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.

Install with Tessl CLI

npx tessl i github:0xrabbidfly/eric-cartman --skill project-scaffold

What are skills?

3.17x

Quality

77%

Does it follow best practices?

Impact

89%

3.17x

Average score across 3 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./.github/skills/project-scaffold/SKILL.md

SKILL.md

Review

Evals

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 explains what the skill does and when to use it. The main weakness is the use of second person voice ('guides you through') which violates the style guidelines, and trigger terms could include more natural user phrases like 'setup' or 'bootstrap'. Otherwise, it provides good specificity and clear differentiation.

Suggestions

Rewrite in third person voice: 'Interactive wizard that guides users through creating...' or 'Guides through creating a comprehensive agentic development scaffold'

Add more natural trigger terms users might say: 'setup', 'initialize', 'bootstrap', 'configure Claude', 'project scaffolding'

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'guides you through creating a comprehensive agentic development scaffold', 'Asks about project goals, tech stack, team size, and workflows', 'generates custom instructions, skills, agents, and MCP configurations'.	3 / 3
Completeness	Clearly answers both what ('Interactive wizard that guides through creating scaffold, asks questions, generates 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 keywords like 'new project', 'AI capabilities', 'scaffold', 'MCP configurations', but uses second person 'you' and could include more natural variations users might say like 'setup', 'initialize', 'bootstrap', or 'configure Claude'.	2 / 3
Distinctiveness Conflict Risk	Clear niche focused on 'agentic development scaffold' with distinct triggers around project initialization and AI/MCP configuration - unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Implementation

70%

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 well-structured wizard workflow with clear phases and good organizational guidance. However, it lacks concrete examples of generated output and relies too heavily on placeholders like [PROJECT_STACK] and [Language-specific test template] rather than showing actual executable content. The meta-guidance about progressive disclosure is valuable but the skill itself could be more actionable.

Suggestions

Replace placeholder text like [Language-specific test template] with at least one concrete, executable example (e.g., a complete Jest or pytest test scaffold)

Add a concrete example of a fully generated `.github/copilot-instructions.md` file showing what the output should look like for a specific stack combination

Trim the progressive disclosure explanation section - Claude understands the pattern from a brief reference; the detailed tier breakdown adds tokens without adding value

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some redundant explanations (e.g., explaining the 3-tier pattern in detail when Claude would understand from a brief reference). The workflow questions section is appropriately structured but could be more compact.	2 / 3
Actionability	Provides a clear questionnaire structure and output file paths, but the actual generation logic is vague. The testing skill example is a template with placeholders rather than executable guidance. Missing concrete examples of what generated content should look like.	2 / 3
Workflow Clarity	Clear three-phase workflow (Discovery → Core Configuration → Skills) with explicit sequencing. Each phase has defined outputs and the progression is logical. The skill directory structure provides a clear checklist for generation.	3 / 3
Progressive Disclosure	Excellent structure with clear sections, well-organized tables for size limits, and the skill explicitly teaches progressive disclosure as a pattern. The required skill directory structure demonstrates proper file organization.	3 / 3
	Total	10 / 12 Passed

Validation

90%

Warnings & errors only

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

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.