Not in the top 1,000 by GitHub stars

awrshift/skill-telegram

The only Telegram skill your AI agent needs. Read messages, parse channels, download voice notes. User API via Telethon.

Claude Code Productivity

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → f1eda1b9d8ad

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit f1eda1b9d8adf5d428e13fc27e5ed6c7e756552a

Version-pinned installation · Claude Code

git clone --filter=blob:none --no-checkout https://github.com/awrshift/skill-telegram.git .hotskills/awrshift-skill-telegram && git -C .hotskills/awrshift-skill-telegram checkout --detach f1eda1b9d8adf5d428e13fc27e5ed6c7e756552a
# Copy each selected skill directory from .hotskills/awrshift-skill-telegram into .claude/skills/<skill-name>/

10GitHub stars

Not availablestars in 7 days

1skill in this repository

0commits in 30 days

Heat

Insufficient history

Not enough history yet to measure heat. It appears after a few days of data.

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

30-day change not yet available: not enough history.

Individual skills in this repository

telegram /

How it works

When your agent uses it

The only Telegram skill your AI agent needs. Read messages, parse channels, download and transcribe voice notes — all via Telethon user API. One session file, zero bots. Use when user says 'read telegram', 'check saved messages', 'fetch from telegram', 'parse channel', 'transcribe voice', 'telegram search', 'check my telegram', or when any agent needs Telegram data. Also trigger on 'what did I save in telegram', 'read my saved messages', 'get messages from channel X', 'download voice notes'. Covers: ad-hoc reading, channel parsing with sanitization, voice/audio download. Requires TG_API_ID, TG_API_HASH env vars and a session file.

What it loads into context

Frontmatter

148 tokens

Always available to the agent

SKILL.md

1,234 tokens

When the skill is activated

Reference documents

2,789 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Setup (first run)
1. Read Messages (any chat)
2. Parse Channels
3. Download Voice Notes
4. Setup & Diagnostics
Architecture
Session Resolution
Limitations

Scripts executed separately

scripts/sanitizer.py
scripts/tg_fetch_channels.py
scripts/tg_fetch_voice.py
scripts/tg_read.py
scripts/tg_setup.py

Files

.claude-plugin/marketplace.jsonasset1,029 bytes
.gitignoreasset13 bytes
LICENSEasset1,074 bytes
README.mddoc6,038 bytes
SKILL.mdcore4,999 bytes
SKILL.mdcore4,999 bytes
SKILL.mdcore4,999 bytes
SKILL.mdcore4,999 bytes
SKILL.mdcore4,999 bytes
assets/telegram-architecture.pngasset2,006,840 bytes
references/json-schema.mddoc2,629 bytes
references/setup.mddoc1,682 bytes
scripts/sanitizer.pyruns2,138 bytes
scripts/tg_fetch_channels.pyruns5,946 bytes
scripts/tg_fetch_voice.pyruns8,021 bytes
scripts/tg_read.pyruns4,185 bytes
scripts/tg_setup.pyruns5,976 bytes

Read SKILL.md


# Telegram Skill — User API Integration

All operations via Telethon (user API, not bot API). One session file for everything.

## Setup (first run)

1. **Get API credentials** at https://my.telegram.org/apps → create app → copy `api_id` and `api_hash`
2. **Set env vars** in your `.env`:
   ```
   TG_API_ID=your_api_id
   TG_API_HASH=your_api_hash
   ```
3. **Install Telethon:** `pip install telethon`
4. **Run setup diagnostic:** `python3 scripts/tg_setup.py`

View the complete source on GitHub

Skills included

Repository facts

License: MIT
Created: Mar 19, 2026
Last pushed: Mar 26, 2026
Forks: 0
Open issues: 0
Project activity: Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 5, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 4 notes

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
No dangerous shell commands
19 network referencesin 5 files: README.md:3 .claude-plugin/marketplace.json:8 SKILL.md:12 and 2 more
1 obfuscation signalin 1 file: scripts/sanitizer.py:17
No instruction overrides
5 executable scriptsin 5 files: scripts/sanitizer.py:1 scripts/tg_fetch_channels.py:1 scripts/tg_fetch_voice.py:1 and 2 more
5 references to secretsin 3 files: README.md:78 references/setup.md:41 scripts/tg_setup.py:163
No requests to vote in Hot

Show all 30 signals by file

`.claude-plugin/marketplace.json`

Network accessline 8

"description": "The only Telegram skill your AI agent needs. Read messages, parse channels, download voice notes via user API.",     "version": "1.0.0",     "homepage": "https://github.com/awrshift/skill-telegram"

Network accessline 9

"version": "1.0.0",     "homepage": "https://github.com/awrshift/skill-telegram"   },

Network accessline 10

"homepage": "https://github.com/awrshift/skill-telegram"

`README.md`

Network accessline 3

![Claude Code](https://img.shields.io/badge/Claude%20Code-D97757?style=for-the-badge&logo=claude&logoColor=white)

Network accessline 4

![Codex CLI](https://img.shields.io/badge/Codex%20CLI-000000?style=for-the-badge&logo=openai&logoColor=white)

Network accessline 5

![Telegram](https://img.shields.io/badge/Telegram-26A5E4?style=for-the-badge&logo=telegram&logoColor=white)

