Life Radar Repo

v1.0.0

Build a concise “what needs action now” daily brief by aggregating reminders from multiple channels (email, calendar, SMS/iMessage, weather, and task notes)...

0· 155·0 current·0 all-time
byLucas@yikailucas

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for yikailucas/life-radar-repo.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Life Radar Repo" (yikailucas/life-radar-repo) from ClawHub.
Skill page: https://clawhub.ai/yikailucas/life-radar-repo
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

Bare skill slug

openclaw skills install life-radar-repo

ClawHub CLI

Package manager switcher

npx clawhub@latest install life-radar-repo
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
Purpose & Capability
The name/description match the SKILL.md: the skill's purpose is to aggregate reminders from calendar, email, SMS/iMessage, weather, and tasks and prioritize them. It does not declare any environment variables or binaries — this is plausible for an instruction-only skill that relies on the platform's existing connectors, but the skill implicitly expects access to multiple personal data sources (email, SMS, calendar) without documenting what connectors/permissions it will use.
Instruction Scope
Instructions are focused on producing an action-first digest and include clear output structure, priority rules, source collection order, and safety guidance (redact secrets, avoid hallucinated dates). However, the 'collect only what is available in current environment' phrasing grants broad discretion to read whatever connected sources exist (calendar, messages, billing notifications, tasks), which is expected for this purpose but worth noting as scope-broadening.
Install Mechanism
No install specification and no code files — lowest-risk delivery model (instruction-only). Nothing is written to disk and no external downloads or package installs are required.
Credentials
The skill requests no environment variables or credentials in metadata, which aligns with having no install. But its function requires access to potentially sensitive sources (email, SMS, calendar, billing). The metadata does not state which connectors or permissions it expects, so verify platform-level connector grants before enabling.
Persistence & Privilege
always is false and the skill is user-invocable; model invocation is allowed (default). This is normal. There is no indication the skill modifies other skills or system-wide settings.
Assessment
This skill is instruction-only and appears to do what it says, but it needs access to several personal data sources (calendar, email, SMS/iMessage, billing, tasks). Before enabling: (1) check which platform connectors or account permissions the agent will be granted and limit them to only the sources you want aggregated; (2) test the skill with non-sensitive data or a limited mailbox/calendar to confirm it redacts sensitive values as promised; (3) confirm retention/visibility rules (will summaries or raw data be stored or sent externally?) and revoke permissions if you see unexpected access.

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

latestvk977tdjhcweryqg0ee1ptkhhes832dga
155downloads
0stars
1versions
Updated 1mo ago
v1.0.0
MIT-0

Life Radar

Generate an action-first digest, not a raw data dump.

If the user asks from a specific role perspective (CEO / manager / employee), read references/modes.md and adapt prioritization/output accordingly.

Output format

Always output in this structure:

  1. Must-do (today) — max 3 items
  2. Should-do (soon) — max 5 items
  3. Nice-to-have — max 3 items
  4. Suggested next actions — 1-line commands the user can say next

Each item must include:

  • What happened
  • Why it matters
  • Deadline/time window (or “unspecified”)

Priority rules

Classify with this order:

  • P0 Must-do
    • Payment due / account risk / security alert
    • Meeting in <2h
    • Time-sensitive message requiring response today
  • P1 Should-do
    • Meeting or task in 24-72h
    • Follow-up pending from important contact
    • Logistics prep (travel, weather-impact, documents)
  • P2 Nice-to-have
    • Low urgency updates
    • Optional optimization tasks

If uncertain, downgrade priority and mark uncertainty explicitly.

Source collection flow

Collect only what is available in current environment; skip unavailable sources without failing.

  1. Calendar events (today + tomorrow)
  2. Recent urgent messages (SMS/iMessage/email/DM)
  3. Billing or financial notifications
  4. Weather impact for planned outings
  5. Existing tasks/notes (if connected)

Time-window defaults

  • If user asks "today": prioritize 0-24h window
  • If user asks "this week": prioritize 7-day window, still keep Must-do today-centric
  • If user asks without a window: default to today + next 72h

Safety and quality

  • Redact secrets, tokens, and full account numbers.
  • Avoid hallucinating dates or amounts; mark as unknown when missing.
  • Prefer fewer high-confidence items over many noisy items.
  • If no meaningful items, return: “Today looks clear. No urgent actions detected.”

Trigger phrases

Treat these as strong triggers:

  • “今天有什么要处理”
  • “给我每日行动清单”
  • “帮我做个优先级摘要”
  • “扫一下我今天的事情”
  • “daily action digest”

Comments

Loading comments...