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.

3.17x

Quality

70%

Does it follow best practices?

Impact

89%

3.17x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/project-scaffold/SKILL.md

Quality

Content

57%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable scaffolding skill whose body is undercut by self-inconsistency: it inlines a long example its own rules forbid, omits a validation phase for a batch operation, and terminates with an unclosed code fence. Tightening the embedded template and adding a verify phase would lift the weaker dimensions.

Suggestions

Add a Phase 4 validation step that checks every generated artifact against the Size Limits table (e.g. line counts, splitting oversized files) before declaring the scaffold complete.

Externalize the embedded testing SKILL.md template into references/testing-skill.template.md and reference it with "See: references/testing-skill.template.md", matching the skill's own >20-line rule.

Close the unterminated ```markdown code fence at the end of the file and replace placeholder stubs like [Stack-specific examples] with concrete guidance or an explicit pointer to a template.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete question lists and file paths, but the 3-tier progressive-disclosure ASCII tree re-explains concepts Claude already knows and the ~35-line inlined testing SKILL.md template pads the body.	3 / 5
Actionability	Provides concrete file paths, directory structures, multiple-choice discovery questions, and a full worked template, but the template leaves several placeholders unfilled ([PROJECT_STACK], [Language-specific test template], [Stack-specific examples]).	4 / 5
Workflow Clarity	Phases 1–3 are clearly sequenced, but this batch artifact-generation workflow has no validation/verification checkpoint (e.g. confirming generated files respect the stated size limits), which caps the score; the body also ends mid-template with an unclosed code fence.	3 / 5
Progressive Disclosure	Sections are organized, but the skill ships no bundle files and inlines a long example that its own rules say should live in examples.md; the referenced files (templates/, reference.md, checklist.md) are outputs to generate, not navigable references within this skill.	3 / 5
	Total	13 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states both capability and triggers in third person, with concrete actions and a well-defined niche. It could be tightened by trimming the "comprehensive" fluff and adding a few more natural synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — "Asks about project goals, tech stack, team size, and workflows, then generates custom instructions, skills, agents, and MCP configurations" — but "comprehensive agentic development scaffold" is mildly abstract, leaving minor gaps versus the fully comprehensive anchor.	4 / 5
Completeness	Explicitly answers both what (an interactive wizard that asks questions and generates instructions/skills/agents/MCP configs) and when (a concrete "Use when..." clause with specific trigger scenarios).	5 / 5
Trigger Term Quality	Natural trigger phrases are present ("Use when starting a new project or adding AI capabilities to an existing codebase") that users would actually say, but common synonyms like "scaffold", "bootstrap", or "set up AI tooling" are missing.	4 / 5
Distinctiveness Conflict Risk	The "agentic development scaffold" niche with project-setup triggers is mostly distinct, but "starting a new project" is broad enough to risk minor overlap with general project-setup or coding skills.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: 0xrabbidfly/eric-cartman
Path: .github/skills/project-scaffold/SKILL.md
Commit: 0b8453f

Reviewed: 5 days 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.