CCM
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
tclawde avatar

Cron Helper

tclawde/openclaw-skills-user
418 installs
Summary

This teaches Claude to use the openclaw cron CLI instead of trying to track time manually, which doesn't work because the model has no internal clock. The key insight is the isolated session mode: when you want Claude to actually do something at a scheduled time (run a check, send a summary, execute a task), it spins up a separate agent session that can use tools and deliver results to chat. Main session is just for simple reminder notifications. It handles the usual cron patterns (every N minutes, daily at 9am) plus duration shortcuts like "+30m" for one-off delayed tasks. The documentation is thorough about when to use which session type and includes a logging format for tracking what jobs got created.

Install to Claude Code

npx -y skills add tclawde/openclaw-skills-user --skill cron-helper --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
Files
SKILL.mdView on GitHub

Cron Helper Skill

Purpose: Guides me to use openclaw cron CLI for time-based tasks and send logs on create/remove.

When to use:

  • User asks for periodic/reminder tasks
  • User mentions "remind me every X"
  • User needs scheduled background checks
  • User wants agent to perform a task at a specific time

Core Principle

Always prefer cron over manual timing.

Reason: I lack an internal clock. Manual "track time yourself" fails because I can get absorbed in reading/thinking and lose track of time. Cron is an external clock that works reliably.


Main vs Isolated Session

Isolated Session (RECOMMENDED for tasks) ✅ Best Practice

Use --session isolated when you want the agent to actually perform a task:

  • Agent receives the message and executes it
  • Can use tools (exec, read, message, etc.)
  • Can deliver output to a channel
  • Does not pollute main conversation history

Format:

openclaw cron add \
  --name "job_name" \
  --cron "0 9 * * *" \
  --session isolated \
  --message "Task instructions for the agent" \
  --deliver \
  --channel feishu

Main Session (simple notifications only)

Use --session main with --system-event for simple notifications only:

  • Just displays a message in main chat
  • Agent does NOT execute any tasks
  • No tool calls, no delivery

Format:

openclaw cron add \
  --name "reminder" \
  --at "+30m" \
  --session main \
  --system-event "Reminder: check email"

How I Should Respond

Step 1: Detect the request

Keywords: "every", "remind", "schedule", "定时", "每小时/每天/每周", "在X分钟后执行"

Step 2: Ask for details

Get from user:

  • What - task description or notification message
  • When - schedule (e.g., "every 2 hours", "at 9am daily", "in 10 minutes")
  • Delivery - does output need to be sent to a chat? (default: no)
  • Name - job name (optional, auto-generated if not provided)

Step 3: Create cron job

For agent tasks (RECOMMENDED):

openclaw cron add \
  --name "task_name" \
  --at "+10m" \
  --session isolated \
  --message "Your task instructions here" \
  --deliver \
  --channel feishu

For simple reminders:

openclaw cron add \
  --name "reminder" \
  --at "+10m" \
  --session main \
  --system-event "Your reminder message"

Remove a cron job:

openclaw cron rm <job_id>

List all cron jobs:

openclaw cron list

Other useful commands:

openclaw cron status          # 查看调度器状态
openclaw cron run <job_id>    # 立即触发任务
openclaw cron enable <job_id> # 启用任务
openclaw cron disable <job_id> # 禁用任务
openclaw cron runs <job_id>   # 查看执行历史

Delivery Options

When using --session isolated, you can deliver output to a chat:

OptionDescription
--deliverEnable delivery (required for channel output)
--channel <name>Channel: feishu, telegram, slack, whatsapp, etc.
--to <dest>Channel-specific target (chat ID, phone, etc.)
--post-mode fullPost full output instead of summary

Examples:

# Deliver to Feishu
--deliver --channel feishu

# Deliver to Telegram
--deliver --channel telegram --to "-1001234567890"

# Deliver with full output
--deliver --channel feishu --post-mode full

Common Options

OptionDescription
--cron <expr>Cron expression (5-field or 6-field with seconds)
--every <duration>Run every duration (e.g., 10m, 1h)
--at <when>Run once at time (ISO or +duration, supports m/s)
--tz <iana>Timezone (default: local)
--session main|isolatedTarget session (default: main)
--system-event <text>System event payload (main session only)
--message <text>Agent message payload (isolated session only)
--delete-after-runDelete one-shot job after success
--disabledCreate job in disabled state

Step 4: Send log

On CREATE/REMOVE only:

After creating or removing cron jobs, send ONE log with the exact command:

Log format:

# 新增任务
[HH:MM] CRON ✅
$ openclaw cron add \
  --name "job_name" \
  --at "+10m" \
  --session isolated \
  --message "task description" \
  --deliver \
  --channel feishu

# 删除任务
[HH:MM] CRON ❌
$ openclaw cron rm <job_id>

Examples:

# 新增
[21:30] CRON ✅
$ openclaw cron add \
  --name "daily-summary" \
  --cron "0 9 * * *" \
  --tz "Asia/Shanghai" \
  --session isolated \
  --message "总结今天的工作" \
  --deliver \
  --channel feishu

