prompt-generator

Generate or convert Claude Code prompt files — command orchestrators, skill files, agent role definitions, or style conversion of existing files. Follows GSD-style content separation with built-in quality gates. Triggers on "create command", "new command", "create skill", "new skill", "create agent", "new agent", "convert command", "convert skill", "convert agent", "prompt generator", "优化".

Quality

81%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

62%

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

This is a comprehensive, highly actionable skill with excellent workflow clarity and validation checkpoints. Its main weakness is extreme verbosity — the same rules (especially about skills not using @ references) are repeated many times, parameter tables are exhaustive where they could be condensed, and the skill doesn't practice the conciseness it would presumably enforce on generated content. The progressive disclosure is partially implemented through external spec references but the main file itself is a monolithic wall of content that could benefit from splitting.

Suggestions

Consolidate the repeated 'skills cannot use @ references' rule into a single prominent callout rather than restating it in sections 1, 5a-skill, 5c, 6b-skill, and multiple inline notes — this alone would save ~30 lines.

Move the detailed quality gate checks (6b, 6b-skill, 6c) into separate referenced files (e.g., specs/quality-gates.md) since they are reference material consulted at a specific step, not core workflow content.

Reduce parameter validation tables by combining common and type-specific parameters into a single compact table, removing the 'Example' column where the parameter name is self-explanatory.

Remove explanatory prose that restates what the tables/code already show (e.g., 'Skills are command-like orchestrators but loaded progressively inline' is stated in purpose, step 1, step 5a-skill, and step 5c).

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~350+ lines. It explains concepts Claude already knows (what commands/agents/skills are, basic file operations), includes extensive parameter tables, and repeats information across sections (e.g., skill-specific rules about no @ refs are stated at least 5 separate times). The content separation principle is explained multiple times. Much of this could be condensed by 50-70%.	1 / 3
Actionability	The skill provides highly concrete, executable guidance: specific bash commands, exact file path patterns, detailed validation tables with pass conditions, concrete AskUserQuestion call patterns, specific regex for name validation, and precise routing tables. Every step has actionable instructions rather than vague descriptions.	3 / 3
Workflow Clarity	The 8-step process is clearly sequenced with explicit validation checkpoints: Step 6 is a mandatory quality gate with specific pass/fail criteria and error recovery (re-generate on fail, user escalation on double-fail). Step 7 includes post-write verification with fallback to Edit tool. The convert mode includes a mandatory content loss verification step with quantitative thresholds. Feedback loops are well-defined throughout.	3 / 3
Progressive Disclosure	The skill references external spec and template files via @-references in <required_reading> (command-design-spec.md, agent-design-spec.md, conversion-spec.md, templates), which is good progressive disclosure. However, no bundle files were provided to verify these exist, and the SKILL.md itself is monolithic — the command generation, skill generation, agent generation, and convert mode logic are all inline rather than being split into separate phase files, despite the skill's own philosophy of progressive loading.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 is a strong description that clearly defines its niche (Claude Code prompt file generation/conversion), lists specific concrete actions, and provides explicit trigger terms. It follows best practices by using third person voice and including a comprehensive 'Triggers on' clause with natural user phrases. The only minor note is the inclusion of '优化' without context, but overall this is well-crafted.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: generate, convert prompt files, and specifies types (command orchestrators, skill files, agent role definitions, style conversion). Also mentions GSD-style content separation and quality gates.	3 / 3
Completeness	Clearly answers both 'what' (generate or convert Claude Code prompt files with specific types and methodology) and 'when' (explicit 'Triggers on' clause listing specific trigger phrases).	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms explicitly listed: 'create command', 'new command', 'create skill', 'new skill', 'create agent', 'new agent', 'convert command', 'convert skill', 'convert agent', 'prompt generator', and even a Chinese term '优化'. These are terms users would naturally say.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche focused specifically on Claude Code prompt file generation/conversion. The specific trigger terms like 'create command', 'create skill', 'create agent' are unlikely to conflict with other skills, and the domain (prompt file authoring) is well-defined.	3 / 3
	Total	12 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	10 / 11 Passed

Repository: catlog22/Claude-Code-Workflow
Commit: 07491b0

Reviewed: 20 days 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.