessl Logo

workflow-builder

Design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.

69

Quality

85%

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

The canonical home for this skill is workflow-builder in alirezarezvani/claude-skills

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.

The SKILL.md body is well-organized, concise, and actionable with a sensible build-validate-run workflow, but its progressive disclosure is undermined because every referenced bundle file is missing. Fixing the absent references is the primary gap.

Suggestions

Add the missing bundle files referenced in the body — references/decision_and_intake_guide.md, references/api_reference.md, references/orchestration_patterns.md, scripts/workflow_intake.py, scripts/scaffold_workflow.py, scripts/validate_workflow.py, and assets/templates + assets/examples — so the signaled references resolve.

Add an explicit fix-and-revalidate feedback loop to the 'Build → validate → run loop' (e.g., 'If validation fails, fix the reported issues and re-run validate_workflow.py before running') to lift workflow clarity.

Move the JS orchestration copy-paste shapes (agent/pipeline/parallel usage) at least in skeleton form into the body or ensure orchestration_patterns.md exists and is linked, since actionability currently depends on files that are absent.

DimensionReasoningScore

Conciseness

The body is lean and sectioned, assumes Claude's competence, and avoids explaining concepts Claude already knows; only the opening motivational paragraph and the 'earn their cost' sentence feel slightly trimmable, so it sits just below the leanest anchor.

4 / 5

Actionability

Provides concrete, executable commands (intake, scaffold, validate) plus named injected globals and specific patterns like `results.filter(Boolean)`; the JS code shapes live in referenced files rather than inline, leaving minor gaps versus copy-paste-ready coverage.

4 / 5

Workflow Clarity

A clear intake → confirm → scaffold → edit → validate → run sequence with an explicit 'Validate before running' checkpoint is present, but there is no stated fix-and-revalidate feedback loop on validation failure.

4 / 5

Progressive Disclosure

References are clearly signaled and one level deep (references/*.md, scripts/*.py, assets/), but none of those bundle files or directories actually exist, so the overview cannot offload detail and navigation leads nowhere.

3 / 5

Total

15

/

20

Passed

Description

100%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 strong, third-person description that cleanly answers both what the skill does and when to invoke it, with rich trigger synonyms and a distinct niche. It hits the top anchor on every dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Design and write deterministic multi-agent workflow scripts', 'orchestrate sub-agents (fan-out, pipeline, loop, judge-panel)', 'automate a repeatable multi-step task' — giving comprehensive coverage rather than a single generic verb.

5 / 5

Completeness

Explicitly states what ('Design and write ... workflow scripts ... for Claude Code's Workflow tool') and when ('Use when a user wants to build, create, author, scaffold, or run ...'), satisfying both halves with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers natural user phrasings with synonyms ('build, create, author, scaffold, or run') plus technical triggers (fan-out, pipeline, loop, judge-panel) and the file/path cue '.js files in .claude/workflows/', matching the comprehensive-synonyms-plus-extension anchor.

5 / 5

Distinctiveness Conflict Risk

The niche is sharply scoped to Claude Code Workflow tool .js files with distinct orchestration triggers (fan-out/pipeline/loop/judge-panel), making accidental triggering of unrelated skills unlikely.

5 / 5

Total

20

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 missing

Warning

referenced_paths_exist

Referenced path issues: 14 missing

Warning

Total

14

/

16

Passed

Repository
alirezarezvani/claude-skills
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.