CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cron-scheduler

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

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/cron-scheduler/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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 exceptional actionability and a well-sequenced, validated workflow with a thorough error-recovery catalog. Its weaknesses are repetition of the wrapper guidance across four sections and a monolithic structure with no bundle files, where two of the deep-dive sections belong in separate references.

Suggestions

Move the managed-brain recipe and the multi-source consolidation details into a reference file (e.g. references/managed-brain.md) and keep a one-line pointer plus the decision rule in SKILL.md.

State the GBRAIN_HOME/wrapper rule once (in the Contract or Phase 6) and have the other sections reference it instead of restating it.

Collect version-dependent notes (v0.11.0 auto-rewrite, v0.40.3.0+ per-source locks) into a short "Version notes" or deprecated-patterns section so they don't bloat the main flow.

DimensionReasoningScore

Conciseness

Mostly dense, non-obvious operational knowledge, but the wrapper/GBRAIN_HOME point is restated in the Contract, Phase 6, "When it fails", and Anti-Patterns sections, and inline version pins ("v0.11.0", "v0.40.3.0+") are not isolated in a deprecated section, which the guidelines penalize. Repetition exceeds the "minor instances" of anchor 4.

3 / 5

Actionability

Fully executable throughout: copy-paste-ready cron lines for both classic and managed brains, exact diagnostic commands ("gbrain doctor --only cron_gbrain_home", "gbrain sources writer status --json"), and concrete error codes each paired with a specific remediation command.

5 / 5

Workflow Clarity

Six numbered phases with explicit validation checkpoints (collision check against a listed slot set, test-on-3-5-items-first convention, idempotency requirement), and the "When it fails" section provides feedback loops for every failure mode, including batch/destructive cron operations.

5 / 5

Progressive Disclosure

The bundle contains no reference or script files; the entire ~160-line body is inline, and long sections (managed-brain recipe, multi-source consolidation, failure catalog) are candidates for one-level-deep reference files. External paths ("skills/conventions/...", "../conventions/...") are clearly signaled but unverifiable within the bundle — matching anchor 3 rather than 4.

3 / 5

Total

16

/

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 uses concrete third-person verbs and a distinctive feature set, but it lacks any 'use when' trigger guidance and misses the most natural keyword ("cron") that users would say. Adding an explicit trigger clause with natural terms would lift both completeness and trigger quality.

Suggestions

Append a trigger clause such as "Use when the user asks to schedule a job, set up cron entries, or asks what jobs are running" to satisfy the missing 'when' half.

Include the natural terms users actually say — "cron", "recurring", "scheduled jobs" — in the description body, not just the triggers list.

Replace internal jargon like "gates delivery" and "staggering" with plainer equivalents ("holds notifications during quiet hours", "spaces jobs 5 minutes apart").

DimensionReasoningScore

Specificity

"Validates schedules, prevents collisions, and gates delivery during quiet hours" plus "staggering" and "wake-up override" name several concrete third-person actions. Not a 5 because coverage omits other capabilities the skill performs (registering with host schedulers, wrapper-based invocation).

4 / 5

Completeness

The "what" is clear (validate schedules, prevent collisions, gate delivery during quiet hours), but there is no "Use when..." clause or equivalent explicit trigger guidance in the description, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

"Schedule" and "quiet hours" are natural user phrases, but the most common term a user would say — "cron" — plus synonyms like "recurring" or "scheduled jobs" are absent from the description, while "gates delivery" and "staggering" are internal jargon. Matches anchor 3 (relevant keywords, missing common variations) rather than 4.

3 / 5

Distinctiveness Conflict Risk

"Quiet hours", "staggering", and "wake-up override" carve a specific niche unlikely to fire for unrelated skills. Not a 5 because "Schedule management" as the opening phrase still overlaps generic task-scheduling skills.

4 / 5

Total

14

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository

garrytan/gbrain

Path

skills/cron-scheduler/SKILL.md

Reviewed

Table of Contents

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.