CtrlK
BlogDocsLog inGet started
Tessl Logo

scheduling-tasks

Advanced scheduling through the letta cron CLI for other conversations, computers, run history, and schedule replacement. Use Wake for ordinary create/list/cancel operations in the current conversation.

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./src/skills/builtin/scheduling-tasks/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

Highly actionable CLI documentation with excellent worked examples, correct and well-explained timezone conversion, and explicit verification steps for creation and destructive replacement. The main cost is token redundancy: repeated conversation-binding semantics and a cron-syntax primer that re-teaches what Claude already knows.

Suggestions

State the --conversation semantics once in the flags table and cut their repetition in 'Binding a Task to the Right Conversation' and the 'Default binding' bullet in Important Notes.

Drop the cron field-position diagram and the 'Common patterns' list (Claude already knows standard cron); keep only the tool-specific deviations such as numeric-only fields and no `?`/`L`/`#` support.

Add a caution or verification step before 'letta cron delete --all --agent' since it batch-deletes every task for an agent.

DimensionReasoningScore

Conciseness

Mostly efficient, but the --conversation semantics are explained three times (the flags table, 'Binding a Task to the Right Conversation', and the 'Default binding' bullet in Important Notes), and the cron field diagram plus 'Common patterns' like '`*/5 * * * *` — every 5 minutes' restate standard cron syntax Claude already knows; only the tool-specific deviations (no named days, no `?`, `L`, `#`) earn their tokens.

3 / 5

Actionability

Fully executable throughout: every command is complete and copy-paste ready ('letta cron add --name "dog-walk-reminder" ... --cron "0 16 * * *"', 'letta cron list --agent "$LETTA_AGENT_ID" --conversation self') with flag tables and realistic worked examples covering the common cases.

5 / 5

Workflow Clarity

Clear sequences with explicit verification checkpoints for risky operations ('Then verify the binding explicitly', 'create and verify the replacement before deleting the old one'), but there is no error-recovery loop and 'letta cron delete --all' is presented without a caution.

4 / 5

Progressive Disclosure

A single, well-organized file with clear section headers and no bundle files to reference; the Cron Expression Reference and Examples sections are the only candidates for extraction, and at this size the inline placement is a minor organization tradeoff rather than a defect.

4 / 5

Total

16

/

20

Passed

Description

78%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.

A strong, specific description with a well-drawn boundary against the overlapping Wake skill. Its main weakness is that the affirmative trigger ('when to use this one') is only implied by contrast with Wake rather than stated directly, and a few natural user terms (reminder, recurring) are absent.

DimensionReasoningScore

Specificity

Names the domain ('letta cron CLI') and enumerates several concrete capabilities — 'other conversations, computers, run history, and schedule replacement' — but never states its own create/manage actions, deflecting 'create/list/cancel' to Wake, leaving a minor gap in coverage.

4 / 5

Completeness

The 'what' is clear ('Advanced scheduling through the letta cron CLI for other conversations, computers, run history, and schedule replacement') and 'when' is addressed through explicit contrast routing ('Use Wake for ordinary create/list/cancel operations in the current conversation'), but there is no affirmative 'Use when...' clause, so the trigger could be more explicit.

4 / 5

Trigger Term Quality

Good natural-keyword coverage ('scheduling', 'cron', 'run history', 'schedule replacement'), but common user phrasings like 'reminder', 'recurring', or 'timer' are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche with an explicit boundary drawn against the sibling Wake skill; distinctive triggers like 'run history', 'schedule replacement', and 'computers' make it unlikely to fire for the wrong skill.

5 / 5

Total

17

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
letta-ai/letta-code
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.