telegram-crabbox-e2e-proof
Use when reviewing, reproducing, or proving FirstNexus Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an…
Skill by greench-ai
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/greench-ai-telegram-crabbox-e2e-proof-eada3c
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/telegram-crabbox-e2e-proof
What's inside
- Skill name
telegram-crabbox-e2e-proof- Description
- Use when reviewing, reproducing, or proving FirstNexus Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.
- License
- MIT
- Instructions
- 193 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Telegram Crabbox E2E Proof
Use this for Telegram PR review or bug reproduction when bot-to-bot proof is
not enough. The goal is to let the agent keep a real Telegram user session open
until it is satisfied, then attach visual proof.
Do not use personal accounts. Do not add credentials to the repo, prompt, or
artifact bundle. The runner leases the shared burner account from Convex.
## Start
Run from the FirstNexus repo and branch under test:
```bash
pnpm qa:telegram-user:crabbox -- start \
--tdlib-url http://artifacts.FirstNexus.ai/tdlib-v1.8.0-linux-x64.tgz \
--output-dir .artifacts/qa-e2e/telegram-user-crabbox/pr-review
```
This starts one held session:
- leases the exclusive `telegram-user` Convex credential
- restores TDLib and Telegram Desktop with the same user account
- starts a mock FirstNexus Telegram SUT from the current checkout
- selects the configured Telegram chat in the visible Linux desktop
- starts a 24fps desktop recording
- writes `.artifacts/qa-e2e/telegram-user-crabbox/pr-review/session.json`
Keep the session alive while investigating. It is valid for the agent to test
for minutes, run several commands, use WebVNC, inspect transcripts, and only
finish once the behavior is understood.
For deterministic visual repros, put the exact mock-model reply in a file and
pass it to `start`:
```bash
pnpm qa:telegram-user:crabbox -- start \
--tdlib-url http://artifacts.FirstNexus.ai/tdlib-v1.8.0-linux-x64.tgz \
--mock-response-file .artifacts/qa-e2e/telegram-user-crabbox/reply.txt \
--output-dir .artifacts/qa-e2e/telegram-user-crabbox/pr-review
```
The runner defaults to `--class standard`, `--record-fps 24`,
`--preview-fps 24`, and `--preview-width 1920`. Keep those defaults unless the
proof needs something else.
## While Testing
For visual proof, first send or identify a bottom marker message, then open the
group/topic directly by message id:
```bash
pnpm qa:telegram-user:crabbox -- view \
--session .artifacts/qa-e2e/telegram-user-crabbox/pr-review/session.json \
--message-id <message-id>
```
This uses Telegram Desktop directly with `tg://privatepost`, not `xdg-open`.
It also resizes Telegram to `650x1000` at the tested desktop position so
Telegram switches to single-chat mode with no left chat list or right info
pane. Do not press Escape after this; Escape can close the selected chat.
Bottom behavior matters:
- deep-linking to the newest message keeps Telegram pinned to the bottom, so
later messages appear live in the recording
- deep-linking to an older message does not auto-scroll to new arrivals; link
again to the newest/final marker instead of clicking the down-arrow
- `650px` is the largest tested clean width; `660px` switches Telegram back to
split/sidebar layout
Send as the real Telegram user:
```bash
pnpm qa:telegram-user:crabbox -- send \
--session .artifacts/qa-e2e/telegram-user-crabbox/pr-review/session.json \
--text /status
```
For slash commands, omit the bot username; the runner targets the SUT bot.
