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

72%

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

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.

The body is a tight, well-organized instruction set that gives Claude concrete tools, a clear discovery-to-invocation flow, and a worked example, with only minor conciseness trims and missing explicit validation feedback loops keeping it off the top band. It assumes the model's competence rather than re-teaching known concepts.

Suggestions

For the batch/destructive-adjacent operations (e.g. provider-api-request joins, staged-dataset reductions), add an explicit validate-or-verify checkpoint to lift workflow_clarity toward 5.

Consider extracting the detailed artifact-field spec or the provider-API call sequence into a one-level-deep reference file so the overview stays lean and progressive_disclosure can reach the 5-anchor.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence — it skips generic explanations of what A2A or providers are and gives actionable rules, with only minor spots that could be trimmed (e.g. the 'A stale catalog is worse than none' rationale).	4 / 5
Actionability	It names concrete tooling and APIs (discoverAgents(), describe-workspace-apps, invokeAgent(), call-agent, provider-api-request, stageAs) and gives a worked sales-intelligence example with an app/calls table, which is mostly executable guidance with only minor gaps in exact call signatures.	4 / 5
Workflow Clarity	Discovery and invocation are sequenced as a clear decision flow (discover → describe-workspace-apps → invokeAgent/call-agent → narrow artifact handoff) and the Example section walks a full HubSpot→Gong→knowledge-base chain with mostly explicit checkpoints, though explicit validate/retry feedback loops are not stated.	4 / 5
Progressive Disclosure	The body is a lean overview with clear section headers and a Related Skills list pointing one level out to sibling skills; with no references/scripts/assets bundle present this structure is appropriate, just shy of the 5-anchor that would require well-signaled separate reference files.	4 / 5
	Total	16 / 20 Passed

Description

70%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 cleanly states both what the skill does and when to use it in third person, with a clear and fairly distinct niche. It is held back from the top band mainly by the specificity of its action list and the narrowness of its trigger-term coverage.

Suggestions

Add 1-2 concrete actions the skill performs (e.g. 'split a workspace into focused one-job apps', 'compose siblings through discovery and A2A') to lift specificity toward the 5-anchor.

Broaden the 'Use when...' clause with a few natural trigger variations and synonyms (e.g. 'Use when breaking a large app into smaller focused apps, designing agent-discoverable apps, or composing cross-app workflows') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The 'what' is concrete but kept high-level — "designing headless mini-apps or cross-app workflows" is more a category than a list of concrete actions the skill performs, so it lands on the anchor naming a domain with minimal concrete actions rather than the level listing several specifics.	3 / 5
Completeness	Both 'what' ("Build many focused workspace apps that compose through agent discovery and A2A") and 'when' ("Use when designing headless mini-apps or cross-app workflows") are present and explicit, though the 'when' clause is a single compact case rather than a set of concrete trigger phrases.	4 / 5
Trigger Term Quality	Natural trigger phrases like "designing headless mini-apps" and "cross-app workflows" are present and would plausibly be said by a user, but coverage is narrow with no synonyms or common variations beyond those two.	4 / 5
Distinctiveness Conflict Risk	The niche — composable headless workspace mini-apps discovered via A2A — is distinct from sibling skills listed in the body (a2a-protocol, actions), with only minor overlap risk against those closely related skills.	4 / 5
	Total	15 / 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/composable-mini-apps/SKILL.md
Commit: cc2a915

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.