cron-scheduler

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

Quality

71%

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 is well-structured and largely actionable with concrete cron commands, paths, and a clear phased workflow plus explicit validation. Its main weakness is conciseness: the multi-source section carries dense, version-specific detail inline rather than in a reference or deprecation note.

Suggestions

Move the version-specific lock/migration details (v0.40.3.0+, v0.11.0) and the legacy per-source pattern into a short 'Deprecated patterns' note or a reference file so the main flow stays lean and time-stable.

Add a concrete example command for at least one host scheduler in phase 4, or link to a per-host reference, so 'Register with host scheduler' is executable rather than a list of options.

Promote the 'test on 3-5 items first' convention into an explicit numbered validation checkpoint (e.g., phase 5.5) with a verify-and-fix loop after the first scheduled run.

Dimension	Reasoning	Score
Conciseness	The Phases, Contract, and Idempotency sections are lean and operational, but the "Multi-source brains" section is dense and embeds time-sensitive version numbers ("v0.40.3.0+", "v0.11.0") inline outside any deprecated/old-patterns section, which the guidelines penalize.	3 / 5
Actionability	Copy-paste-ready specifics like "gbrain sync --all --parallel 4 --workers 4 --skip-failed" and "reports/{job-name}/{YYYY-MM-DD-HHMM}.md" are strong, but the "Register with host scheduler" step lists four options (OpenClaw, Railway, crontab, process manager) without a concrete command for each.	4 / 5
Workflow Clarity	Five numbered phases are clearly sequenced with an explicit collision-validation checkpoint in phase 2 and an idempotency requirement, but a post-registration verification feedback loop (confirm the job actually ran and produced correct output) is only implied via the testing convention rather than a numbered checkpoint.	4 / 5
Progressive Disclosure	The body is well-organized into labeled sections and signals one-level-deep references inline ("See `skills/conventions/cron-via-minions.md`"), but no bundle files ship with the skill and the detailed multi-source section could plausibly live in its own reference file.	4 / 5
	Total	15 / 20 Passed

Description

75%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 names a clear niche with multiple concrete actions and supplies natural trigger terms via the frontmatter trigger list. It is strong but not maximal because the lead phrasing is mildly generic and the "when" guidance lives in the trigger list rather than integrated prose.

Dimension	Reasoning	Score
Specificity	Quotes "staggering, quiet hours, and wake-up override", "Validates schedules, prevents collisions, and gates delivery" list several concrete actions, though the lead phrase "Schedule management" is slightly generic and registration (covered in the body) is absent.	4 / 5
Completeness	The "what" is clear and concrete, and the explicit trigger list supplies the "when" as equivalent trigger guidance; the "when" is not woven into the description prose itself, so it stops just short of a fully integrated "Use when..." clause.	4 / 5
Trigger Term Quality	Triggers "schedule a job", "cron", "quiet hours", "what jobs are running" are natural phrases a user would say, but common synonyms like "recurring task" or "automate" are missing.	4 / 5
Distinctiveness Conflict Risk	The quiet-hours/staggering niche and triggers like "cron" and "quiet hours" are mostly distinct, with only minor overlap risk against general task-scheduling skills.	4 / 5
	Total	16 / 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: 7b7921d

Reviewed: ~12 hours 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.