CtrlK
BlogDocsLog inGet started
Tessl Logo

cron

Schedule reminders and recurring tasks.

56

Quality

63%

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 ./nanobot/skills/cron/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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, concise, and provides concrete executable examples covering the common scheduling cases, with only the lack of a validation step around the destructive remove operation holding workflow clarity back.

Suggestions

Add an explicit validation step before removal, e.g. run `cron(action="list")` first and confirm the job_id matches the intended job before calling `action="remove"`.

Make the one-time example fully concrete by showing how to compute the ISO datetime, or note that `at` accepts a computed absolute timestamp.

Clarify what "agent executes and sends result" means for the Task mode so the dynamic-task flow is unambiguous.

DimensionReasoningScore

Conciseness

The body is lean with no background explanations of what cron is, and the boundary guidance earns its tokens; a few sentences (e.g. the long intro line, the per-mode glosses) could be trimmed slightly, fitting the efficient-with-minor-over-explanation anchor.

4 / 5

Actionability

Concrete `cron(action=...)` calls cover add/list/remove/one-time/timezone cases and the Time Expressions table maps natural phrases to parameters; the `<ISO datetime>` placeholder and the unexplained dynamic-task execution leave minor gaps short of fully copy-paste-ready 5.

4 / 5

Workflow Clarity

This is a simple single-tool skill, but `cron(action="remove")` is a destructive operation shown without an explicit validation step (e.g. list-then-confirm the job_id), so the destructive-operations cap holds workflow clarity at 3.

3 / 5

Progressive Disclosure

The skill is a single self-contained file with well-organized sections (Modes, Examples, Time Expressions, Timezone) and no nested references; the only external mention (HEARTBEAT.md) is boundary disambiguation, not a navigation pointer, satisfying the simple-skill exception.

5 / 5

Total

16

/

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 clear niche with natural trigger terms, but it omits an explicit "Use when..." clause, which caps completeness and limits the overall score to the middle of the scale.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to schedule reminders, recurring tasks, or time-based notifications."

Include a few natural synonyms such as "remind me" or "automate" to broaden trigger-term coverage.

Mention one-time/scheduled reminders in the description to better reflect the skill's full capability set.

DimensionReasoningScore

Specificity

"Schedule reminders and recurring tasks" names the scheduling domain and two concrete action types (reminders, recurring tasks), matching the anchor for 1-2 concrete actions without being comprehensive enough for a 4.

3 / 5

Completeness

It gives a clear "what" (schedule reminders and recurring tasks) but has no "Use when..." trigger clause, so per the rubric cap completeness stays at 3.

3 / 5

Trigger Term Quality

"schedule", "reminders", and "recurring tasks" are natural user phrases, but common variations like "remind me", "automate", or "notifications" are missing, fitting the anchor with relevant-but-incomplete keyword coverage.

3 / 5

Distinctiveness Conflict Risk

The scheduling/reminders niche is mostly distinct with only minor overlap risk against general todo/task-management skills, aligning with the mostly-distinct anchor.

4 / 5

Total

13

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
HKUDS/nanobot
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.