CtrlK
BlogDocsLog inGet started
Tessl Logo

vibe-agents

Generate project agent instructions from agreed requirements and technical decisions. Not for ordinary incremental feature changes.

55

Quality

62%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/vibe-agents/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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, concrete, and well-sequenced with real validation checkpoints, making it strongly actionable for an instruction skill. The main weakness is structural: it lacks section organization despite being otherwise tidy.

Suggestions

Add section headers (e.g. '## Setup', '## Validation', '## No-filesystem fallback') to turn the flowing paragraphs into scannable, well-organized sections.

Make the validation feedback loop explicit, e.g. 'Run `npx vibeworkflow doctor`; if it reports required errors, fix them and re-run until required errors are clear.'

Tighten the densely packed sentences (split the dry-run/initialize/force paragraph) so each instruction earns its own line.

DimensionReasoningScore

Conciseness

The body is lean and command-driven with no over-explanation of concepts Claude already knows; a few densely packed sentences mix multiple instructions and could be trimmed slightly, keeping it just below the 'every token earns its place' level 5.

4 / 5

Actionability

It gives concrete copy-paste commands ('npx vibeworkflow --dry-run --json', 'npx vibeworkflow doctor') and specific paths (docs/PRD-*-MVP.md, AGENTS.md, MEMORY.md, agent_docs), but steps like 'Fill required placeholders from decisions' remain abstract, leaving minor gaps.

4 / 5

Workflow Clarity

There is a clear sequence (read PRD/Tech Design -> dry-run -> initialize -> fill placeholders -> doctor -> resolve) with validation checkpoints (dry-run, doctor), so the destructive/batch cap does not apply; however the error-recovery feedback loop is only implied ('resolve required setup errors') rather than explicit re-run-until-clean.

4 / 5

Progressive Disclosure

No bundle files exist and the body is short and self-contained, but it is flowing prose under a single H1 with no section headers, so while no external references are needed, the content could be better organized into labeled sections.

3 / 5

Total

15

/

20

Passed

Description

53%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 gives a clear, concise statement of what the skill does and a useful negative boundary, but lacks a positive 'Use when...' trigger and broader natural trigger terms. Completeness is the main limiter due to the missing explicit trigger clause.

Suggestions

Add a positive 'Use when...' clause, e.g. 'Use when bootstrapping agent instructions for a new project from an agreed PRD and tech design.'

Broaden trigger terms with natural user phrasings and synonyms (e.g. 'set up project agents', 'agent rules', 'AGENTS.md', 'project bootstrap').

List one or two more concrete actions (e.g. 'reconcile PRD and tech design conflicts', 'generate AGENTS.md, MEMORY.md, and agent_docs') to lift specificity.

DimensionReasoningScore

Specificity

The phrase 'Generate project agent instructions from agreed requirements and technical decisions' names the domain and one concrete action (generate instructions) with its inputs, but does not enumerate several specific actions, matching the '1-2 concrete actions, not comprehensive' anchor rather than the multi-action level 4.

3 / 5

Completeness

It states a clear 'what' but the only 'when' guidance is the negative exclusion 'Not for ordinary incremental feature changes' with no positive 'Use when...' clause, so per the judging guideline completeness is capped at 3.

3 / 5

Trigger Term Quality

Terms like 'project agent instructions', 'agreed requirements', and 'technical decisions' are relevant but lean technical; common natural user phrasings (e.g. 'set up agents', 'agent rules') and synonyms are missing, fitting the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The niche of generating project agent instructions is fairly distinct, and the explicit negative boundary ('Not for ordinary incremental feature changes') reduces overlap risk, placing it above the 'somewhat specific but could still overlap' anchor at 3.

4 / 5

Total

13

/

20

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.