CtrlK
BlogDocsLog inGet started
Tessl Logo

vibe-build

Implement a new-project slice through the relevant checks and working user journey.

44

Quality

45%

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-build/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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 concise, well-sequenced process description that assumes competence and avoids padding, but it stays at a high altitude with no concrete commands, examples, or explicit validation gates. Its main weakness is actionability, followed by implicit rather than gated validation checkpoints.

Suggestions

Add at least one concrete, copy-paste-ready example per phase (e.g. a sample acceptance-criteria checklist, a recovery-checkpoint git command, or a user-journey verification snippet) to lift actionability.

Make the validation loop explicit with a gated step such as 'Run the affected checks; only proceed when they pass; otherwise fix and re-run', so the verify→fix→retry checkpoint is unambiguous.

Break the four paragraphs into labeled H2 sections (Scope, Implement, Verify, Report) to give the short body clearer navigation and structure.

DimensionReasoningScore

Conciseness

The body is lean, assumes Claude's competence, and avoids explaining basic concepts; only minor phrases (e.g. the 'accounts, databases, infrastructure, paid services, and AI' enumeration) could be tightened, so it sits just below the every-token-earns-its-place score-5 anchor.

4 / 5

Actionability

It instructs at a high altitude ('Establish the requested outcome...', 'Implement the intended behavior using the chosen stack') with useful guardrails, but provides no concrete commands, examples, or specific executable steps, fitting the score-2 anchor of high-level hints missing the specific steps to execute.

2 / 5

Workflow Clarity

A clear four-phase sequence (scope → implement → verify → report) is present, but validation checkpoints are implicit ('Use the project's affected checks', 'Fix failures') rather than explicit validate-then-proceed gates, so it matches the score-3 anchor with validation gaps.

3 / 5

Progressive Disclosure

The skill is under 50 lines and needs no external reference files, and the four paragraphs are logically sequenced; the only organization gap is the absence of section headers, placing it just below the well-organized-sections score-5 anchor.

4 / 5

Total

13

/

20

Passed

Description

37%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 conveys a clear 'what' but relies on jargon, omits any 'when to use it' trigger guidance, and uses generic language that raises overlap risk with other build skills. It sits at the lower-middle of the scale, primarily limited by missing trigger terms and an absent Use-when clause.

Suggestions

Add an explicit 'Use when...' clause naming natural user phrases, e.g. 'Use when starting a new project, scaffolding a feature slice, or building a working vertical of a greenfield app.'

Replace jargon ('new-project slice', 'relevant checks') with concrete, user-recognizable terms (e.g. 'build a working end-to-end slice of a new project, run its tests, and verify the user journey').

List one or two more concrete actions to lift specificity above a single generic verb.

DimensionReasoningScore

Specificity

The phrase 'Implement a new-project slice' names the domain and one action, but 'through the relevant checks and working user journey' is minimal/generic elaboration rather than a second concrete action, matching the score-2 anchor better than the two-action score-3 anchor.

2 / 5

Completeness

It states clearly what the skill does ('Implement a new-project slice...') but provides no 'Use when...' clause or equivalent trigger guidance, so completeness is capped at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Terms like 'new-project slice', 'relevant checks', and 'working user journey' are internal jargon rather than natural phrases a user would say, leaving only a couple of generic keywords with the natural trigger phrases missing.

2 / 5

Distinctiveness Conflict Risk

'new-project slice' carves a niche that is more specific than 'helps with document files', but the generic triggers and absence of distinct activation phrases mean it could still overlap with general build/implement skills.

3 / 5

Total

10

/

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.

Validation — 15 / 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.