cron-scheduler

Schedule management with staggering, quiet hours, and wake-up override. Validates schedules, prevents collisions, and gates delivery during quiet hours.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/cron-scheduler/SKILL.md

Quality

Content

67%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 delivers a clearly sequenced, validated workflow with genuinely concrete details (slots, cron line, report format, idempotency rules). Its main weaknesses are the verbose, version-pinned multi-source section inlined into the main body and a registration phase that stops short of executable commands.

Suggestions

Move the multi-source gbrain deep-dive into a reference file and keep only the preferred cron line plus a one-line pointer in SKILL.md; relegate version-specific migration notes (v0.11.0, v0.40.3.0+) to that file's deprecated/old-patterns section.

Add a concrete registration example for at least one host (e.g. the exact crontab entry or OpenClaw registration command) and a verification step confirming the job fired once.

Add a short release-the-held-queue step to Phase 3 or the Output Format so the morning backlog handling is actionable rather than descriptive.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean imperative prose (slot lists, default hours, a one-line cron example), but the ~25-line "Multi-source brains" section over-explains legacy lock races, embeds version pins ("GBrain's v0.11.0 migration", "v0.40.3.0+ uses per-source locks") in active guidance rather than a deprecated section, and the Anti-Patterns list repeats that section's content. More than minor tightening is needed, so it sits below the 4 anchor.	3 / 5
Actionability	Mostly executable guidance: the concrete slot list (":05, :10, :15, :20, :25, :30, :35, :40, :45, :50"), default quiet hours ("11 PM - 8 AM local time"), a copy-paste cron line ("/5 * * * gbrain sync --all --parallel 4 --workers 4 --skip-failed"), the exact report string, and the thin-prompt template. Phase 4's registration step only names hosts ("OpenClaw cron, Railway cron, crontab, or process manager") without an executable registration command — a minor gap that keeps it below 5 but well above the pseudocode-level 3 anchor.	4 / 5
Workflow Clarity	Phases 1-5 are clearly sequenced with a real feedback loop ("If collision detected, suggest the next available slot"), idempotency checkpoints ("Check for existing output before creating new output"), and test-before-bulk validation, so the batch-operation cap at 3 does not apply. It falls short of 5 because no step verifies the registration succeeded or specifies how the held queue is released beyond a brief mention.	4 / 5
Progressive Disclosure	Sections are well organized and external references ("skills/conventions/cron-via-minions.md", "docs/guides/plugin-handlers.md", "skills/conventions/test-before-bulk.md") are one level deep and clearly signaled. The skill exceeds 50 lines and inlines the dense host-specific gbrain deep-dive that belongs in a separate reference file, which keeps it below the 5 anchor.	4 / 5
	Total	15 / 20 Passed

Description

58%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 is specific and third-person, with a clear statement of what the skill does, but it omits any "use when" trigger guidance and buries its most natural keywords (cron, schedule a job) in the separate triggers field rather than the description text. Adding a "Use when the user asks to schedule a cron job, stagger recurring tasks, or respect quiet hours" clause would raise both completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause to the description, e.g. "Use when scheduling cron/recurring jobs, staggering schedules, or when the user mentions quiet hours."

Move the natural keywords currently only in the triggers list ("cron", "schedule a job") into the description text itself so trigger matching works from the description alone.

Name the concrete artifacts the skill produces (e.g. reports saved under reports/{job-name}/) to sharpen the what and reduce overlap with generic reminder/scheduling skills.

Dimension	Reasoning	Score
Specificity	The description lists several concrete third-person actions — "Validates schedules, prevents collisions, and gates delivery during quiet hours" plus "staggering" and "wake-up override" — but coverage has minor gaps (no mention of job registration, report output, or what kinds of jobs). It exceeds the 3 anchor (only 1-2 actions) but is not comprehensive enough for 5.	4 / 5
Completeness	The "what" is clear (schedule management, validation, collision prevention, quiet-hours gating), but the description contains no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. The 4 anchor requires both what and when.	3 / 5
Trigger Term Quality	"quiet hours" is a phrase a user would naturally say, but the description's other keywords ("staggering", "wake-up override", "gates delivery") are internal vocabulary rather than natural user terms; the core trigger words "cron" and "schedule a job" appear only in the separate triggers field, not in the description. Missing common variations keeps this below 4.	3 / 5
Distinctiveness Conflict Risk	"quiet hours", "wake-up override", and "staggering" carve a distinct scheduling-niche identity with low conflict risk against unrelated skills. Minor overlap remains with generic task-scheduling or reminder skills since the description never names cron or recurring jobs, keeping it below 5.	4 / 5
	Total	14 / 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: garrytan/gbrain
Path: skills/cron-scheduler/SKILL.md
Commit: e78f1c3

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.