CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

new-app

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

Quality

75%

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

67%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.

A well-structured, actionable workflow with a clear six-step sequence, explicit approval and build-verification checkpoints, and concrete default technology choices. Its main weaknesses are recurring wordiness — especially the placeholder-asset passages — and an inlined tech-stack table that would sit better as a headered section or separate reference.

Suggestions

Tighten step 4's placeholder guidance to a single sentence covering create-if-possible / label-if-not, removing the repeated restatements.

Promote the technology-preference list to its own headered section (or a references/ file) so it reads as a lookup table rather than a nested bullet.

Make the verify step a closed loop: 'If the build fails, fix errors and rebuild before proceeding' rather than a one-shot check.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows and stays instructional, but phrasing is padded in places — the placeholder guidance in step 4 restates the same idea three ways ('Use placeholders only when essential, intending to replace them with more refined versions or instruct the user on replacement during polishing if generation is not feasible'). This fits 'mostly efficient but could be tightened' rather than the minor-trim level-4 anchor.

3 / 5

Actionability

Guidance is largely concrete: exact scaffold commands ('npm init', 'npx create-react-app') and a specific default stack table (React with Bootstrap, Next.js, Compose Multiplatform, Three.js). Per the scoring notes, absence of code in an instruction-only skill is not penalized when guidance is actionable; it falls short of level 5 only because the verify/deliver steps remain directional.

4 / 5

Workflow Clarity

Six numbered steps are clearly sequenced with an explicit user-approval gate (step 3) and a validation checkpoint that builds and checks for compile errors (step 5, 'MOST importantly, build the application and ensure there are no compile errors'). It lacks the explicit error-recovery loop ('if errors: fix and re-validate') of the level-5 anchor, and the batch/destructive cap does not apply since this is not a destructive or batch operation.

4 / 5

Progressive Disclosure

The skill is self-contained (no references/, scripts/, or assets/ bundle exists and nothing points to one), so there are no broken or nested references. Structure is a clear numbered workflow, but the tech-stack preference list is reference-like content inlined in a sub-bullet without section headers or signaling, keeping it just below the well-organized-sections bar for a 5.

4 / 5

Total

15

/

20

Passed

Description

71%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 is specific and well-scoped, enumerating the full workflow phases concretely and staking out a distinct greenfield niche. Its main weakness is the absence of any 'Use when...' trigger clause within the description field itself (the frontmatter's separate when_to_use field is not part of the evaluated text), which caps completeness and slightly weakens trigger-term coverage.

Suggestions

Append a trigger clause to the description, e.g. 'Use when the user asks to create a new application, website, game, mobile app, CLI tool, or library from scratch', to satisfy completeness and mirror the natural terms already in when_to_use.

Add natural synonyms such as 'build' and 'new project' alongside 'creating' to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

The description lists five concrete workflow phases ('requirements gathering, tech stack selection, scaffolding, implementation, and delivery of a functional prototype'), giving comprehensive coverage. It clearly matches the anchor for multiple specific concrete actions rather than the level-4 anchor, which requires minor coverage gaps.

5 / 5

Completeness

It answers 'what' clearly (a workflow with five named phases) but the description field contains no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It does not reach level 4, which requires an explicit 'when' clause even if imperfect.

3 / 5

Trigger Term Quality

Natural phrases like 'creating new applications from scratch' and 'prototype' are present, but common user variations ('build', 'new project', 'app') and platform terms (website, game, CLI) are missing from the description field. Good keyword coverage with a few natural terms missing fits the level-4 anchor; it lacks the synonym/file-extension comprehensiveness of level 5.

4 / 5

Distinctiveness Conflict Risk

'Creating new applications from scratch' carves a distinct greenfield niche unlikely to trigger for modification, review, or analysis skills. Minor overlap remains with scaffolding/boilerplate tools, placing it between the mostly-distinct level-4 anchor and the minimal-conflict level-5 anchor.

4 / 5

Total

16

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

QwenLM/qwen-code

Path

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

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.