telegram-report-sender
Skill2 starsChanged 8 days agoMITView on GitHub
Send generated research artifacts to Telegram as an explicit post-processing step, using credentials from the sender skill folder or CLI flags.
- Reads credentials
In this repository42 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- kr-analyst-report-discoverSkill
- kr-analyst-report-fetchSkill
- kr-analyst-report-insightSkill
- kr-analyst-report-watchSkill
- kr-article-readabilitySkill
- kr-chatgpt-reviewSkill
- kr-daily-market-newsSkill
- kr-earnings-reviewSkill
- kr-finance-slide-claritySkill
- kr-foreign-analystSkill
- kr-market-leadersSkill
- kr-market-sentimentSkill
- kr-naver-bloggerSkill
- kr-naver-blog-publishSkill
- kr-naver-browseSkill
- kr-naver-insightSkill
- kr-order-backlog-analysisSkill
- kr-portfolio-guardSkill
- kr-portfolio-monitorSkill
- kr-research-siteSkill
- kr-sector-analysisSkill
- kr-sector-auditSkill
- kr-sector-compareSkill
- kr-sector-data-packSkill
- kr-sector-planSkill
- kr-sector-updateSkill
- kr-stock-analysisSkill
- kr-stock-chartSkill
- kr-stock-dart-analysisSkill
- kr-stock-data-packSkill
- kr-stock-planSkill
- kr-stock-updateSkill
- kr-strategy-backtestSkill
- kr-trade-flow-analysisSkill
- kr-web-browseSkill
- us-daily-market-newsSkill
- us-earnings-reviewSkill
- us-sec-analysisSkill
- us-stock-analysisSkill
- us-strategy-backtestSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill only when the user explicitly asks to send a generated report or preview a Telegram send plan.
- Very specific: line 18
Read Telegram credentials from this sender skill folder's gitignored .env, or accept --token and --chat-id flags:
- Very specific: line 31
Remove --dry-run only after explicit user approval.
- Distinctive: line 43
Never auto-send as part of collection, Naver publishing, scheduled report generation, or validation.
- Distinctive: line 45
Do not assume the user is working from the source repository.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Telegram Report Sender
Use this skill only when the user explicitly asks to send a generated report or preview a Telegram send plan.
Workflow
- Confirm the report artifact path exists. Supported inputs include Markdown and JSON artifacts from:
kr-market-leaderskr-analyst-report-watchkr-daily-market-newsus-daily-market-news- generic JSON or Markdown research artifacts
Read Telegram credentials from this sender skill folder's gitignored
.env, or accept--tokenand--chat-idflags:TELEGRAM_BOT_TOKEN=123456789:replace_with_your_bot_token TELEGRAM_CHAT_ID=123456789Preview first unless the user already approved sending:
node skills/telegram-report-sender/scripts/send-telegram.js --input <artifact> --dry-run- Remove
--dry-runonly after explicit user approval. The sender posts a short summary and, unless--summary-onlyis used, attaches the matching Markdown file when the input is JSON and a same-basename.mdexists.
Options
--summary-only: send only the summary text.--document-only: send only the attachment.--attach <path>: attach a specific file instead of the auto-detected artifact.--token <token>and--chat-id <id>: override.env.TELEGRAM_API_BASE: optional Bot API-compatible gateway.
Safety
- Never auto-send as part of collection, Naver publishing, scheduled report generation, or validation.
- Redact bot tokens in errors and chat output.
- Do not assume the user is working from the source repository. Locate this sender skill folder and run the script from there or by absolute path.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.