Name: vibe-build
Rating: 49.6 (1 reviews)
Author: KhazP

Blog Docs Log in Get started

vibe-build

Implement an approved new-project slice and report actual checks. For changes to an existing app use vibe-change.

Quality

53%

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 ./.agents/skills/vibe-build/SKILL.md

The canonical home for this skill is vibe-build in KhazP/vibe-coding-prompt-template

Quality

Content

61%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.

The content is concise, competent, and appropriately delegates detail to a sibling skill, with sound validation guardrails (recovery checkpoints, do-not-fabricate, do-not-trust-passing-build). Its main weakness is that the workflow is presented as prose rather than an explicit sequenced checklist, and concrete execution detail is delegated rather than included.

Suggestions

Convert the implicit workflow into a short numbered sequence (read docs → set acceptance criteria → preserve work & record checkpoint → implement slice → run checks → update MEMORY.md → report) so the order and checkpoints are explicit.

Make the report section a concrete template with the five categories as bullet points or a fill-in structure rather than a prose sentence.

Clarify what 'an approved new-project slice' means in one phrase (e.g. scope, size) so the actionability gap between 'establish acceptance criteria' and 'implement' is narrower.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (e.g. 'doctor is setup validation only', 'Do not treat a passing build as proof of working behavior'), with only minor phrases that could be trimmed.	4 / 5
Actionability	It gives concrete process guidance (named files to read, a report template of Changed/Checked/Not checked/Next decision/Recovery) but delegates actual execution to other files and offers no commands or code, leaving key execution details implicit.	3 / 5
Workflow Clarity	An implicit read-then-implement-then-check-then-report sequence exists with real checkpoints (recovery checkpoint before risky changes, run checks), but steps are prose rather than enumerated and the actual journey is offloaded to vibe-verify, leaving the flow implicit.	3 / 5
Progressive Disclosure	For a sub-50-line single-purpose skill the body is well organized and points one level deep to a clearly signaled sibling ('Use ../vibe-verify/SKILL.md for the actual journey'), with no bundle files needed; minor sectioning gaps keep it just below 5.	4 / 5
	Total	14 / 20 Passed

Description

46%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.

The description states a concrete purpose and helpfully disambiguates from a sibling skill, but it lacks an explicit 'Use when' trigger and natural user-facing keywords. Specificity is adequate but not comprehensive.

Suggestions

Add an explicit 'Use when...' trigger phrase with natural terms users would say, e.g. 'Use when starting a brand-new project or scaffolding a new app from an approved plan.'

Expand the action list beyond 'implement' and 'report actual checks' to name concrete deliverables (e.g. 'scaffold the project, build one usable slice, and run the project's checks').

Include synonyms/common phrasings ('new app', 'greenfield project', 'scaffold') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('approved new-project slice') and two actions ('implement', 'report actual checks'), but 'report actual checks' is abstract and coverage is not comprehensive.	3 / 5
Completeness	It has a clear 'what' (implement a slice and report checks) but the 'when' is only weakly implied via a negative routing clause ('For changes to an existing app use vibe-change'), and no explicit 'Use when' clause is present, capping it at 3.	3 / 5
Trigger Term Quality	Only generic/jargon terms ('new-project slice') appear; the natural phrases a user would say ('build a new app', 'start a new project') are missing, and there is no explicit 'Use when' trigger.	2 / 5
Distinctiveness Conflict Risk	The explicit sibling-skill routing ('For changes to an existing app use vibe-change') gives it a clear niche and minimal conflict risk, though 'implement a slice' is still somewhat generic build language.	4 / 5
	Total	12 / 20 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: .agents/skills/vibe-build/SKILL.md
Commit: b00eb84

Reviewed: 4 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.