Skip to content
Agentmart
Submit a tool

proactive-checkin

Internal scheduled task - sends high-value proactive messages with strict anti-spam rules.

Skill by aldorado

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/aldorado-proactive-checkin

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Internal scheduled task - sends high-value proactive messages with strict anti-spam rules.

Use cases: productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/proactive-checkin

What's inside

Skill name
proactive-checkin
Description
Internal scheduled task - sends high-value proactive messages with strict anti-spam rules.
License
MIT
Instructions
64 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Proactive Check-in Task

You run as a background task.
Send thoughtful proactive messages without being annoying.

## Core behavior

- max 1-2 proactive messages/day
- allowed types: reminder, idea, research-find
- priority: creative ideas > project progress > everything else

## Guardrails

Do NOT send if any is true:
- local time 00:00-08:00 (Europe/Vienna)
- 2 proactive messages already sent today
- less than 4 hours since last proactive message
- active chat in last 90 minutes

If blocked:
- do housekeeping
- log `decision: skipped (guardrail)`
- set `response_text` to empty string

## Candidate quality

Generate 3-5 candidates, score each:
- relevance (0-3)
- novelty (0-2)
- actionability (0-2)

Send only if top score >= 5.
Otherwise skip and log why.

## Context sources

Always check:
1. `data/proactive-log.md`
2. recent sessions in `data/sessions/`
3. semantic memory lookup (memory-lookup skill)
4. Obsidian ideas/forge only if Obsidian is configured:
   - read `OBSIDIAN_VAULT_PATH` from environment
   - use `$OBSIDIAN_VAULT_PATH/ideas/` and `$OBSIDIAN_VAULT_PATH/forge/`
   - if missing, skip Obsidian source cleanly

## Housekeeping

Per run max:
- memory cleanup: 2 actions
- instructions cleanup: 1 tiny improvement in `.pi/SYSTEM.md` only if clearly needed

## Log format

Append short entries to `data/proactive-log.md`.

If sending:
- `response_text`: short natural message
- `conversation_finished`: false

If not sending:
- `response_text`: ""
- `conversation_finished`: true

From aldorado/visor, MIT.

More from aldorado/visor

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Feb 23, 2026 (8 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from aldorado

Cite this page

proactive-checkin skill. Agent Mart. https://agentmart.dev/skills/aldorado-proactive-checkin (last updated 2026-10-24)