cron

Schedule reminders and recurring tasks.

Quality

73%

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 ./nanobot/skills/cron/SKILL.md

Quality

Content

92%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 an excellent example of a lean, tool-specific skill: concrete call examples for every mode, a natural-language time-expression table, and a clear boundary rule against the heartbeat alternative. The only real gap is the one-time mode's placeholder ISO datetime with no shown method for computing it. Content quality is high overall.

Suggestions

Show how to compute the `at` value concretely, e.g. a worked example: if it is currently 14:00 and the user says 'in 2 hours', pass at="2026-09-25T16:00:00" (computed from the current session time).

Optionally note how to verify a scheduled job after adding it (e.g. calling cron(action="list") to confirm the job_id and schedule) to close the loop on the add flow.

Dimension	Reasoning	Score
Conciseness	The body is lean and entirely tool-specific — mode definitions, concrete parameter examples, a natural-language-to-parameters table, and the HEARTBEAT boundary rule — with no padding or explanation of concepts Claude already knows. Every token earns its place.	5 / 5
Actionability	Five concrete cron(...) call examples plus a parameter-mapping table make the guidance mostly executable, but `at="<ISO datetime>"` is a placeholder and 'compute ISO datetime from current time' gives no concrete method. This is 'Mostly executable guidance with minor gaps', not the copy-paste-ready bar of 5.	4 / 5
Workflow Clarity	This is a simple single-purpose skill whose core action is unambiguous: the three modes are enumerated with examples, and an explicit decision rule ('Do not use `cron` for periodic background checks that should stay quiet... update HEARTBEAT.md') cleanly separates this path from the heartbeat path. No destructive or batch operations are involved, so no validation checkpoints are required.	5 / 5
Progressive Disclosure	The skill is short and self-contained with well-organized sections (Modes / Examples / Time Expressions / Timezone); no bundle files exist or are needed, and there are no nested or buried references. Per the simple-skill exception this earns a 5.	5 / 5
	Total	19 / 20 Passed

Description

53%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 concise and names a distinct niche, but it only covers two of the tool's several capabilities and completely lacks a 'when to use' trigger clause. It reads as a minimal, serviceable description rather than a strong one. Adding explicit trigger guidance would raise it most.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when the user asks to be reminded of something, wants a check to run on a schedule (e.g. every 20 minutes), or asks for recurring or one-time scheduled tasks.'

Enumerate more concrete capabilities in the description: one-time scheduled reminders, timezone-aware schedules, and listing/removing existing jobs — not just 'reminders and recurring tasks'.

Include natural trigger variations users would actually say, such as 'remind me', 'every day at 8am', and 'recurring', to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Schedule reminders and recurring tasks" names the domain and exactly two concrete actions, but omits other capabilities (listing/removing jobs, one-time scheduling, timezone support). This matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' rather than 4, which requires several listed actions.	3 / 5
Completeness	The "what" is clear (schedule reminders and recurring tasks) but there is no "Use when..." clause or equivalent trigger guidance anywhere. Per the rubric guidelines a missing 'Use when' clause caps completeness at 3, which this matches exactly.	3 / 5
Trigger Term Quality	Terms like "reminders" and "recurring tasks" are natural phrases users would say, but common variations such as "remind me", "every day at", or "schedule a check" are missing. It sits at 'Some relevant keywords but missing common variations or synonyms', above 2 because the present terms are genuinely natural rather than generic.	3 / 5
Distinctiveness Conflict Risk	Scheduling is a distinct niche with clear, specific triggers, carrying only minor overlap risk with closely related skills (e.g., general task-planning or heartbeat/notification tooling). Matches 'Mostly distinct; minor overlap risk' — not 5 because the description gives no distinguishing trigger phrases.	4 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: HKUDS/nanobot
Path: nanobot/skills/cron/SKILL.md
Commit: 6eccc28

Reviewed: 6 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.