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".
84
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Quality
Discovery
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 skill description that clearly defines its scope (generating and converting Claude Code prompt files), lists specific artifact types it handles, and provides an extensive set of explicit trigger terms. It uses proper third-person voice and is concise while being comprehensive. The only minor note is that 'GSD-style content separation' and 'quality gates' are somewhat jargon-heavy, but they serve as useful differentiators for the target audience.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generate prompt files, convert prompt files, and specifies subtypes (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 listed) and 'when' (explicit trigger phrases listed with 'Triggers on...' clause). Both dimensions are well-covered. | 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 phrases users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific niche of Claude Code prompt file generation/conversion with explicit artifact types (command orchestrators, skill files, agent role definitions). The trigger terms are specific enough to avoid conflicts with general coding or document skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
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 highly actionable and well-structured skill with excellent workflow clarity, clear validation checkpoints, and concrete executable guidance at every step. Its primary weakness is extreme verbosity — the content repeats the skill-vs-command distinction multiple times, includes extensive inline tables that could live in referenced spec files, and explains concepts at length that could be condensed. The progressive disclosure structure references external files but then duplicates much of their presumed content inline.
Suggestions
Reduce redundancy by stating the skill-vs-command distinction once (e.g., in Step 1) and removing the repeated explanations in the purpose block, Step 5a-skill, and Step 6b-skill.
Move the detailed convert mode logic (Steps 5c.1-5c.5) and the extensive quality gate tables (Steps 6b, 6b-skill, 6c) into the referenced spec files (conversion-spec.md, command-design-spec.md, agent-design-spec.md) and keep only summaries inline, since these specs are already listed in <required_reading>.
Condense parameter validation tables — Claude can infer regex patterns and min-length checks from a brief description rather than needing full table layouts for each parameter type.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines. It contains extensive tables, repeated explanations of the same concepts (e.g., skill vs command distinction is explained 4+ times), and detailed parameter validation tables that Claude could infer. The convert mode alone takes up massive space with inventory schemas and verification tables that could be dramatically condensed. | 1 / 3 |
Actionability | The skill provides highly concrete, executable guidance throughout: specific bash commands, exact file path patterns, structured Agent() call patterns, precise validation tables with pass/fail conditions, concrete AskUserQuestion examples with full option structures, and detailed quality gate checklists. Every step has specific actions rather than vague directions. | 3 / 3 |
Workflow Clarity | The 8-step process is clearly sequenced with explicit validation checkpoints: Step 6 is a mandatory quality gate with PASS/REVIEW/FAIL routing and retry logic, Step 7 includes post-write verification with fallback to Edit tool, and the convert mode has a mandatory content loss verification step (5c.5) that stops on failure. 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 — much of the detailed content (convert mode steps, quality gate tables, generation rules) could be split into the referenced spec files rather than duplicated inline. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%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
227244f
- 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.