agent-creator
Create high-quality Claude Code agents from scratch or by adapting existing agents as templates. Use when the user wants to create a new agent, modify agent configurations, build specialized subagents, or design agent architectures. Guides through requirements gathering, template selection, and agent file generation following Anthropic best practices (v2.1.63+).
92
Quality
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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 a well-crafted skill description that excels across all dimensions. It provides specific actions, includes natural trigger terms users would actually say, explicitly states both what the skill does and when to use it, and carves out a clear niche around Claude Code agent creation that won't conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Create high-quality Claude Code agents from scratch', 'adapting existing agents as templates', 'requirements gathering', 'template selection', and 'agent file generation'. | 3 / 3 |
Completeness | Clearly answers both what (create agents, adapt templates, guide through requirements/selection/generation) AND when with explicit 'Use when...' clause covering multiple trigger scenarios (create new agent, modify configurations, build subagents, design architectures). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'create a new agent', 'modify agent configurations', 'build specialized subagents', 'design agent architectures', 'template'. These are terms users would naturally use when requesting this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche focused on 'Claude Code agents' with distinct triggers like 'agent configurations', 'subagents', 'agent architectures'. The version reference (v2.1.63+) and 'Anthropic best practices' further distinguish it from generic coding or documentation skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, comprehensive skill for creating Claude Code agents. It excels in actionability with concrete examples and workflow clarity with explicit validation phases. The main weakness is length - at ~700 lines, some content (particularly the extensive 'Common Mistakes' section) could be moved to reference files to improve token efficiency while maintaining the excellent structure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some redundancy and explanatory content that could be tightened. Tables and guides are useful but some sections (like the 'Common Mistakes' section at ~100 lines) could be condensed or moved to a reference file. | 2 / 3 |
Actionability | Provides fully executable guidance with concrete YAML examples, bash commands, specific templates, and copy-paste ready code blocks. The workflow phases are explicit with clear steps and validation commands. | 3 / 3 |
Workflow Clarity | Excellent multi-phase workflow with explicit validation checkpoints (Phase 6 validation checklist, Phase 8 post-creation validation). Includes clear feedback loops for testing and iteration, with specific commands like `uvx skilllint@latest check` and `claude plugin validate`. | 3 / 3 |
Progressive Disclosure | Well-structured with clear Quick Reference section pointing to one-level-deep references (agent-schema.md, agent-templates.md, agent-examples.md). Main content is organized with semantic XML tags and collapsible sections. Related skills clearly signaled. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1075 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- Jamie-BitFlight/claude_skills
- Commit
fd243f9
- 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.