Agent skill

meta

Execute Claude Code commands in the telegram_agent project directory. Use when the user wants to work on the telegram agent itself, fix bugs, add features, or modify the bot code. This is a COMMAND HANDLER, not a script executor.

Stars 74
Forks 17

Install this agent skill to your Project

npx add-skill https://github.com/glebis/claude-skills/tree/main/meta

SKILL.md

Meta Skill - Command Handler

⚠️ IMPORTANT: This skill is a COMMAND HANDLER registration. It tells the bot to handle /meta commands by spawning Claude Code Agent SDK sessions in the telegram_agent directory.

What This Does

Registers /meta as a command handler that:

  1. Takes the user's prompt after /meta
  2. Spawns a Claude Code Agent SDK session
  3. Sets working directory to ~/ai_projects/telegram_agent
  4. Returns responses in Telegram

Implementation

The actual command handler needs to be registered in the telegram bot codebase at:

  • src/bot/handlers/claude_commands.py - Add meta command handler
  • src/bot/bot.py - Register the command

Usage Pattern

User types in Telegram:

/meta fix the rate limiting bug
/meta add better logging
/meta refactor authentication

Bot spawns Claude Agent SDK with:

  • Working directory: ~/ai_projects/telegram_agent
  • Prompt: User's text after /meta
  • Same infrastructure as /claude command

Example User Requests

  • /meta fix bug in message handler
  • /meta add error recovery to file sending
  • /meta refactor the session management
  • /meta improve the keyboard layout

Implementation Notes

Must use ClaudeCodeService with custom cwd parameter:

python
service.execute_prompt(
    prompt=user_prompt,
    cwd="/Users/server/ai_projects/telegram_agent"
)

Expand your agent's capabilities with these related and highly-rated skills.

glebis/claude-skills

tdd

This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the Task tool for architecturally enforced context isolation. Supports Jest, Vitest, pytest, Go test, cargo test, PHPUnit, and RSpec.

74 17
Explore
glebis/claude-skills

brand-agency

Applies Agency brand colors and typography to artifacts including presentations, SVG graphics, documents, and web interfaces. This skill should be used when brand colors, visual formatting, neobrutalism style, or Agency design standards apply. Keywords - branding, corporate identity, visual identity, styling, brand colors, typography, visual formatting, visual design, neobrutalism.

74 17
Explore
glebis/claude-skills

github-gist

Publish files or Obsidian notes as GitHub Gists. Use when user wants to share code/notes publicly, create quick shareable snippets, or publish markdown to GitHub. Triggers include "publish as gist", "create gist", "share on github", "make a gist from this".

74 17
Explore
glebis/claude-skills

chrome-history

Query Chrome browsing history with natural language. Filter by date range, article type, keywords, and specific sites.

74 17
Explore
glebis/claude-skills

wispr-analytics

This skill should be used when analyzing Wispr Flow voice dictation history for self-reflection, work patterns, mental health insights, or productivity analytics. Triggered by requests like "/wispr-analytics", "analyze my dictations", "what did I dictate today", "wispr reflection", or any request to review voice dictation patterns. Supports modes - technical (coding/work), soft (communication), trends (volume/frequency), mental (sentiment/energy/rumination).

74 17
Explore
glebis/claude-skills

granola

This skill should be used when importing, listing, or exporting Granola meeting recordings and transcripts. Queries Granola's local cache and API to list meetings, extract transcripts, and export to Obsidian notes in Fathom-compatible format.

74 17
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results