bchewy/codex-telegram-plugin/telegram-search

Claude Code and agent skill by bchewy/codex-telegram-plugin

Trust tier 2
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use when finding Telegram messages by query or window.

Install

npx vskill@latest install bchewy/codex-telegram-plugin/telegram-search

SKILL.md

  1. Convert the user’s request into a precise search query, target dialog(s), sender filter, and time window.
  2. If the target dialog is known, prefer search_cache over live search. Pass chat_ref, query, from_user, min_date, max_date, compact=True for token-efficient result previews, and a freshness window such as auto_sync_seconds=600 when recent messages may matter.
  3. If the target dialog is known but the user explicitly wants a full rebuild, call sync_chat_cache(chat_ref, full=True) first. Otherwise rely on incremental sync (sync_chat_cache(chat_ref) or search_cache(chat_ref, ..., auto_sync_seconds=...)).
  4. Use search_messages_in_chat only for narrow recent one-off lookups where cache setup is unnecessary. Use search_messages_global or list_dialogs only when the dialog is unknown, then switch to cached per-dialog search for deeper work.
  5. Narrow with from_user, min_date, max_date, and conservative limit values whenever the user gives enough context.
  6. Return the best matches first with:
  • short relevance note
  • sender
  • date
  • chat name or chat_ref
  • message snippet
  1. If search_cache returns has_more / next_offset, offer to continue from next_offset instead of rerunning the same search.
  2. If the user’s request is ambiguous, show the top plausible matches instead of pretending there was one obvious answer.
  3. If the user wants surrounding discussion, use thread-aware tools when available; otherwise use get_message_context for chronological neighbors and say that it is chronological context, not necessarily the reply/topic thread.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewPassed

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
18
7-day trend score
15

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 26 Apr 2026, 6 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/bchewy/codex-telegram-plugin/telegram-search/badge)](https://verified-skill.com/skills/bchewy/codex-telegram-plugin/telegram-search)

Something wrong with this skill or its page? Tell us.