prompt-factory

World-class prompt powerhouse that generates production-ready mega-prompts for any role, industry, and task through intelligent 7-question flow, 69 comprehensive presets across 15 professional domains (technical, business, creative, legal, finance, HR, design, customer, executive, manufacturing, R&D, regulatory, specialized-technical, research, creative-media), multiple output formats (XML/Claude/ChatGPT/Gemini), quality validation gates, and contextual best practices from OpenAI/Anthropic/Google. Supports both core and advanced modes with testing scenarios and prompt variations.

2.25x

Quality

33%

Does it follow best practices?

Impact

88%

2.25x

Average score across 3 eval scenarios

Securityby

Risky

Do not use without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./generated-skills/prompt-factory/SKILL.md

Quality

Content

35%

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

This skill suffers from severe verbosity, repeating critical constraints 3+ times and explaining obvious concepts. While it has good structural bones (clear workflow, question banks, template formats), the excessive length (~700+ lines) undermines usability. The content would be significantly more effective at 1/3 the current size with concrete examples replacing abstract placeholders.

Suggestions

Reduce the CRITICAL CONSTRAINTS section to a single 5-line summary instead of repeating the same points with checkmarks, X marks, and prose explanations

Move the 69 presets list to a separate PRESETS.md file and reference it with a one-liner, keeping only 3-5 example presets inline

Replace placeholder-heavy template examples (e.g., '[Role title with expertise]') with one fully concrete example showing a real generated prompt

Add specific validation commands or checks for the 7-point quality gates (e.g., 'Run: python scripts/validator.py --check-xml' instead of just '✓ XML Structure')

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~700+ lines with excessive repetition of constraints (the 'CRITICAL CONSTRAINTS' section repeats the same points multiple times), redundant explanations Claude already knows (what XML is, how to copy/paste), and unnecessary emoji decorations throughout.	1 / 3
Actionability	Provides concrete template structures and question banks, but much is pseudocode-like with placeholders like '[Role title with expertise]' rather than fully executable examples. The Python script examples are concrete but the core prompt generation templates are abstract.	2 / 3
Workflow Clarity	Has clear 8-step workflow with numbered phases, but validation is mentioned without concrete verification steps (just checkmarks). The 7-point quality gates are listed but lack specific how-to-verify instructions, and there's no feedback loop for fixing failed validations.	2 / 3
Progressive Disclosure	References external files appropriately (templates/presets/, references/best-practices/) but the main document is a monolithic wall of text with massive inline content that should be split. The 69 presets list and full template examples could be in separate reference files.	2 / 3
	Total	7 / 12 Passed

Description

32%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description suffers from excessive marketing language ('world-class', 'powerhouse', 'mega-prompts') that obscures rather than clarifies its purpose. While it attempts to be comprehensive by listing many features and domains, it lacks the critical 'Use when...' guidance needed for skill selection and uses unnatural terminology that users wouldn't typically say.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases like 'when the user asks to write a prompt', 'create a system prompt', 'help with prompt engineering', or 'generate instructions for an AI'.

Replace marketing buzzwords ('world-class', 'powerhouse', 'mega-prompts') with concrete action verbs in third person (e.g., 'Generates structured prompts', 'Creates system instructions').

Simplify the feature list to focus on core capabilities rather than exhaustively listing all 15 domains and 69 presets, which adds noise without helping skill selection.

Dimension	Reasoning	Score
Specificity	Names the domain (prompt generation) and mentions some actions like '7-question flow', 'quality validation gates', and 'testing scenarios', but the language is heavily padded with marketing buzzwords ('world-class', 'powerhouse', 'mega-prompts') rather than concrete, actionable capabilities.	2 / 3
Completeness	Describes what it does (generates prompts with various features) but completely lacks any 'Use when...' clause or explicit trigger guidance. There is no indication of when Claude should select this skill over others.	1 / 3
Trigger Term Quality	Includes some relevant keywords like 'prompt', 'XML', 'Claude', 'ChatGPT', 'Gemini', and domain names, but lacks natural user phrases. Users would say 'help me write a prompt' or 'create a system prompt' rather than 'mega-prompts' or 'prompt powerhouse'.	2 / 3
Distinctiveness Conflict Risk	The focus on prompt generation is somewhat distinctive, but the extremely broad scope ('any role, industry, and task', '15 professional domains') makes it unclear when this should trigger versus other writing or generation skills.	2 / 3
	Total	7 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1110 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Repository: thinmintdev/claude-cooker
Commit: e5df233

Reviewed: 4 months 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.