adding-workspace-apps

How to add an app to an Agent-Native workspace: classifying an "agent" request, scaffolding `apps/<app-name>`, app discovery and descriptions, mounting and base paths, action-first data, and finishing a chat-template app. Use when asked to create, build, scaffold, or generate a new agent or app in a workspace.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

75%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 strong, lean, policy-dense body with concrete commands, exact identifiers, and an explicit post-scaffold verification step with failure handling. Its remaining gaps are a run-on discovery paragraph, no sample action file or template list, and no single end-to-end ordered workflow.

Suggestions

Break the 'Discovery, Links, And The UI Stack' run-on paragraph into a short bulleted rule list (manifest, env vars, links/ports, base path, UI stack) so each rule is scannable.

Add a minimal executable defineAction example and enumerate the available --template values so the scaffold command is fully copy-paste ready.

Add a short ordered checklist at the end (classify -> scaffold -> verify `/<app-name>` on the gateway -> finish/brand) that ties the existing topic sections into one explicit workflow with the verification checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is dense, imperative workspace policy that assumes Claude's competence (pnpm, Drizzle, React Router, shadcn) with every sentence carrying a rule, but the 'Discovery, Links, And The UI Stack' section crams roughly seven distinct rules into one run-on paragraph and a few clauses restate a prior rule ("the active workspace gateway/browser origin owns the port"), so minor trimming could improve it.	4 / 5
Actionability	It gives a copy-paste scaffold command ("pnpm exec agent-native create <app-name> --template=<template>") and exact identifiers (AGENT_NATIVE_WORKSPACE_APPS_JSON, "/_agent-native/actions/:name", appBasePath() in app/entry.client.tsx), but includes no example defineAction file or enumeration of valid template names, leaving minor gaps.	4 / 5
Workflow Clarity	An explicit validation checkpoint with failure recovery exists ("Before saying the app is created, request `/<app-name>` on the running gateway and confirm it returns the new app, not a fallback route", plus guidance for a host running the wrong dev command), but the classify-scaffold-verify-finish flow is spread across topic sections rather than one sequenced workflow with checkpoints.	4 / 5
Progressive Disclosure	A well-sectioned single file with clearly signaled one-level-deep references ("Read `.agents/skills/shadcn-ui/SKILL.md` before adding, updating, or debugging shadcn components" and the Related Skills list), but with no bundle files of its own and ~110 dense inline lines, sections like discovery/vault/database could arguably live in reference files.	4 / 5
	Total	16 / 20 Passed

Description

87%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.

A strong description with an explicit what-and-when structure, concrete niche vocabulary, and good trigger synonyms. Its only weaknesses are a few topic-noun items in the capability list and missing natural trigger verbs like 'add' and 'make'.

Dimension	Reasoning	Score
Specificity	The description enumerates six concrete items ("classifying an 'agent' request, scaffolding `apps/<app-name>`, app discovery and descriptions, mounting and base paths, action-first data, and finishing a chat-template app"), but several are topic nouns rather than actions and database/vault coverage is omitted, matching the 'several specific actions; minor gaps' anchor rather than the comprehensive anchor 5.	4 / 5
Completeness	It explicitly answers both 'what' ("How to add an app to an Agent-Native workspace: classifying... finishing a chat-template app") and 'when' ("Use when asked to create, build, scaffold, or generate a new agent or app in a workspace") with concrete trigger phrases, matching anchor 5 exactly.	5 / 5
Trigger Term Quality	"Use when asked to create, build, scaffold, or generate a new agent or app in a workspace" provides good synonym coverage of the triggering verbs, but natural phrases like 'add' and 'make' are missing, fitting anchor 4 rather than the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	Terms like "Agent-Native workspace", "`apps/<app-name>`", and "chat-template app" establish a clear niche with distinct triggers and minimal risk of firing for an unrelated skill.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: BuilderIO/agent-native
Path: .agents/skills/adding-workspace-apps/SKILL.md
Commit: a941a2e

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.