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.
69
56%
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 voice like 'Guides users through' or 'Interactive wizard for creating...'
Add more natural trigger terms users might say, such as 'setup', 'initialize', 'bootstrap', 'project template', or 'configure workspace'
| 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
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill describes a comprehensive scaffold generation wizard but suffers from significant verbosity and ironic self-contradiction — it teaches progressive disclosure while being a monolithic document. The questionnaire is well-structured but the generation guidance relies heavily on placeholders rather than concrete, actionable templates. Missing validation checkpoints between phases and no verification of generated output quality weaken the workflow.
Suggestions
Extract the discovery questionnaire, size limits table, and example SKILL.md template into separate bundle files (e.g., questionnaire.md, size-limits.md, templates/testing.template.md) to practice the progressive disclosure pattern the skill teaches.
Replace placeholder text like '[Language-specific best practices]' and '[project-specific command]' with concrete examples for at least one stack (e.g., TypeScript/React) to demonstrate actionable output.
Add explicit validation checkpoints: confirm discovery answers with user before generating, validate generated files against size limits, and verify directory structure completeness after generation.
Remove the explanation of the 3-tier progressive disclosure pattern (Claude can follow the rules without the diagram) and condense the size limits into a brief constraint list to improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~150+ lines. It includes extensive multiple-choice question lists that could be summarized, explains concepts like progressive disclosure tiers that Claude already understands, and includes a full example SKILL.md template inline (violating its own rule about not embedding examples >20 lines). Much of this content could be extracted to supporting files or condensed significantly. | 1 / 3 |
Actionability | The skill provides a structured questionnaire and describes what to generate, but the actual generation guidance is incomplete — Phase 2 uses placeholders like '[Language-specific best practices]' and '[project-specific command]' rather than concrete templates or executable examples. The testing skill example is a template with blanks rather than copy-paste ready content. | 2 / 3 |
Workflow Clarity | The three-phase workflow (Discovery → Core Configuration → Skills) is clearly sequenced, but there are no validation checkpoints between phases. There's no feedback loop for verifying generated output quality, no step to confirm discovery answers before proceeding, and no verification that generated files meet the stated size limits. | 2 / 3 |
Progressive Disclosure | Despite extensively describing the progressive disclosure pattern, the skill itself violates it — the entire content is a monolithic wall including inline tables, full directory structures, complete example SKILL.md templates, and the full questionnaire. No bundle files are provided, and the skill doesn't reference any supporting files for its own lengthy content (e.g., the questionnaire, templates, or examples could be extracted). | 1 / 3 |
Total | 6 / 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
17bd06f
- 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.