flyer103flyer103/skills/cron-task-spec/SKILL.md

cron-task-spec

Skill1 starsChanged 5 months agoMITView on GitHub

Standard specification for cron tasks. Used for creation, update, and validation of OpenClaw cron tasks.

In this repository8 other files it gives its agents.
- ai-cognitive-loadSkill
- android-controlSkill
- autonomous-researchSkill
- git-worktreeSkill
- hermes-pr-guidelinesSkill
- jj-workspaceSkill
- knowledge-explorerSkill
- xurl-best-practicesSkill

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Execute strictly per task requirements: - Do not add content not mentioned in the task description
line 24
Distinctive:
Targeted modifications: - Only modify parts specified by the user.
line 31
Distinctive:
When creating / updating a task, auto-check:
line 156

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Cron Task Standard Specification

Based on SMART-ER principles: Specific, Measurable, Achievable, Relevant, Time-bound, Evaluated, Reviewed

Core Principles

Execute strictly per task requirements - Do not add content not mentioned in the task description
Confirm ambiguous requirements - The following are considered ambiguous and must be confirmed with the user:
- Output format is not specified
- Data source is not specified
- Time range is not defined
- Push target is not specified
Targeted modifications - Only modify parts specified by the user; protect other content

Output Flow

Data Collection → Store to Database → Push to Discord Channel

Do not output any additional content in the current session after pushing (e.g., "Task completed")

Validation Flow

New task / Update → Execute once → Check standards → [Fail] → Analyze cause → Refine task → Repeat (max 3 times)
                                         ↓ [Pass]
                                    Notify user

Validation Checklist

#	Check Item	Failure Handling
1	Task understanding is clear	Confirm with user
2	Data source is accessible	Specify source
3	Data storage successful	Check connection
4	Discord push successful	Check ID
5	No extraneous output	Adjust logic
6	Content quality meets standards	Adjust generation

Loop Limits

Max iterations: 3 times
Interval between iterations: 5 minutes
Single execution timeout: 10 minutes

Task Description Template

⚠️ All tasks must use the unified format

Required Fields

Field	Description
Task Name	Unique identifier
Execution Time	cron expression + timezone
Push Target	Discord Channel ID (numeric)
Data Sources	Markdown list
Output Requirements	Format, word count, number of entries

Optional Fields

Field	Description
Storage Config	Database type, table name, fields
Execution Logic	Execution steps for complex tasks
Change Log	Fill in when updating

Template Example

# [Task Name]

## Basic Info

| Item | Value |
|------|-----|
| **Task Name** | [Name] |
| **Execution Time** | [cron] (Asia/Shanghai) |
| **Push Target** | Discord Channel ID: [Numeric ID] |
| **Created At** | [YYYY-MM-DD] |

## Data Sources

- Source 1: [URL]
- Source 2: [URL]

## Output Requirements

| Item | Requirement |
|------|------|
| **Format** | Markdown/JSON/Text |
| **Entry Count** | TOP N |
| **Word Count** | X words per entry |

## Storage Config (Optional)

- Database: PostgreSQL (localhost:5432/db)
- Table Name: [table_name]
- Fields: [field_list]

Effectiveness Evaluation

Automatically evaluated after each execution:

Metric	Target
Execution success rate	≥ 95%
Push success rate	≥ 95%
Execution duration	≤ 5 minutes

Exception handling:

3 consecutive failures → Notify user
Success rate < 80% → Trigger review

Detailed References

Full Specification: See references/full-spec.md
Example Tasks: See references/examples.md
Rich Template for Complex Tasks: See references/rich-template.md — recommended for multi-stage / multi-source tasks, includes flowcharts, Schema, Pitfalls, and version history

Quick Check

When creating / updating a task, auto-check:

Title uses #, sections use ##
Basic Info includes a table
Execution time includes timezone
Channel ID is numeric
Data sources are in list format

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free