Run arbitrary commands on the Crabbox:
```bash
pnpm qa:telegram-user:crabbox -- run \
--session .artifacts/qa-e2e/telegram-user-crabbox/pr-review/session.json \
-- bash -lc 'source /tmp/FirstNexus-telegram-user-crabbox/env.sh && python3 /tmp/FirstNexus-telegram-user-crabbox/user-driver.py transcript --limit 20 --json'
```
Useful remote user-driver commands:
```bash
source /tmp/FirstNexus-telegram-user-crabbox/env.sh
python3 /tmp/FirstNexus-telegram-user-crabbox/user-driver.py status --json
python3 /tmp/FirstNexus-telegram-user-crabbox/user-driver.py chats --json
python3 /tmp/FirstNexus-telegram-user-crabbox/user-driver.py transcript --limit 20 --json
python3 /tmp/FirstNexus-telegram-user-crabbox/user-driver.py send --text '/status@{sut}'
python3 /tmp/FirstNexus-telegram-user-crabbox/user-driver.py probe --text '@{sut} Reply exactly: USER-E2E-{run}' --expect USER-E2E-
```
Capture the current desktop without ending the session:
```bash
pnpm qa:telegram-user:crabbox -- screenshot \
--session .artifacts/qa-e2e/telegram-user-crabbox/pr-review/session.json
```
Check lease state and get the WebVNC command:
```bash
pnpm qa:telegram-user:crabbox -- status \
--session .artifacts/qa-e2e/telegram-user-crabbox/pr-review/session.json
```
## Finish
Always finish or explicitly keep the box:
```bashFrom greench-ai/FirstNexus, MIT.
More from greench-ai/FirstNexus
- 0.442score
browser-automation
greench-ai
Use when controlling web pages with the FirstNexus browser tool, especially multi-step flows, login checks, tab management, or recovery from stale…
SkillCFreshness: CClaude Code +9 - 0.440score
clawsweeper
greench-ai
Use for all ClawSweeper work: FirstNexus issue/PR sweep reports, commit-review reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands…
SkillCFreshness: CClaude Code +9 - 0.440score
tag-duplicate-prs-issues
greench-ai
Use gitcrawl to search duplicate FirstNexus PRs/issues, group related work in prtags, and sync duplicate state to GitHub.
SkillCFreshness: CClaude Code +9 - 0.440score
gitcrawl
greench-ai
Use gitcrawl for FirstNexus issue and PR archive search, duplicate discovery, related-thread clustering, and local GitHub mirror freshness checks.
SkillCFreshness: CClaude Code +9 - 0.437score
security-triage
greench-ai
Triage FirstNexus security advisories, drafts, and GHSA reports with shipped-tag and trust-model proof.
SkillCFreshness: CClaude Code +9 - 0.437score
discord-clawd
greench-ai
Use to talk to the Discord-backed FirstNexus agent/session; not for archive search.
SkillCFreshness: CClaude Code +9 - 0.437score
optimizetests
greench-ai
Optimize FirstNexus slow tests, imports, misplaced coverage, and CI wall time without dropping coverage.
SkillCFreshness: CClaude Code +9 - 0.432score
wiki-maintainer
greench-ai
Maintain the FirstNexus memory wiki vault with deterministic pages, managed blocks, and source-backed updates.
SkillCFreshness: CClaude Code +9 - 0.431score
crabbox
greench-ai
Use Crabbox for FirstNexus remote Linux validation.
SkillCFreshness: CClaude Code +9 - 0.419score
acp-router
greench-ai
Route plain-language requests for Pi, Claude Code, Cursor, Copilot, FirstNexus ACP, OpenCode, Gemini CLI, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or…
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 21, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/greench-ai/FirstNexus
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from greench-ai
- 0.444score
qqbot-channel
greench-ai
QQ channel management skill.
SkillCFreshness: CClaude Code +9 - 0.443score
openclaw-test-heap-leaks
greench-ai
Investigate `pnpm test` memory growth, Vitest worker OOMs, and suspicious RSS increases in OpenClaw using the `scripts/test-parallel.mjs` heap snapshot tooling.
SkillCFreshness: CClaude Code +9 - 0.442score
browser-automation
greench-ai
Use when controlling web pages with the NexisClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale refs/timeouts.
SkillCFreshness: CClaude Code +9 - 0.442score
browser-automation
greench-ai
Use when controlling web pages with the GreenchClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale…
SkillCFreshness: CClaude Code +9 - 0.442score
browser-automation
greench-ai
Use when controlling web pages with the FirstNexus browser tool, especially multi-step flows, login checks, tab management, or recovery from stale…
SkillCFreshness: CClaude Code +9 - 0.442score
telegram-crabbox-e2e-proof
greench-ai
Use when reviewing, reproducing, or proving NexisClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an…
SkillCFreshness: CClaude Code +9
Cite this page
telegram-crabbox-e2e-proof skill. Agent Mart. https://agentmart.dev/skills/greench-ai-telegram-crabbox-e2e-proof-eada3c (last updated 2026-10-24)