CtrlK
BlogDocsLog inGet started
Tessl Logo

scheduled-tasks

Use for complex Agent Zero scheduler work, including creating, updating, deleting, running, waiting for, timezone-correcting, or auditing scheduled, planned, and adhoc tasks.

68

Quality

81%

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

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable reference with copy-paste JSON examples and clear field signatures. The main gap is the absence of explicit validation/retry checkpoints for destructive and batch task operations, which leaves workflow clarity just short of full marks.

Suggestions

Add an explicit verify-then-act checkpoint for destructive operations (e.g., 'show_task by UUID to confirm before delete_task') as a numbered step, not just a safety bullet.

Provide a brief retry/feedback pattern for batch operations (e.g., re-list and confirm state after run_task) to satisfy the feedback-loops requirement.

Optionally separate the full action signature reference into a referenced file if the body grows, keeping the overview concise.

DimensionReasoningScore

Conciseness

The body is lean: a compact action reference, field lists, two minimal JSON examples, and short safety bullets, with no preamble explaining concepts Claude already knows — every section earns its tokens.

3 / 3

Actionability

It gives concrete, copy-paste-ready JSON for planned, scheduled, and lookup actions plus explicit field signatures for every action, matching the 'fully executable ... copy-paste ready' anchor.

3 / 3

Workflow Clarity

The opening 'Always inspect existing tasks before creating, updating, deleting, or running one' sequences the basic flow, and safety rules cover destructive UUID lookup, but there is no validate/verify checkpoint for batch or destructive operations, which the rubric caps at 2.

2 / 3

Progressive Disclosure

At under 85 lines with no external bundle files, the content is well-organized into clear sections (Actions, Schedule Fields, Safety, Example) one level deep, which the simple-skills scoring note allows to score 3.

3 / 3

Total

11

/

12

Passed

Description

77%

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, mostly concrete description with an explicit 'Use for' trigger and a broad but specific action list. It is held back by product jargon ('complex Agent Zero scheduler work') and trigger phrasing that leans on internal terminology rather than natural user language.

Suggestions

Lead with natural user language (e.g., 'Remind me', 'schedule a recurring task', 'set a one-time reminder') rather than 'complex Agent Zero scheduler work' to improve trigger_term_quality.

Add reminder/cron phrasings a user would actually say so the description triggers on everyday requests, not just 'scheduler work'.

Tighten the niche framing to make it unambiguously distinct from general task-management skills.

DimensionReasoningScore

Specificity

The description lists many concrete actions ('creating, updating, deleting, running, waiting for, timezone-correcting, or auditing') across three task types, matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

It answers both 'what' (the enumerated CRUD/audit actions) and 'when' via the explicit 'Use for ...' trigger clause, satisfying the 'clearly answers both what AND when' anchor.

3 / 3

Trigger Term Quality

It includes natural terms users might say ('scheduled, planned, and adhoc tasks'), but the leading 'complex Agent Zero scheduler work' is product jargon and it omits common phrasings like 'remind me', 'reminder', or 'set up a cron task' that a user would actually say.

2 / 3

Distinctiveness Conflict Risk

The scheduler niche is fairly distinct, but 'complex Agent Zero scheduler work' is broad and 'scheduled, planned, and adhoc tasks' could overlap with general task-management skills; it is somewhat specific but not a clearly bounded, conflict-free niche.

2 / 3

Total

10

/

12

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
agent0ai/agent-zero
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.