terrylica/cc-skills

search-messages

user wants to search for messages across all Telegram chats or within a specific chat, find old messages by text, or look up Telegram message.

查看源码

使用方法

  1. 复制安装命令,在自己的智能体环境安装前先检查源码包。
  2. 从原始文档核对所需工具、凭据和支持的宿主。
  3. 说明输入材料与期望交付物,并对照来源检查输出。
npx skills add https://github.com/terrylica/cc-skills --skill search-messages

开始前需了解

  • 安装不包含模型订阅、API 额度或访问文件的权限。
  • 仓库星数和安装量反映活跃情况,不等于独立质量或安全测试。
仓库原始内容

按源仓库内容呈现,保留标题、案例、代码、表格、链接以及原文引用的演示图片。

Search Telegram Messages

Search messages globally across all chats or within a specific chat.

Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.

Preflight

  1. Session must exist: ~/.local/share/gramjs/<profile>.session
  • If missing, run /tlg:setup first

Usage

bash
/usr/bin/env bash << 'EOF'
ROOT="$(cc-plugin-root tlg)"
SCRIPT="$ROOT/scripts/tg-cli.ts"

# Global search (all chats)
bun "$SCRIPT" search "search term" -n 20

# Search in specific chat
bun "$SCRIPT" search "keyword" --chat 2124832490

# Filter by sender
bun "$SCRIPT" search "topic" --from @username

# Combined: search in chat from specific sender
bun "$SCRIPT" search "query" --chat @groupname --from @sender -n 10
EOF

Parameters

ParameterTypeDescription
querystringSearch text (required)
--chatstring/intLimit to specific chat (omit for global)
--fromstring/intFilter by sender
-n/--limitintMax results (default: 20)
--previewintTruncate each body to N chars (default: full text, multi-line indented).

Output Format

Default (full text, multi-line indented):

[YYYY-MM-DD HH:MM] [Chat Name] (id:12345) Sender: First line of body
    continuation line 1 (indented under header)
    continuation line 2

With --preview 100:

[YYYY-MM-DD HH:MM] [Chat Name] (id:12345) Sender: First line of body ⏎ continuation collapsed onto…

Use --preview N only for high-volume scans where you want one row per message. Default = full text — long bodies are no longer silently truncated at 150 chars (the prior default forced manual workarounds when content actually mattered).

Anti-Patterns

  • Flood risk: Global search with common terms may hit rate limits (~30s wait per 10 requests)
  • Empty results: Global search requires non-empty query string

Post-Execution Reflection

After this skill completes, check before closing:

  1. Did the command succeed? — If not, fix the instruction or error table that caused the failure.
  2. Did parameters or output change? — If tg-cli.ts's interface drifted, update Usage examples and Parameters table to match.
  3. Was a workaround needed? — If you had to improvise (different flags, extra steps), update this SKILL.md so the next invocation doesn't need the same workaround.

Only update if the issue is real and reproducible — not speculative.

来自同一仓库

更多 Skills

全部 Skills
terrylica
社区

academic-pdf-to-gfm

Convert academic PDF papers to GitHub-renderable GFM markdown with math equations. TRIGGERS - PDF, GitHub markdown, math

1小时安装量
1
GitHub Stars
2
最近更新
11月5日
terrylica
社区

adr-code-traceability

Add ADR references to code for traceability. TRIGGERS - ADR traceability, code reference, document decision in code.

1小时安装量
1
GitHub Stars
2
最近更新
11月5日
terrylica
社区

arxiv-source-first-paper-ingest

Read an arXiv paper faithfully by fetching the authors' own LaTeX source instead of OCR-ing the PDF. Extracts every display equation with its label, environment and enclosing proposition, renders each to MathML, and proves usability by compiling each formula with a real TeX engine. Use when you need a paper's formulas exactly — to replicate a method, implement a loss function or custom objective, verify a quoted number, or check a claim against what the authors actually wrote. TRIGGERS - read th

1小时安装量
1
GitHub Stars
2
最近更新
11月5日
terrylica
社区

azure-provision

Bootstrap Azure automation when interactive az login is blocked by a Conditional Access policy (error 530035, "Device state: Unregistered"). Mints a service principal through the Azure Portal session ONCE — using Microsoft Graph over a captured token, not DOM clicking — then provisions resource groups, Cognitive Services / AI Language / Speech resources and their keys entirely via az/REST, writing key AND endpoint together into the SCS vault. Use when az login fails but the portal works, when mo

1小时安装量
1
GitHub Stars
2
最近更新
11月5日