vibe-build

Build your MVP following the AGENTS.md plan. Use when the user wants to start building, implement features, or says "build my MVP", "start coding", or "implement the project".

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/vibe-build/SKILL.md

Quality

Content

77%

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

The content is a clearly sequenced, actionable build workflow with strong validation checkpoints. Its weaknesses are generic behavioral coaching that pads the token budget and a monolithic structure with no progressive disclosure.

Suggestions

Trim or remove generic coaching sections (Communication Style, Error Handling, Asking for Help, What NOT To Do) that restate behavior Claude already applies, keeping only vibe-workflow-specific guidance.

Move detailed build-order phase lists and message templates into a bundled reference file (e.g., references/build-order.md) and link to it from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-structured, but sections like "Communication Style", "Error Handling" ("Don't apologize"), and "Asking for Help" coach behavior Claude already knows, so it could be tightened rather than earning level 3.	2 / 3
Actionability	For an instruction-only skill it provides concrete commands (`npm test`, `npm run lint`), specific file references (AGENTS.md, agent_docs/), and copy-paste templates (Current State markdown, completion message), meeting the actionable bar.	3 / 3
Workflow Clarity	The Plan -> Execute -> Verify workflow is clearly sequenced with explicit validation checkpoints (run tests/linter, fix before moving on) and a fix-retry feedback loop, matching the level-3 anchor.	3 / 3
Progressive Disclosure	The ~190-line body is a single monolithic file with no bundle references to offload detail (e.g., build-order phases or templates), and it exceeds the 50-line simple-skill threshold, so structure is present but content that could be separate stays inline.	2 / 3
	Total	10 / 12 Passed

Description

82%

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

The description is well-formed with an explicit what-and-when structure and natural trigger terms. Its main weakness is mild genericness in a couple of triggers and only a single concrete action named.

Dimension	Reasoning	Score
Specificity	"Build your MVP following the AGENTS.md plan" names a concrete domain (MVP building) and one main action tied to a plan file, but does not enumerate multiple specific concrete actions, so it sits at level 2 rather than 3.	2 / 3
Completeness	It answers both what ("Build your MVP following the AGENTS.md plan") and when (explicit "Use when the user wants to start building, implement features, or says..." clause), matching the level-3 anchor.	3 / 3
Trigger Term Quality	The "Use when..." clause lists natural phrases users would actually say — "build my MVP", "start coding", "implement the project" — giving good coverage of realistic trigger terms.	3 / 3
Distinctiveness Conflict Risk	The MVP-building niche is reasonably distinct, but generic triggers like "start coding" and "implement the project" could overlap with general coding/building skills, so it is not a clear level-3 niche.	2 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: KhazP/vibe-coding-prompt-template
Path: .claude/skills/vibe-build/SKILL.md
Commit: 06d0796

Reviewed: about 18 hours 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.