recurring-jobs

Scheduled tasks the agent runs on a cron schedule. Use when a user asks for something recurring ("every morning", "daily", "weekly"), when creating or updating jobs, or when debugging the job scheduler.

Quality

86%

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

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is well-structured, concise, and rich in app-specific pointers, but it lacks a concrete worked example and explicit validation checkpoints for a workflow that can run destructive recurring operations. Adding a sample job file and a verify-before-enable step would lift the two level-2 dimensions.

Suggestions

Add a minimal worked example of job creation — a sample `jobs/<name>.md` file with its YAML frontmatter and a sample `manage-jobs` create invocation — to make the guidance copy-paste ready.

Insert an explicit validation/verification checkpoint into the job creation flow (e.g., confirm the parsed cron with `describeCron`/`isValidCron` and verify MCP tool bindings resolve before enabling the job).

Consider extracting the dense "Connected MCPs in background jobs" section into a `references/mcp-jobs.md` file referenced one level deep, which would keep SKILL.md a tighter overview while preserving the advanced detail.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence — no explanation of what cron or MCPs are, and every sentence in the dense MCP section carries app-specific security/architecture guidance that earns its place, matching the level-3 lean anchor rather than level-2 unnecessary-explanation padding.	3 / 3
Actionability	Concrete pointers exist (the `manage-jobs` tool table with create/list/update, Key Files paths, `/agent#jobs` surface), but there is no worked example — no sample job file YAML or sample tool invocation — so guidance is specific yet incomplete per the level-2 anchor rather than copy-paste-ready level-3.	2 / 3
Workflow Clarity	The 4-step "How It Works" sequence is clear, but the create/update flow has no validation checkpoint and jobs can run destructive/batch agent loops, so per the rubric's batch-operation cap it stays at level-2 (steps present, checkpoints implicit) rather than level-3.	2 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), and the body is self-contained with well-organized sections (Rule, How It Works, MCPs, Job Tool, UI Surface, Key Files, Related Skills), so per the simple-skills note well-organized sections score 3 without external references.	3 / 3
	Total	10 / 12 Passed

Description

100%

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 answers both what the skill does and when to use it with natural trigger terms. It is a strong, low-conflict description that would correctly activate on the intended requests.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the domain — "creating or updating jobs", "debugging the job scheduler" — anchored to "Scheduled tasks the agent runs on a cron schedule", matching the level-3 anchor of multiple specific actions rather than the level-2 single-domain example.	3 / 3
Completeness	Explicitly states both what ("Scheduled tasks the agent runs on a cron schedule") and when ("Use when a user asks for something recurring...") with explicit trigger guidance, matching the level-3 what-and-when anchor and avoiding the level-2 cap for a missing 'Use when' clause.	3 / 3
Trigger Term Quality	Covers natural phrasing a user would actually say — "every morning", "daily", "weekly", "recurring" — alongside task verbs, matching level-3 broad coverage; not reduced to 2 because common variations are well represented.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (cron-scheduled recurring jobs) with distinct triggers unlikely to fire for unrelated skills, matching the level-3 clear-niche anchor rather than the overlapping level-2 case.	3 / 3
	Total	12 / 12 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/recurring-jobs/SKILL.md
Commit: c1ee18b

Reviewed: 5 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.