# 删除
[21:41] CRON ❌
$ openclaw cron rm 983a0f0e-0976-414a-b3d0-fd09c533e301

Key points:

  • Send log ONLY on create/remove, NOT on execution
  • Keep it minimal: One command block, no extra text

Cron → Human mapping (五位 - 分时日月周):

  • */5 * * * * → 每5分钟
  • */30 * * * * → 每30分钟
  • 0 * * * * → 每1小时
  • 0 */2 * * * → 每2小时
  • 0 9 * * * → 每天1次(09:00)
  • 0 10,22 * * * → 每天2次(10:00,22:00)
  • 0 9 * * 1 → 每周1次(周一09:00)

Cron → Human mapping (六位 - 秒分时日月周):

  • */1 * * * * * → 每1秒
  • */5 * * * * * → 每5秒
  • */30 * * * * * → 每30秒

Best Practice Summary

Use CaseSessionPayloadDelivery
Agent performs taskisolated--message--deliver ✅
Simple notificationmain--system-event❌

Rule of thumb: If you want the agent to do something (use tools, send messages), use --session isolated + --message.


What NOT To Do

❌ Don't say "I'll set a reminder myself" ❌ Don't try to track time manually ❌ Don't use --system-event when you need the agent to execute tasks ❌ Don't forget --deliver when you need output sent to chat ❌ Don't send execution logs (only log on create/remove)

✅ Always use the openclaw cron CLI ✅ Use --session isolated for agent tasks ✅ Use --session main for simple notifications only ✅ Send log on create/remove only ✅ Keep log simple and clean


Common Schedule Patterns

五位 Cron(分 时 日 月 周)

FrequencyCron ExpressionCLI Flag
Every 5 min*/5 * * * *--cron "*/5 * * * *"
Every 30 min*/30 * * * *--cron "*/30 * * * *"
Every hour0 * * * *--cron "0 * * * *"
Every 2 hours0 */2 * * *--cron "0 */2 * * *"
Daily at 9am0 9 * * *--cron "0 9 * * *"
Twice daily (10am, 10pm)0 10,22 * * *--cron "0 10,22 * * *"
Weekly (Monday 9am)0 9 * * 1--cron "0 9 * * 1"

六位 Cron(秒 分 时 日 月 周)

FrequencyCron ExpressionCLI Flag
Every 1 second*/1 * * * * *--cron "*/1 * * * * *"
Every 5 seconds*/5 * * * * *--cron "*/5 * * * * *"
Every 30 seconds*/30 * * * * *--cron "*/30 * * * * *"

Duration flags:

FrequencyCLI Flag
Every 10 minutes--every "10m"
Every 2 hours--every "2h"
Once in 20 minutes--at "+20m"
Once in 20 seconds--at "+20s"

Loaded automatically when skill is installed.

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
Categories
AI & Agent BuildingAutomation & WorkflowsCLI & Terminal
First SeenJun 3, 2026
View on GitHub

Recommended

More AI & Agent Building →
rllm-org avatar
hive

rllm-org/hive

Run the hive experiment loop — autonomous iteration on a shared task. Use when the agent is in a hive task directory and needs to run experiments, submit results, or participate in the swarm. Triggers on "hive", "run hive", "autoresearch", "start experimenting", "join the swarm", "start the loop", or when .hive/task file is detected.
417
213
rysweet avatar
mermaid-diagram-generator

rysweet/amplihack

Converts architecture descriptions, module specs, or workflow docs into Mermaid diagrams. Use when visualizing brick module relationships, workflows (DDD, investigation), or system architecture. Supports: flowcharts, sequence diagrams, class diagrams, state machines, entity relationship diagrams, and Gantt charts. Generates valid Mermaid syntax for embedding in markdown docs.
417
71
tldraw avatar
skill-creator

tldraw/tldraw

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends an AI agent's capabilities with specialized knowledge, workflows, or tool integrations.
417
49.6k
alirezarezvani avatar
handoff

alirezarezvani/claude-skills

Compact the current conversation into a handoff document for another agent to pick up. References existing artifacts (PRDs, plans, ADRs, issues, commits, diffs) by path or URL instead of duplicating them. Use when user wants to hand off the conversation to a fresh agent or starts a new session that picks up prior work.
414
24.6k
xcrawl-api avatar
xcrawl

xcrawl-api/xcrawl-skills

Use this skill as the default XCrawl entry point for direct XCrawl requests, including single-URL fetch, format selection, sync or async execution, and JSON extraction with prompt or json_schema.
414
453
jezweb avatar
fastmcp

jezweb/claude-skills

Build MCP servers in Python with FastMCP to expose tools, resources, and prompts to LLMs. Supports storage backends, middleware, OAuth Proxy, OpenAPI integration, and FastMCP Cloud deployment. Prevents 30+ errors. Use when: creating MCP servers, or troubleshooting module-level server, storage, lifespan, middleware, OAuth, background tasks, or FastAPI mount errors.
413
960