prompt-architect
Create and enhance prompts, system instructions, and principle files. Capabilities: transform verbose prompts, add patterns/heuristics, optimize token usage, structure CLAUDE.md principles, improve agent/persona definitions, apply prompt engineering techniques (CoT, few-shot, ReAct). Actions: create, enhance, optimize, refactor, compress prompts. Keywords: prompt engineering, system prompt, CLAUDE.md, principle files, instruction optimization, agent prompt, persona prompt, token efficiency, prompt structure, workflow prompts, rules, constraints, few-shot, chain-of-thought, soul, tensions, dialectic. Use when: creating new prompts, enhancing principle files, improving system instructions, optimizing CLAUDE.md, restructuring verbose prompts, adding patterns to workflows, defining agent behaviors.
91
Quality
88%
Does it follow best practices?
Impact
95%
1.28xAverage score across 3 eval scenarios
Passed
No known issues
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 an excellent skill description that comprehensively covers capabilities, actions, keywords, and explicit usage triggers. It uses proper third-person voice throughout and provides specific technical terms (CoT, few-shot, ReAct) alongside natural language variations. The structured format with labeled sections (Capabilities, Actions, Keywords, Use when) makes it highly scannable and complete.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'transform verbose prompts, add patterns/heuristics, optimize token usage, structure CLAUDE.md principles, improve agent/persona definitions, apply prompt engineering techniques (CoT, few-shot, ReAct)' along with explicit action verbs 'create, enhance, optimize, refactor, compress prompts.' | 3 / 3 |
Completeness | Clearly answers both what (capabilities and actions sections) AND when with explicit 'Use when:' clause listing specific trigger scenarios like 'creating new prompts, enhancing principle files, improving system instructions, optimizing CLAUDE.md'. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say including 'prompt engineering', 'system prompt', 'CLAUDE.md', 'principle files', 'agent prompt', 'persona prompt', 'few-shot', 'chain-of-thought', and common variations like 'rules', 'constraints', 'soul', 'tensions'. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on prompt engineering and principle file creation with distinct triggers like 'CLAUDE.md', 'principle files', 'system prompt', 'agent prompt' that are unlikely to conflict with general coding or document skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable skill with excellent workflow clarity and concrete guidance through decision tables, transformation examples, and ready-to-use templates. The dialectic/tensions approach is well-articulated with genuine depth. Main weaknesses are moderate verbosity (some concepts repeated across sections) and the monolithic structure that could benefit from progressive disclosure to separate files.
Suggestions
Extract the detailed building_blocks section into a separate BUILDING_BLOCKS.md reference file, keeping only a summary in the main skill
Consolidate the multiple explanations of 'tensions' (appears in soul, tensions section, key_transformations, and example) into a single authoritative definition with cross-references
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some redundancy—the tensions concept is explained multiple times across sections, and some examples could be tightened. However, it largely avoids explaining concepts Claude already knows and uses domain-specific terminology efficiently. | 2 / 3 |
Actionability | Highly actionable with concrete patterns, executable YAML/XML templates, specific transformation examples (before/after), decision tables for mode detection and technique selection, and copy-paste ready building blocks. The example output demonstrates exactly what to produce. | 3 / 3 |
Workflow Clarity | Clear workflow: detect mode → diagnose type/complexity → select techniques → apply building blocks → validate. The summary section provides an explicit numbered sequence, and validation criteria serve as checkpoints. Decision tables make branching logic unambiguous. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and tables, but it's a monolithic ~300-line file that could benefit from splitting detailed building blocks or examples into separate reference files. No external file references are provided for advanced patterns or extended examples. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- majiayu000/claude-skill-registry
- Commit
6213d1a
- 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.