skill-generator
Meta-skill for creating new Claude Code skills with configurable execution modes. Supports sequential (fixed order) and autonomous (stateless) phase patterns. Use for skill scaffolding, skill creation, or building new workflows. Triggers on "create skill", "new skill", "skill generator".
69
62%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/skill-generator/SKILL.mdQuality
Discovery
89%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 solid description that clearly identifies its niche as a meta-skill for skill creation, includes explicit trigger terms, and answers both what and when. Its main weakness is that the specificity of concrete actions could be improved—it mentions execution modes but doesn't detail the specific outputs or steps involved in skill creation (e.g., generates YAML frontmatter, creates markdown templates, sets up file structure).
Suggestions
Add more concrete actions describing what the skill produces, e.g., 'Generates YAML frontmatter, markdown skill templates, and directory structure for new skills.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (skill creation) and mentions some actions like 'skill scaffolding' and 'building new workflows', and references configurable execution modes (sequential, autonomous). However, it doesn't list multiple concrete actions in detail—what exactly does it produce or do beyond scaffolding? | 2 / 3 |
Completeness | Clearly answers both 'what' (meta-skill for creating new Claude Code skills with configurable execution modes, supports sequential and autonomous phase patterns) and 'when' (explicit 'Use for' and 'Triggers on' clauses with specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'create skill', 'new skill', 'skill generator', 'skill scaffolding', 'skill creation', 'building new workflows'. These cover the most likely phrasings a user would use when wanting to create a new skill. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche—creating skills is a meta-level activity unlikely to conflict with domain-specific skills. The trigger terms 'create skill', 'new skill', 'skill generator' are highly specific and wouldn't overlap with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a comprehensive framework for generating new skills with two execution modes, but suffers significantly from verbosity and duplication. The entire 'Reference Documents by Phase' section is copy-pasted twice, and the content mixes high-level overview with detailed execution pseudocode that should live in phase files. The workflow is well-structured but lacks intermediate validation checkpoints and error recovery guidance.
Suggestions
Remove the duplicated 'Reference Documents by Phase' section - it appears twice in full, wasting significant tokens.
Move the detailed 'Execution Protocol' JavaScript pseudocode to a separate phase guide file, keeping only the high-level Execution Flow summary in SKILL.md.
Remove the 'Key Design Principles' and 'Architecture Overview' sections which explain concepts Claude can infer from the execution flow itself.
Add explicit validation checkpoints between phases (e.g., validate skill-config.json schema after Phase 1, verify directory structure after Phase 2) and describe error recovery steps if Phase 5 validation fails.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely verbose at ~350+ lines. The entire 'Reference Documents by Phase' section is duplicated verbatim. The architecture ASCII diagram, execution modes explanation, and design principles sections explain concepts Claude already understands. The JavaScript pseudocode in the Execution Protocol section largely restates what was already described in the Execution Flow section above it. | 1 / 3 |
Actionability | The execution flow provides a reasonably detailed step-by-step process with tool names (AskUserQuestion, Bash, Write, Glob, Read) and the JavaScript-style pseudocode gives concrete guidance. However, the code is pseudocode with undefined functions (generateConfig, generateSkillEntry, etc.) rather than executable code, and the actual generation logic is deferred entirely to external template and phase files. | 2 / 3 |
Workflow Clarity | The 6-phase pipeline (Phase 0-5) is clearly sequenced with inputs/outputs specified for each phase. However, validation is only present in Phase 5 as a final check rather than having intermediate validation checkpoints between phases. Phase 0 says 'MUST complete before Phase 1' but there's no mechanism to verify this. The feedback loop for error recovery is missing - Phase 5 validates but doesn't describe what to do if validation fails. | 2 / 3 |
Progressive Disclosure | The skill has extensive well-organized references to external files (specs/, templates/, phases/) with clear tables showing purpose and when to use each document. However, the 'Reference Documents by Phase' section is completely duplicated (appears twice identically), and the SKILL.md itself is monolithic with content that should be in the referenced phase files rather than inline (e.g., the full Execution Protocol pseudocode). | 2 / 3 |
Total | 7 / 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.