agentleFS
PraveensenpaiPraveensenpai/karakuri/skills/ai-agents/tayori/SKILL.md

tayori

Skill0 starsChanged 2 months agoMITView on GitHub

Sends aesthetic Telegram notifications, interactive approval requests, and completion notices to the user's phone via Tayori (便り). Use 'tayori ask -i' (strictly with -i) when awaiting user approval or asking critical questions, 'tayori done' when a task finishes, and 'tayori alert' for important warnings or errors.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Awaiting Approval (Interactive Required): When pausing for human confirmation before running destructive actions, major migrations, or …

    line 14
  2. Very specific:

    Task Milestones & Completion: When finishing a multi-step task, build, or release so the user knows immediately (tayori done).

    line 15

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

tayori (便り) Notification Skill

Integrates AI coding assistants with Telegram notifications via the tayori CLI.

When to Use

  • Awaiting Approval (Interactive Required): When pausing for human confirmation before running destructive actions, major migrations, or architectural decisions. Mandatory: Always pass -i (--interactive) so the CLI blocks until the user taps [Approve] or [Reject] on Telegram.
  • Task Milestones & Completion: When finishing a multi-step task, build, or release so the user knows immediately (tayori done).
  • Informational Notifications: One-way status messages or progress updates (tayori send). Never use tayori ask for one-way messages.
  • Errors & Warnings: High-priority errors or build failures requiring user attention (tayori alert).

Usage

# 1. Interactive Mobile Approval (Mandatory: blocks until user taps [Approve] or [Reject])
tayori ask -i "Proposed English and Romaji search support for app titles. Awaiting approval to proceed."

# With custom timeout in seconds (default is 300s)
tayori ask -i --timeout 600 "Run destructive database migration on production?"

# 2. Informational One-Way Notification
tayori send "Starting background compilation for release v1.0.0..."

# 3. Task Completion Alert
tayori done "Release v1.0.0 successfully published and CI is green!"

# 4. Warning or Error Alert
tayori alert "Database connection failed after 3 retries" --level error

# 5. Pipe Command Logs
cargo test 2>&1 | tayori pipe --title "Cargo Test"

Approval Protocol Rules

  • Never Run tayori ask Without -i: Fire-and-forget approval questions exit immediately without waiting for human input, defeating the approval protocol.
  • Exit Code Verification:
    • Exit code 0: User tapped [Approve]. Safe to proceed.
    • Non-zero exit code: User tapped [Reject] or the request timed out. Do not execute proposed modifications.

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.