CtrlK
BlogDocsLog inGet started
Tessl Logo

app-builder

Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.

56

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/app-builder/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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 token-efficient, well-organized overview that correctly uses progressive disclosure on paper, but it provides only directional rather than executable guidance, lacks validation checkpoints in its multi-agent workflow, and references bundle files that do not exist.

Suggestions

Add an explicit validation/checkpoint step to the workflow (e.g. verify the scaffold compiles or the agent outputs match the plan before reporting progress).

Provide at least one concrete executable snippet or command rather than relying solely on an illustrative Instagram-clone example.

Either include the referenced bundle files (references/*.md and templates/*/TEMPLATE.md) or remove the dangling references so progressive disclosure points to real materials.

DimensionReasoningScore

Conciseness

The body is lean and table-driven with no concept explanations Claude already knows; every line (reference map, template table, agent table, usage example) earns its place.

3 / 3

Actionability

Guidance is directional ('Read the matching template only!') with an illustrative rather than executable usage example, and no concrete commands or scripts are given; it describes a process rather than providing copy-paste-ready steps.

2 / 3

Workflow Clarity

The usage example shows a numbered sequence (project type, tech stack, plan, coordinate agents, report, preview) but there is no explicit validation/verification checkpoint, and coordinating agents and scaffolding are batch operations, which per the rubric caps workflow clarity at 2.

2 / 3

Progressive Disclosure

The body is well structured as a one-level-deep overview pointing to reference files and templates, but no bundle files actually exist — references like project-detection.md and templates/*/TEMPLATE.md are dangling, so the structure is not backed by a real bundle.

2 / 3

Total

9

/

12

Passed

Description

67%

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 distinct, naming concrete orchestrator actions, but keeps its trigger guidance in a separate when_to_use field instead of embedding a 'Use when...' clause directly in the description, which caps its completeness and trigger-term coverage.

Suggestions

Add an explicit 'Use when...' clause directly in the description (e.g. 'Use when creating a new full-stack app from scratch or scaffolding project structure') so the description self-contains both what and when.

Incorporate natural user-voice trigger terms like 'build an app', 'make a web app', or 'scaffold a project' into the description rather than only formal terms like 'natural language requests'.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Creates full-stack applications from natural language requests', 'Determines project type, selects tech stack, coordinates agents' — matching the highest anchor.

3 / 3

Completeness

It clearly answers 'what' but the 'when' trigger guidance lives in a separate when_to_use field rather than within the description itself; per the rubric a missing 'Use when...' clause in the description caps completeness at 2.

2 / 3

Trigger Term Quality

Terms like 'full-stack applications', 'natural language requests', and 'tech stack' are relevant, but the description field itself lacks the most natural user phrasing ('make/build an app', 'scaffold a project'); those appear only in the sibling when_to_use field, so coverage is partial.

2 / 3

Distinctiveness Conflict Risk

The framing as a 'full-stack application building orchestrator' that 'coordinates agents' carves a clear niche that is unlikely to trigger for unrelated skills.

3 / 3

Total

10

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

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

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 13 missing, 13 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository
vudovn/ag-kit
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.