Network accessline 6

![License MIT](https://img.shields.io/badge/License-MIT-yellow.svg?style=for-the-badge)

Network accessline 47

# Copy skill to your project git clone https://github.com/awrshift/skill-telegram.git

Network accessline 48

git clone https://github.com/awrshift/skill-telegram.git

Network accessline 56
```
1. Go to https://my.telegram.org/apps
```
Access to secretsline 78
```
[Credential-related source omitted]
```
Access to secretsline 86
```
[Credential-related source omitted]
```

Network accessline 111

{"channel": "SEOBAZA", "id": 1546, "date": "2026-03-19T03:29:34+00:00", "text": "Original", "text_sanitized": "Cleaned", "links": ["https://..."], "hash": "64e9a72207ed56d4", "views": 1403}

Network accessline 156

| Codex CLI | Copy `./` to `.openai/skills/` | | Gemini CLI | Copy `./` to `.gemini/skills/` | | Any Agent Skills tool | Follow [spec](https://agentskills.io) |

Network accessline 158

| Any Agent Skills tool | Follow [spec](https://agentskills.io) |

Network accessline 162

- [**skill-awrshift**](https://github.com/awrshift/skill-awrshift) — adaptive decision-making framework

Network accessline 163

- [**skill-brainstorm**](https://github.com/awrshift/skill-brainstorm) — 3-round Claude x Gemini adversarial brainstorm

Network accessline 164

- [**ClawClaw Soul**](https://clawclawsoul.com) — persistent identity protocol for AI agents

`SKILL.md`

Network accessline 12

1. **Get API credentials** at https://my.telegram.org/apps → create app → copy `api_id` and `api_hash`

`references/json-schema.md`

Network accessline 25

{"channel": "SEOBAZA", "channel_id": "1234567", "id": 456, "date": "2026-03-06T12:00:00+00:00", "text": "Google update...", "text_sanitized": "Google update...", "links": ["https://example.com"], "hash": "abc123def456", "reply_to": null, "v

`references/setup.md`

Network accessline 5
```
1. Go to https://my.telegram.org/apps
```
Access to secretsline 41
```
[Credential-related source omitted]
```
Access to secretsline 63
```
[Credential-related source omitted]
```

`scripts/sanitizer.py`

Executable scriptline 1
```
Executable file
```
Possible obfuscationline 17
```
r'[\x00-\x08\x0b\x0c\x0e-\x1f\x7f'
```

`scripts/tg_fetch_channels.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/tg_fetch_voice.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/tg_read.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/tg_setup.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 163
```
[Credential-related source omitted]
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 27 facts

Network access in prose of documentationREADME.md:3Low confidence
Network access in prose of documentationREADME.md:4Low confidence
Network access in prose of documentationREADME.md:5Low confidence
Network access in prose of documentationREADME.md:6Low confidence
Network access in code of documentationREADME.md:47Low confidence
Network access in code of documentationREADME.md:48Low confidence
Network access in prose of documentationREADME.md:56Low confidence
Access to secrets in code of documentationREADME.md:78Low confidence
Access to secrets in code of documentationREADME.md:86Low confidence
Network access in code of documentationREADME.md:111Low confidence
Network access in prose of documentationREADME.md:156Low confidence
Network access in prose of documentationREADME.md:158Low confidence
Network access in prose of documentationREADME.md:162Low confidence
Network access in prose of documentationREADME.md:163Low confidence
Network access in prose of documentationREADME.md:164Low confidence
Network access in prose of the SKILL.mdSKILL.md:12Low confidence
Network access in code of documentationreferences/json-schema.md:25Low confidence
Network access in prose of documentationreferences/setup.md:5Low confidence
Access to secrets in code of documentationreferences/setup.md:41Low confidence
Access to secrets in code of documentationreferences/setup.md:63Low confidence
Executable script in prose of a file that runsscripts/sanitizer.py:1Low confidence
Possible obfuscation in code of a file that runsscripts/sanitizer.py:17High confidence
Executable script in code of a file that runsscripts/tg_fetch_channels.py:1High confidence
Executable script in code of a file that runsscripts/tg_fetch_voice.py:1High confidence
Executable script in code of a file that runsscripts/tg_read.py:1High confidence
Executable script in code of a file that runsscripts/tg_setup.py:1High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/tg_setup.py:163Low confidence

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Native	Manifest .claude-plugin/marketplace.json	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md SKILL.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

awrshift/skill-telegram

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

telegram

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Before you install

.claude-plugin/marketplace.json

README.md

SKILL.md

references/json-schema.md

references/setup.md

scripts/sanitizer.py

scripts/tg_fetch_channels.py

scripts/tg_fetch_voice.py

scripts/tg_read.py

scripts/tg_setup.py

How the signals fit together

Works with

You might also use

nyxandro/telegram-bot-development-skill

eugeniughelbur/obsidian-second-brain

AgriciDaniel/claude-obsidian

AgriciDaniel/claude-ads

internet-court/internet-court-skill

epoko77-ai/im-not-ai

`SKILL.md`

`.claude-plugin/marketplace.json`

`README.md`

`SKILL.md`

`references/json-schema.md`

`references/setup.md`

`scripts/sanitizer.py`

`scripts/tg_fetch_channels.py`

`scripts/tg_fetch_voice.py`

`scripts/tg_read.py`

`scripts/tg_setup.py`