reminder

v1.0.2

Capture events in natural language, save to workspace, and schedule Telegram reminders with customizable offsets and query support for upcoming events.

0· 117·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for kirkraman/jx-reminder.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "reminder" (kirkraman/jx-reminder) from ClawHub.
Skill page: https://clawhub.ai/kirkraman/jx-reminder
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Canonical install target

openclaw skills install kirkraman/jx-reminder

ClawHub CLI

Package manager switcher

npx clawhub@latest install jx-reminder
Security Scan
Capability signals
Requires sensitive credentials
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description match the instructions: capture natural-language events, save to workspace, and schedule reminders via SkillBoss cron. However, registry metadata claims no required env vars while SKILL.md declares SKILLBOSS_API_KEY as required; also the delivery target is described as "current Telegram" but no Telegram credentials are requested (this appears to rely on SkillBoss managing delivery). These mismatches should be clarified with the publisher.
Instruction Scope
Runtime instructions are scoped to parsing user messages, writing/updating a workspace file (~/.skillboss/workspace/reminders/events.yml), and creating remote cron jobs via SkillBoss. The provided snippet sends user input to the external SkillBoss /v1/pilot LLM endpoint (containing event text). This is expected for parsing but is a privacy consideration because user event contents are sent to a third-party service.
Install Mechanism
Instruction-only skill with no install spec and no code files beyond a small YAML template — nothing is written to disk by an installer. Low install risk.
Credentials
The skill requires SKILLBOSS_API_KEY (declared in SKILL.md and used in the example code) which is consistent with calling the SkillBoss API. Optional envs REMINDER_TZ and REMINDER_OFFSETS_MINUTES are reasonable. The registry summary's 'Required env vars: none' is inconsistent with SKILL.md. No Telegram tokens are requested — the skill assumes SkillBoss can send reminders to the user's linked Telegram, which is plausible but should be confirmed.
Persistence & Privilege
always:false and no system-wide modifications. The skill writes its own workspace file under ~/.skillboss and uses remote scheduling; it does not request elevated or persistent platform privileges beyond normal skill behavior.
Assessment
This skill behaves as a normal reminder agent but sends event text to SkillBoss's /v1/pilot endpoint for parsing and requires a SKILLBOSS_API_KEY (the registry listing omitted this). Before installing: 1) Verify you trust SkillBoss with the contents of your events (they will receive message text). 2) Confirm what SKILLBOSS_API_KEY scopes/permissions are and whether SkillBoss will deliver notifications to your Telegram account (no Telegram token is requested locally). 3) Ensure the workspace path (~/.skillboss/workspace/reminders/events.yml) is acceptable for storing personal events and that sensitive secrets are not accidentally written there. 4) Ask the publisher to correct the registry metadata to list SKILLBOSS_API_KEY as required and clarify how reminders are delivered to Telegram. If you’re uncomfortable with remote parsing/delivery, decline or run in a restricted environment.

Like a lobster shell, security has layers — review code before you run it.

aivk976nznay516q0eftvsre7b75h8572sjlatestvk976nznay516q0eftvsre7b75h8572sj
117downloads
0stars
2versions
Updated 1w ago
v1.0.2
MIT-0

Reminder (secretary)

A lightweight personal secretary for SkillBoss:

  • Tell it events in natural language (Chinese/English).
  • It extracts structured info and stores it in your workspace (so Git/claw-roam can sync across devices).
  • It schedules Telegram reminders using SkillBoss cron.

What it does

  • Capture events from chat (meetings / birthdays / deadlines)
  • Store events in a workspace data file (easy to back up & sync via Git/claw-roam)
  • Schedule Telegram reminders using SkillBoss cron
  • Answer queries like "我最近有什么安排/计划?"

Data (separated from skill)

This skill contains no personal event data.

User data lives in the workspace at:

  • Events file: ~/.skillboss/workspace/reminders/events.yml

Template (shipped with the skill):

  • skills/reminder/assets/events.template.yml

Config (env)

  • SKILLBOSS_API_KEY — SkillBoss API Hub 统一认证 Key
  • REMINDER_TZ (default: Asia/Shanghai)
  • REMINDER_OFFSETS_MINUTES (default: 1440,60,10 for 24h/1h/10m)

AI 能力调用

当需要解析自然语言事件时,通过 SkillBoss API Hub 的 /v1/pilot 接口自动路由最优 LLM:

import requests, os

SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

def parse_event_with_llm(user_input: str) -> dict:
    r = requests.post(
        "https://api.skillbossai.com/v1/pilot",
        headers={
            "Authorization": f"Bearer {SKILLBOSS_API_KEY}",
            "Content-Type": "application/json"
        },
        json={
            "type": "chat",
            "inputs": {
                "messages": [
                    {"role": "system", "content": "Extract event info (title, datetime, notes, repeat) from user input. Return JSON."},
                    {"role": "user", "content": user_input}
                ]
            },
            "prefer": "balanced"
        },
        timeout=60,
    )
    result = r.json()
    return result["result"]["choices"][0]["message"]["content"]

Capture behavior

When user says something like:

  • "后天上午10点有个会"
  • "下个月2号我妈生日"
  • "周五下午三点交报告"

Do:

  1. Parse the event:
    • title
    • start datetime (Shanghai)
    • notes (optional)
    • reminders offsets (default 24h/1h/10m)
    • repeat (optional: yearly/monthly/weekly)
  2. If key info is ambiguous (e.g. '后天' date, '下个月' which month, lunar birthday conversion, time missing), ask only the minimal clarifying question(s).
  3. Write/update the event in reminders/events.yml.
  4. Create cron jobs for each reminder time (delivery to current Telegram).

Reply style

  • After scheduling: reply briefly with the resolved datetime + confirmation.
  • For cancellations/changes: confirm what was changed and whether cron jobs were removed/replaced.

Queries

If user asks:

  • "我最近有什么安排?"
  • "下周有什么?"

Then read reminders/events.yml, compute upcoming items (Shanghai time), and summarize.

Notes / safety

  • Never commit machine-specific secrets (keep them in LOCAL_CONFIG.md, already gitignored).
  • For lunar birthdays: store the canonical lunar date + the computed solar date for the target year; ask how to handle leap months when needed.

Comments

Loading comments...