vibe-coding

Transform an AI agent into a tasteful, disciplined development partner. Not just a code generator, but a collaborator with professional standards, transparent decision-making, and craftsmanship. Use for any development task: building features, fixing bugs, designing systems, refactoring. The human provides vision and decisions. The agent provides execution with taste and discipline.

Quality

70%

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 ./packages/builtin-skills/skills/vibe-coding/SKILL.md

Quality

Content

66%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 body is a well-structured, actionable guide with strong workflow sequencing and validation checkpoints and a genuine, well-signaled reference bundle. Its main weakness is conciseness: significant verbosity, repeated slogans, and conceptual padding that competes with context for little added value.

Suggestions

Cut repeated slogans ('Human provides the Vibe. Agent provides the Code' appears multiple times) and trim conceptual padding about trust/craftsmanship that Claude already knows, to improve token efficiency.

Move the large inlined template blocks (Discovery/Design/Execution prompts) into a reference file and keep SKILL.md as a lean overview, removing the duplicated quick-reference box.

Consolidate the NEVER list, Quality checklist, and Communication Standards where they overlap to reduce redundant sections.

Dimension	Reasoning	Score
Conciseness	The ~715-line body is noticeably verbose, with repeated slogans, conceptual padding about trust/craftsmanship Claude already knows, and illustrative template blocks; matches the score-2 anchor of 'several unnecessary explanations or padded sections', kept from 3 by genuine structural value.	2 / 5
Actionability	Provides concrete, specific templates (Discovery questions, Design proposal, RAPID debug, code review) and exact mandatory reference paths; the placeholder-filled code blocks are templates rather than executable code, but as an instruction/collaboration skill the guidance is actionable, matching 'mostly executable guidance; minor gaps'.	4 / 5
Workflow Clarity	Multi-step processes (Discovery → Design → Execution → Debug) are clearly sequenced with explicit confirmation checkpoints and feedback loops, plus verification woven through each task; matches the score-5 anchor of clear sequence with explicit validation steps and error-recovery loops.	5 / 5
Progressive Disclosure	A real, well-organized references/ and assets/ bundle is surfaced via a 'Reference File Index' table with one-level-deep, verified paths; held at 4 by an inlined quick-reference box that duplicates the index and template content that could live in reference files.	4 / 5
	Total	15 / 20 Passed

Description

75%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 clearly answers what the skill does and when to use it, with concrete development-task trigger phrases and a distinct collaborative-partner framing. It is slightly held back by aspirational language and missing synonym variations that would push specificity, completeness, and trigger quality to a clean 5.

Suggestions

Tighten the 'what' from aspirational framing ('transform into a development partner') to a more functional verb-led statement of what the skill actually does.

Add natural trigger synonyms and phrasings users might say (e.g., 'writing code', 'shipping features', 'cleaning up code') to broaden trigger-term coverage.

Consider narrowing 'any development task' or adding a sharper distinguishing clause to reduce overlap risk with generic coding assistants.

Dimension	Reasoning	Score
Specificity	Names the development domain and several concrete actions ('building features, fixing bugs, designing systems, refactoring'), matching the score-4 anchor with only minor aspirational framing gaps; not a clean 5 because the 'transform into a development partner' framing is partly abstract rather than purely functional.	4 / 5
Completeness	Explicitly answers both 'what' (transform into a disciplined development partner) and 'when' ('Use for any development task: building features, fixing bugs, designing systems, refactoring'); not 5 because the 'what' is aspirational rather than a tight functional statement.	4 / 5
Trigger Term Quality	Includes natural task phrases users actually say ('building features, fixing bugs, designing systems, refactoring') with good coverage; falls short of 5 because synonyms and additional natural variations are absent.	4 / 5
Distinctiveness Conflict Risk	The 'any development task' scope risks overlap with generic coding assistants, but the specific taste/discipline/collaboration framing gives a distinct niche and concrete triggers, matching 'mostly distinct; minor overlap risk'.	4 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (727 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 21 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: shareAI-lab/Kode-CLI
Path: packages/builtin-skills/skills/vibe-coding/SKILL.md
Commit: c7f6fcc

Reviewed: 3 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.