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 creating other skills, with explicit trigger terms and a clear 'when to use' clause. Its main weakness is that the specific capabilities could be more concrete — it mentions execution modes but doesn't detail the concrete outputs or steps involved in skill creation. Overall it performs well for skill selection purposes.
Suggestions
Add more concrete action verbs describing what the skill produces, e.g., 'Generates YAML frontmatter, creates phase templates, scaffolds directory structure' to improve specificity.
| 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 like 'generates YAML frontmatter, creates phase templates, validates skill structure'. | 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 triggers: 'Use for skill scaffolding, skill creation, or building new workflows. Triggers on "create skill", "new skill", "skill generator"'). | 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 likely phrasings a user would employ when wanting to create a new skill. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — creating Claude Code skills specifically. The trigger terms ('create skill', 'new skill', 'skill generator') are unlikely to conflict with other skills since this is a meta-skill about skill creation itself, not general code generation or document creation. | 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 has a well-thought-out architecture with clear phase separation and good use of external references, but suffers significantly from verbosity and duplication. The entire 'Reference Documents by Phase' section is duplicated word-for-word, and the execution flow is described three times in different formats (prose, pseudocode, and JavaScript). The content would benefit greatly from aggressive trimming and trusting the external files to carry the detail.
Suggestions
Remove the duplicated 'Reference Documents by Phase' section — it appears twice in full, wasting significant tokens.
Consolidate the execution flow into a single representation (either the structured prose OR the JavaScript pseudocode, not both) and move the detailed version to an external phase guide.
Add explicit error recovery/feedback loops between phases (e.g., 'If Phase 5 validation fails, return to Phase 3 and regenerate') to improve workflow clarity.
Move the detailed execution protocol JavaScript block to a separate file (e.g., specs/execution-protocol.md) and keep only a concise summary in SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The entire 'Reference Documents by Phase' section is duplicated verbatim (appears twice in full). The architecture diagram, execution flow, and execution protocol all convey overlapping information in three different formats. The content is extremely verbose at ~350+ lines when it could be condensed to under 100 lines with references to external files. | 1 / 3 |
Actionability | The execution protocol provides pseudocode with specific tool calls (Read, Write, Bash, AskUserQuestion) and concrete file paths, which is somewhat actionable. However, the JavaScript code is illustrative pseudocode (e.g., `generateConfig(answers)` is undefined), not truly executable, and the actual generation logic is deferred to external template/phase files. | 2 / 3 |
Workflow Clarity | The phases are clearly sequenced (0-5) with inputs and outputs defined for each. However, validation is only present in Phase 5 as a final check rather than having feedback loops between phases. There's no explicit error recovery guidance (e.g., what happens if Phase 3 generation fails or if validation in Phase 5 finds issues). | 2 / 3 |
Progressive Disclosure | The skill does reference many external files (specs, templates, phases) with clear tables and links, which is good progressive disclosure structure. However, the SKILL.md itself is a monolithic wall of text that inlines too much detail (full execution protocol, duplicated reference tables, detailed architecture diagrams) that should live in the referenced phase files instead. | 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
0f8e801
- 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.