CtrlK
BlogDocsLog inGet started
Tessl Logo

vibe-agents

Generate AGENTS.md and AI configuration files for your project. Use when the user wants to create agent instructions, set up AI configs, or says "create AGENTS.md", "configure my AI assistant", or "generate agent files".

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 skill is a well-sequenced, directive workflow with strong copy-paste tool configs and a clear placeholder system. Its main weakness is that the entire template-instantiation step references a /templates/ bundle that is not shipped, which hurts both actionability and progressive disclosure.

Suggestions

Ship the referenced templates/ directory (AGENTS.md, MEMORY.md, REVIEW-CHECKLIST.md, agent_docs/*.md, tool-adapters/) as bundle files so the core 'instantiate the templates' step is executable and the references resolve to real content.

Add an explicit post-generation verification feedback loop — e.g. grep for any remaining [REPLACE:]/[CHOOSE:] placeholders and confirm every expected output file exists — before the 'After Completion' summary.

Tighten the discursive prose sections ('Session Continuity', 'Your Role', 'Naming Policy') into concise bullets to improve token efficiency.

DimensionReasoningScore

Conciseness

The body is directive and well-structured with copy-paste config blocks and specific fill instructions; it does not pad with concepts Claude already knows, so most tokens earn their place.

3 / 3

Actionability

Provides concrete, copy-paste-ready configs (CLAUDE.md, .cursor/rules/vibe.mdc, .agent/rules/vibe.md) and a clear placeholder system, but the central Step 3 ('Read and instantiate the canonical templates in /templates/') depends on template files that are not shipped in the bundle, leaving the core action incomplete.

2 / 3

Workflow Clarity

A clearly numbered sequence (Load Context → Ask Questions → Instantiate Templates → Generate Tool Configs → After Completion) with a prerequisite guard ('If either is missing, suggest running the appropriate skill first') and a completion check ('No square-bracket placeholders may remain').

3 / 3

Progressive Disclosure

The body is well-organized and signals one-level-deep references via the template/destination table, but the referenced detail files (templates/AGENTS.md, templates/agent_docs/*.md, templates/tool-adapters/) are absent from the bundle, so the disclosed references are dangling rather than functional.

2 / 3

Total

10

/

12

Passed

Description

100%

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 specific, uses natural quoted trigger phrases, and explicitly covers both what the skill does and when to invoke it. It is written in imperative/third-person voice with no first- or second-person phrasing that would trigger a penalty.

DimensionReasoningScore

Specificity

Names concrete deliverables and actions — 'Generate AGENTS.md and AI configuration files for your project' — rather than vague language, matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Clearly answers both 'what' (generate AGENTS.md and AI configuration files) and 'when' with an explicit 'Use when the user wants to...' clause and enumerated triggers.

3 / 3

Trigger Term Quality

Includes direct quoted user utterances ('create AGENTS.md', 'configure my AI assistant', 'generate agent files') plus 'create agent instructions' and 'set up AI configs', giving strong coverage of natural trigger terms.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (agent-instruction-file generation) with specific quoted triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
KhazP/vibe-coding-prompt-template
Reviewed

Table of Contents

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.