composable-mini-apps

Build many focused workspace apps that compose through agent discovery and A2A. Use when designing headless mini-apps or cross-app workflows.

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/composable-mini-apps/SKILL.md

Quality

Content

85%

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 well-structured, highly actionable design guide that assumes Claude's competence and avoids explaining general concepts, with concrete tooling, an artifact schema, and a worked multi-app example. Its only real weakness is mild verbosity in the Discovery section, where several dense bullets could be tightened without losing clarity.

Suggestions

Tighten the Discovery And Invocation section by merging the overlapping credential/delegation guidance and trimming the longest bullets, which would move conciseness toward the score-3 lean anchor.

Consider extracting the artifact-handoff field schema into a short reference file and linking to it one level deep, keeping the overview shorter while preserving progressive disclosure at 3.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes platform knowledge Claude lacks (discoverAgents, agent-card.json), but the Discovery And Invocation section runs to seven dense bullets with some repetition of the Shape/Don't themes, so it could be tightened rather than scoring the lean score-3 anchor.	2 / 3
Actionability	It names concrete tools and calls (describe-workspace-apps, invokeAgent(), call-agent, invokeAgentAction(), provider-api-request, stageAs, the GET /_agent-native/agents endpoint) plus a worked example table and an artifact schema, giving copy-ready actionable guidance per the score-3 anchor even though it is instruction-only.	3 / 3
Workflow Clarity	The discover -> describe-capability -> invoke -> hand-off-artifact sequence is explicit, with a concrete deal-brief -> hubspot -> gong -> knowledge-base flow example; no destructive/batch operation is involved so absent validation checkpoints do not cap the score, matching the score-3 clear-sequence anchor.	3 / 3
Progressive Disclosure	No bundle files exist, so this evaluates the body's organization: clear sectioned overview (Rule, Shape, Discovery, Artifact Handoff, Provider APIs, Example, Don't, Related Skills) with one-level-deep Related Skills links and no nested references, meeting the score-3 well-organized anchor for a self-contained design skill.	3 / 3
	Total	11 / 12 Passed

Description

75%

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 concise, third-person, and clearly answers both what the skill does and when to use it with an explicit trigger clause. Its main weakness is specificity and trigger coverage: it names one primary action and leans on jargon (A2A, agent discovery) rather than enumerating concrete actions or natural keyword variations.

Suggestions

Add one or two more concrete actions to the description (e.g., 'split a workspace into one-job apps, wire them together via A2A, delegate provider calls') to lift specificity from 2 to 3.

Soften jargon in the trigger clause by adding natural phrasings a user would actually say (e.g., 'building small single-purpose apps', 'connecting apps together') alongside 'headless mini-apps' and 'cross-app workflows'.

Dimension	Reasoning	Score
Specificity	Quotes "Build many focused workspace apps that compose through agent discovery and A2A" name the domain and the composition mechanism, but only one primary action rather than a list of concrete actions as in the score-3 anchor (extract/fill/merge); it is above the vague score-1 anchor.	2 / 3
Completeness	It states both what ("Build many focused workspace apps that compose through agent discovery and A2A") and an explicit when ("Use when designing headless mini-apps or cross-app workflows"), satisfying the score-3 anchor with an explicit trigger clause; not capped at 2 because the Use-when clause is present.	3 / 3
Trigger Term Quality	Triggers "designing headless mini-apps or cross-app workflows" include some natural terms, but "agent discovery" and "A2A" are jargon and common user variations are missing, matching the score-2 anchor rather than the full coverage of score 3.	2 / 3
Distinctiveness Conflict Risk	The composable-mini-apps architectural niche with triggers like "headless mini-apps" and "cross-app workflows" is distinct from sibling mechanics skills, matching the score-3 clear-niche anchor; it would not score lower since it is unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 12 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/composable-mini-apps/SKILL.md
Commit: c1ee18b

Reviewed: 4 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.