prompt-builder

Build effective prompts for Claude Code skills. Creates clear, specific, actionable prompts using engineering principles, templates, and validation. Use when creating skill instructions, workflow steps, task operations, or any Claude prompt.

Quality

73%

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 ./skills/prompt-builder/SKILL.md

Quality

Content

62%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 well-sequenced, highly actionable prompt-building workflow with strong validation feedback loops, undermined by significant verbosity and redundant duplication between the body and the reference files. Progressive disclosure is weakened by generic, end-only reference signaling.

Suggestions

Trim redundancy: remove the Common Mistakes good/bad examples (duplicated from Step 2) and the Quick Reference re-summary, or convert them to inline links into the reference files.

Replace generic end-of-document reference pointers with inline, context-specific links — e.g., link prompt-templates.md from Step 3 and prompt-engineering-principles.md from the Best Practices section.

Move the inlined prompt templates and principles out to the existing reference files so SKILL.md stays a lean overview rather than restating what references/ already covers.

Dimension	Reasoning	Score
Conciseness	At ~870 lines the body is noticeably verbose with several padded/redundant sections — Common Mistakes reuses the Step 2 good/bad examples, Quick Reference re-summarizes the whole workflow, and Best Practices repeats Step 5 principles — and it over-explains prompt-engineering concepts Claude already knows, fitting the 2 anchor better than the tighter 3.	2 / 5
Actionability	Provides concrete, copy-paste-ready templates (task definition, core prompt structure, workflow/task/analysis/creation patterns) plus a real validation script, giving mostly executable guidance with only minor gaps, so 4 rather than a fully-covered 5.	4 / 5
Workflow Clarity	The 5-step workflow is clearly sequenced with explicit →Output/→Next transitions, a dedicated Step 5 'Refine & Validate' with quality dimensions, testing strategies, and 'Common Issues & Fixes' feedback loops, plus checklists throughout — matching the top anchor.	5 / 5
Progressive Disclosure	references/ and scripts/ contain real, relevant files, but they are only signaled by a generic end-of-document pointer rather than inline links at the relevant steps, and the body inlines templates/principles that duplicate the reference files, fitting the 3 anchor.	3 / 5
	Total	14 / 20 Passed

Description

83%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, concise description that clearly states both capability and trigger conditions with concrete natural-language phrases. It is specific and distinctive, with only minor gaps in keyword coverage and overlap risk.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Build effective prompts', 'Creates clear, specific, actionable prompts using engineering principles, templates, and validation' — with only minor coverage gaps, matching the 'lists several specific actions' anchor rather than the comprehensive 5.	4 / 5
Completeness	Explicitly answers both what ('Build effective prompts... Creates clear, specific, actionable prompts') and when ('Use when creating skill instructions, workflow steps, task operations, or any Claude prompt') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural trigger phrases ('creating skill instructions, workflow steps, task operations, or any Claude prompt') give good keyword coverage a user would actually say, though a few synonyms are missing, so it sits at 4 rather than a comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (prompt-building for Claude Code skills) with distinct triggers, but minor overlap risk remains with closely related skill-builder skills, placing it at 4 rather than 5.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (878 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	14 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/prompt-builder/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.