project-scaffold
Interactive wizard that guides you through creating a comprehensive agentic development scaffold. Use when starting a new project or adding AI capabilities to an existing codebase. Asks about project goals, tech stack, team size, and workflows, then generates custom instructions, skills, agents, and MCP configurations.
71
60%
Does it follow best practices?
Impact
89%
3.17xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.github/skills/project-scaffold/SKILL.mdQuality
Discovery
85%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 strong description that clearly communicates both what the skill does and when to use it, with specific outputs enumerated. The main weakness is the use of second person voice ('guides you through') which violates the third-person guideline, and some trigger terms lean toward jargon ('agentic development scaffold') rather than natural user language. Overall it would effectively help Claude select this skill in the right context.
Suggestions
Replace second person 'guides you through' with third person 'guides users through' to match voice guidelines.
Add more natural trigger terms users might say, such as 'setup', 'initialize', 'bootstrap', 'project template', or 'configure Claude for a project'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: guides through creating a scaffold, asks about project goals/tech stack/team size/workflows, generates custom instructions/skills/agents/MCP configurations. | 3 / 3 |
Completeness | Clearly answers both what ('interactive wizard that guides through creating a comprehensive agentic development scaffold, generates custom instructions, skills, agents, and MCP configurations') and when ('Use when starting a new project or adding AI capabilities to an existing codebase'). | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'new project', 'AI capabilities', 'scaffold', 'MCP configurations', but misses common user phrasings like 'setup', 'initialize', 'bootstrap', 'project template', or 'getting started'. Terms like 'agentic development scaffold' are somewhat jargon-heavy. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'interactive wizard', 'agentic development scaffold', and the specific outputs (instructions, skills, agents, MCP configurations) creates a clear niche that is unlikely to conflict 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 reasonable structural framework for scaffold generation but suffers from verbosity, explaining concepts Claude already understands (progressive disclosure tiers, test types) and using placeholder content instead of concrete, executable examples. The workflow lacks validation checkpoints between phases and the skill doesn't practice the progressive disclosure pattern it prescribes for generated output.
Suggestions
Replace placeholder text like '[Language-specific test template]' and '[project-specific command]' with at least one concrete, fully realized example for a common stack (e.g., TypeScript + React + Jest) so Claude has a clear model to follow.
Add explicit validation checkpoints between phases — e.g., 'Present generated file list to user for confirmation before writing' and 'Verify all generated files respect size limits before completing.'
Extract the lengthy question list and the generated skill template example into supporting files (e.g., `questions.md`, `templates/testing-skill.template.md`) to practice the progressive disclosure pattern the skill itself advocates.
Remove explanatory content Claude already knows — the progressive disclosure tier diagram, definitions of test types (unit/integration/e2e), and the 'When to Use' bullets that describe obvious scenarios.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~150+ lines with significant padding. It explains concepts Claude already knows (what unit/integration/e2e tests are, what progressive disclosure means), includes lengthy multiple-choice question lists that could be condensed, and the generated skill template example is generic placeholder content rather than actionable guidance. | 1 / 3 |
Actionability | The skill provides a structured questionnaire and outlines what to generate, but the actual generation guidance is incomplete — Phase 2 and Phase 3 use placeholders like '[Language-specific test template]' and '[project-specific command]' instead of concrete examples. The directory structures and size limits table are concrete, but the core generation logic is vague. | 2 / 3 |
Workflow Clarity | The three-phase workflow (Discovery → Core Config → Skills) is clearly sequenced, but there are no validation checkpoints — no step to verify generated files are valid, no feedback loop for reviewing output with the user, and no explicit confirmation gates between phases. For a generative/destructive operation creating many files, this is a significant gap. | 2 / 3 |
Progressive Disclosure | The skill describes progressive disclosure as a pattern to follow in generated output and defines a 3-tier structure, but the SKILL.md itself is a monolithic wall of text. It doesn't reference any supporting files for its own lengthy content (e.g., the full question list or template examples could be extracted). The skill teaches progressive disclosure without practicing it. | 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- 0xrabbidfly/eric-cartman
- Commit
1e34e1c
- 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.