CtrlK
BlogDocsLog inGet started
Tessl Logo

new-app

Workflow for creating new applications from scratch. Covers requirements gathering, tech stack selection, scaffolding, implementation, and delivery of a functional prototype.

57

Quality

64%

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 ./packages/core/src/skills/bundled/new-app/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-sequenced, checkpointed workflow with named tools and concrete stack guidance, but it is somewhat verbose and its actionability, while solid, stops short of complete executable examples.

Suggestions

Trim repeated visual-quality phrasing ('beautiful, modern, and polished', 'visually coherent and functional') to single statements to reduce token cost without losing intent.

Add one short concrete scaffold/build example per major stack (e.g., a ready-to-run Next.js init+dev command block) to move actionability from named-tools toward copy-paste ready.

Replace abstract directives like 'implement each task' and 'Fix bugs, deviations' with a brief, specific verify-rebuild loop ('run build; if errors, fix and rebuild until clean') to make the existing feedback loop explicit.

DimensionReasoningScore

Conciseness

The body is mostly directive and useful, but steps like the plan-presentation and placeholder-asset guidance are padded with repeated phrasing ('beautiful, modern, and polished', 'visually coherent and functional') and some over-explanation that could be tightened.

2 / 3

Actionability

It names concrete tools ('write_file', 'edit', 'run_shell_command', 'todo_write') and specific scaffold commands ('npm init', 'npx create-react-app') plus per-app-type stacks, but much guidance stays abstract ('implement each task', 'Fix bugs, deviations') with no complete executable examples.

2 / 3

Workflow Clarity

A clear six-step sequence (Understand, Propose, Approval, Implement, Verify, Feedback) with explicit checkpoints — user approval at step 3 and a Verify step that builds to catch compile errors with implied fix-and-rebuild — matches the anchor for a well-sequenced workflow with validation.

3 / 3

Progressive Disclosure

The skill is a self-contained workflow under 50 lines with no external references needed, organized as a Goal header plus numbered steps, which per the rubric's simple-skills note earns a 3 for well-organized sections without bundle files.

3 / 3

Total

10

/

12

Passed

Description

60%

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 and lists concrete workflow stages, but it carries only the 'what' — the 'when to use' trigger and the breadth of natural app-type keywords live in a separate when_to_use field rather than the description itself.

Suggestions

Fold a concise 'Use when...' trigger into the description (e.g., 'Use when creating a new application, website, game, mobile app, CLI tool, or library from scratch') so both what and when live in one field.

Include the natural app-type terms (website, game, mobile app, CLI tool, library) directly in the description to improve trigger-term coverage and distinctiveness.

Tighten 'Covers requirements gathering, tech stack selection, scaffolding, implementation, and delivery of a functional prototype' to the most distinguishing actions to reduce overlap with generic build/coding skills.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — 'requirements gathering, tech stack selection, scaffolding, implementation, and delivery of a functional prototype' — matching the anchor that lists several specific concrete actions.

3 / 3

Completeness

It clearly answers 'what' (the workflow and its stages) but the description field contains no 'Use when...' trigger; the when guidance lives in the separate when_to_use field, so per the guideline a missing trigger clause caps completeness at 2.

2 / 3

Trigger Term Quality

'creating new applications from scratch' is a natural phrase a user might say, but the description itself lacks the common variations (website, game, mobile app, CLI, library) that appear only in the separate when_to_use field, so coverage is partial.

2 / 3

Distinctiveness Conflict Risk

'creating new applications from scratch' plus 'delivery of a functional prototype' defines a niche, but the phrase is broad enough to overlap with general coding/build skills and, without the enumerated triggers, is only somewhat specific.

2 / 3

Total

9

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
QwenLM/qwen-code
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.