create-skill
Use when creating a new skill, writing a skill from scratch, or converting a process into a reusable skill — enforces TDD, empirical validation, and quality monitoring
64
76%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/create-skill/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 with excellent trigger terms and completeness, clearly answering both what and when. Its main weakness is that the specific capabilities are described more in terms of methodology (TDD, empirical validation) rather than concrete actions the skill performs. The description would benefit from listing a few more specific actions like generating skill files or creating test suites.
Suggestions
Add more concrete action verbs describing what the skill actually produces, e.g., 'Generates SKILL.md files with proper frontmatter, creates test cases, and scaffolds skill structure'
Expand the methodology terms with brief clarifications so users unfamiliar with TDD understand the value, e.g., 'enforces test-driven development (writes tests before implementation)'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (skill creation) and mentions some approaches (TDD, empirical validation, quality monitoring), but doesn't list concrete actions like 'generates SKILL.md files', 'creates test cases', or 'writes frontmatter with YAML'. The actions are more about methodology than specific capabilities. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (enforces TDD, empirical validation, and quality monitoring for skill creation) and 'when' (creating a new skill, writing a skill from scratch, converting a process into a reusable skill) with a clear 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'creating a new skill', 'writing a skill from scratch', 'converting a process into a reusable skill'. These are phrases a user would naturally say when they need this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | The description targets a very specific niche — creating new skills with TDD methodology. The trigger terms ('new skill', 'skill from scratch', 'reusable skill') are distinct and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 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 well-structured meta-skill with excellent workflow clarity — the Mermaid flowchart, quality gates, and feedback loops are strong. However, actionability suffers from lack of concrete examples (what does a pressure scenario look like? what does a baseline failure document contain?) and references to external tools without documentation. The rationalization table is a creative and useful addition, though the overall content could be tightened.
Suggestions
Add a concrete, complete example of a pressure scenario and its baseline failure documentation to make the RED phase actionable rather than abstract.
Provide brief inline descriptions or links for external dependencies (tessl, Hindsight, ralph-loop, superpowers:writing-skills) so the skill is self-contained or clearly navigable.
Consider extracting the rationalization table and common mistakes into a referenced file to reduce the main skill's token footprint while preserving the critical workflow steps.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly well-structured but includes some verbosity — the rationalization table is extensive, some explanations are redundant (e.g., restating 'every box is mandatory' and 'skipping any box = start over'), and the Mermaid flowchart duplicates the step details. However, most content earns its place given the complexity of the process. | 2 / 3 |
Actionability | The workflow is clearly sequenced with specific steps, but many steps lack concrete executable examples. For instance, 'Write 3+ pressure scenarios' gives no example of what a pressure scenario looks like, 'Run scenarios WITHOUT the skill loaded' doesn't explain how to run them, and references to `tessl skill review` and `tessl eval run` assume tool availability without showing usage. The invocation syntax and search locations are concrete, but the RED/GREEN/REFACTOR phases are more descriptive than executable. | 2 / 3 |
Workflow Clarity | The Mermaid flowchart provides an excellent visual overview, and the step-by-step details clearly sequence the process with explicit validation checkpoints (quality gates table, pass/fail decision points, feedback loops for REFACTOR and ralph-loop). The 'every box is mandatory' constraint and the quality gates table serve as explicit verification checklists. | 3 / 3 |
Progressive Disclosure | The skill references external tools and skills (e.g., `superpowers:writing-skills`, `tessl`, `Hindsight`, `ralph-loop`) but doesn't provide links or paths to documentation for these. The content is well-organized with clear sections, but for a skill this long (~150 lines of substantive content), some sections like the detailed rationalization table or common mistakes could be split into referenced files. No bundle files are provided to support the references made. | 2 / 3 |
Total | 9 / 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
- AndreJorgeLopes/proof-of-skill
- Commit
4e8e219
- 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.