automations

Event-triggered and schedule-triggered automations with natural-language conditions. Use when creating automations, wiring events, or understanding how triggers fire.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

78%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 dense, highly actionable reference: concrete tool actions, complete field tables, executable code, and well-sequenced workflows with confirmation checkpoints. The main weaknesses are inlined reference-grade detail with no separate bundle files, and some repetition between the Markdown Format, How It Works, and Example sections.

Suggestions

Move the Failure Handling details and Event Bus API tables into reference files under references/ (e.g., references/failure-handling.md, references/event-bus.md), keeping SKILL.md a concise overview with clearly signaled one-level-deep links.

Deduplicate the Example section, which repeats the Markdown Format sample body and condition verbatim; point to the format section instead and show only the manage-automations define call.

Add a post-define verification step to the example agent flow (e.g., call fire-test or list to confirm the automation was created with the intended trigger) to close the workflow validation gap.

Dimension	Reasoning	Score
Conciseness	The body is dense and system-specific throughout (e.g., "An MCP allowlist is enforced, not advisory: every named tool must resolve in the creator's request context"), with no filler explaining concepts Claude already knows. Minor over-length comes from repetition: the Example section restates the Markdown Format sample and How It Works steps nearly verbatim. Fits anchor 4 rather than 5 due to that duplication.	4 / 5
Actionability	Fully concrete and executable: an action table with exact parameter values (action=list-events, action=define), a complete frontmatter field table, a complete registerEvent/emit code example, and a full example agent call with named parameters and a ${keys.SLACK_WEBHOOK} body. Covers the common cases copy-paste ready, matching anchor 5.	5 / 5
Workflow Clarity	The 7-step How It Works sequence is clear, with validation checkpoints ("Confirms the plan with the user", delete "always confirm with user first") and a fire-test mechanism plus failure-recovery semantics. Minor gap: the example agent flow ends at define with no post-define verification step, so it fits anchor 4 rather than 5.	4 / 5
Progressive Disclosure	No bundle reference files exist; all reference-grade material (the very long Failure Handling section, the Event Bus API table, key-substitution details) is inlined in a single ~290-line SKILL.md. Structure is good with clear headers, but content that clearly belongs in separate reference files is inline, matching anchor 3.	3 / 5
	Total	16 / 20 Passed

Description

78%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 that clearly and concisely states both the capability domain and explicit use-when triggers in third person. Keyword coverage is good, though a few natural synonyms (cron, scheduled tasks, recurring jobs) are absent and the action list is not comprehensive.

Dimension	Reasoning	Score
Specificity	"Event-triggered and schedule-triggered automations with natural-language conditions" names the domain, and "creating automations, wiring events" gives 1-2 concrete actions, but coverage is not comprehensive (no listing, updating, deleting, or failure handling). It matches anchor 3 rather than 4, which requires several specific actions with only minor gaps.	3 / 5
Completeness	It explicitly answers both: what ("Event-triggered and schedule-triggered automations with natural-language conditions") and when ("Use when creating automations, wiring events, or understanding how triggers fire") with concrete trigger phrases. This matches the anchor 5 example pattern.	5 / 5
Trigger Term Quality	Good natural keyword coverage: "automations", "triggers", "wiring events", "schedule-triggered", "creating automations". A few natural terms users might say are missing ("cron", "recurring jobs", "scheduled tasks"), so it fits anchor 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche (event/schedule triggered automations with conditions) with distinct triggers, but there is minor overlap risk with the closely related recurring-jobs skill surface. Mostly distinct, fitting anchor 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: BuilderIO/agent-native
Path: .agents/skills/automations/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.