CtrlK
BlogDocsLog inGet started
Tessl Logo

schedule-ops-skill

Trigger when the user wants to hand a task to background async execution, run it on a cron/recurring schedule, delegate it to a project Agent for a long run, or inspect/approve/cancel tasks on the board. Typical phrasings: "every day at 9am help me X", "let the coder agent run this", "what's pending approval". **Not for**: one-shot immediate answers (→ just use tools directly), real calendar meetings/appointments (→ calendar-ops-skill), one-off plan approvals (→ `SubmitPlan`).

73

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 highly actionable and clearly sequenced with validation checkpoints and feedback loops for risky operations. Its main weakness is redundancy — several antipatterns and rules are repeated between the explanatory sections and 'Common Mistakes' — which is the primary token-efficiency drag.

Suggestions

De-duplicate the three points repeated in 'Common Mistakes' (Bash-sleep polling, ScheduledTaskWait on scheduled tasks, forgetting ScheduledTaskWait after immediate create) — keep them in one place and cross-reference rather than restating verbatim.

Trim 'Why:' explanations that restate the obvious (e.g. 'past times cannot be scheduled and will be rejected'); retain only the non-obvious reasoning such as the UTC-vs-local timezone pitfall.

Consider moving the cron example table and the full 'Common Mistakes' list into a reference file referenced one level deep from SKILL.md to reduce inline length and improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly efficient and avoids explaining concepts Claude already knows, but three topics (the Bash-sleep polling antipattern, not calling ScheduledTaskWait on scheduled tasks, and forgetting ScheduledTaskWait after immediate create) are restated nearly verbatim between the main sections and 'Common Mistakes', and several 'Why:' lines restate the obvious.

3 / 5

Actionability

Provides copy-paste-ready tool calls with concrete arguments — `ScheduledTaskManage(action:'create', skipPlanConfirm:true)`, `ScheduledTaskWait({taskId, timeoutSec:60})`, `cronExpr: "0 9 * * 1-5"`, `intervalMs: 1800000` — plus a full resolve JSON example, covering the common cases executably.

5 / 5

Workflow Clarity

Multi-step flows are explicitly numbered (immediate create+wait, scheduled create+reply, approval handling, bulk cleanup) with validation checkpoints ('Look before you leap', 'Run date via Bash to confirm timezone') and feedback loops (timeout→re-wait or hand off, rework→replan), and batch/destructive ops carry explicit validation so the cap does not apply.

5 / 5

Progressive Disclosure

The skill is a single self-contained file with no bundle references, but it is well-organized under clear section headers with a logical overview-to-detail flow; because it exceeds 50 lines, the simple-skill exception does not apply and some referenceable material (cron examples, common mistakes) is inlined, keeping it just short of a 5.

4 / 5

Total

17

/

20

Passed

Description

100%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 exemplary: it states concrete capabilities, gives natural trigger phrasings, answers both what and when, and draws clear boundaries against adjacent skills. Voice stays in third person ('the user wants') so no specificity penalty applies.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'hand a task to background async execution, run it on a cron/recurring schedule, delegate it to a project Agent for a long run, or inspect/approve/cancel tasks on the board' — giving comprehensive coverage of the skill's capabilities rather than vague abstractions.

5 / 5

Completeness

Explicitly answers both what the skill does and when to trigger it ('Trigger when the user wants to...'), reinforced with concrete typical phrasings and an explicit 'Not for' boundary — both what and when are present and concrete.

5 / 5

Trigger Term Quality

Provides natural user phrasings ('every day at 9am help me X', 'let the coder agent run this', 'what's pending approval') alongside technical synonyms (cron/recurring, background async), covering the terms users would actually say.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (scheduled/async task operations) and includes an explicit 'Not for' clause disambiguating against calendar-ops-skill and SubmitPlan, minimizing conflict risk with neighboring skills.

5 / 5

Total

20

/

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
itsablabla/openloaf-web
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.