agentleFS
Sign inStart free
0xOpCode0xOpCode/tele-harness/.agents/skills/tg-copywriter/SKILL.md

tg-copywriter

Skill1 starsChanged 51 days agoMITView on GitHub

Crafts mobile-optimized, slop-free conversational copy, command naming schemes, and BotFather descriptions.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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
  1. Distinctive:

    Follow these constraints when authoring bot messages, commands, and prompts:

    line 9
  2. Distinctive:

    Delete conversational throat-clearing: "Sure!", "Here is what you requested:", "I am glad to help!", "As an automated bot...".

    line 17
  3. Very specific:

    Avoid underscores and hyphens in primary commands.

    line 24
  4. Distinctive:

    Keep command words under 8 characters for user memory retention.

    line 25
  5. Distinctive:

    Keep descriptions between 15 and 40 characters.

    line 30
  6. Distinctive:

    Never repeat the command word in its description.

    line 37
  7. Distinctive:

    Prefer HTML parse mode over MarkdownV2 to avoid character escaping parse failures.

    line 40
  8. Distinctive:

    Use native blockquotes for contextual quotes or logs:

    line 43
  9. Distinctive:

    Use at most one emoji per message block.

    line 49
  10. Very specific:

    Always attach an inline Cancel or Retry button to error messages to prevent conversational dead ends.

    line 59

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Telegram Bot Copy & Interface Protocol

Follow these constraints when authoring bot messages, commands, and prompts:

1. Mobile Viewport Budget

  • Design messages for mobile screens (360x640px base viewports).
  • Enforce the 5-line threshold: keep standard status and prompt messages under 5 lines before presenting keyboard rows.
  • Split multi-topic reports into paginated messages or expandable blockquotes (<blockquote>...</blockquote>). Never paste unformatted walls of text into chat.

2. Slop Elimination in Bot Dialogue

  • Delete conversational throat-clearing: "Sure!", "Here is what you requested:", "I am glad to help!", "As an automated bot...".
  • Lead with actionable status or data.
  • Ban fake conversational status messages ("Processing your data..."). Use native Telegram chat actions (sendChatAction: typing or upload_document) while calculations run.
  • Zero adverbs in bot dialogue. State status values directly.

3. Command Naming Standards

  • Format: Lowercase letters only (/start, /settings, /profile, /status, /help).
  • Avoid underscores and hyphens in primary commands. Prefer /export over /export_all_records.
  • Keep command words under 8 characters for user memory retention.
  • Reserve multi-part names (/admin_users, /sys_restart) for restricted administrative panels.

4. BotFather Command Descriptions

  • Telegram client UI truncates command descriptions after 40 characters.
  • Keep descriptions between 15 and 40 characters.
  • Begin each description with an active verb:
    • /start: Open main menu and dashboard
    • /settings: Manage alerts and preferences
    • /status: View runtime metrics
    • /wallet: Check balance and payments
    • /help: Access documentation and support
  • Never repeat the command word in its description.

5. Visual Hierarchy & Formatting

  • Prefer HTML parse mode over MarkdownV2 to avoid character escaping parse failures.
  • Bold section headers: <b>Account Overview</b>.
  • Code format keys, transaction hashes, user IDs, and numeric values: <code>TX-94821</code>.
  • Use native blockquotes for contextual quotes or logs:
    <b>Deployment Alert</b>
Service <code>api-gateway</code> restarted.
<blockquote>Worker pool reloaded in 420ms.</blockquote>
  • Use at most one emoji per message block. Never cluster decorative emojis.

6. Tone Calibration by Domain

  • Developer & Infrastructure Bots: Compact tabular data, monospace metrics, minimal text.
  • Financial & Payment Bots: Explicit currency denominations, high-contrast confirmation warnings, transaction IDs.
  • Community & Support Bots: Concise instructions, direct button labels, step indicators ([Step 1 of 3]).

7. Error & Recovery Patterns

  • State the specific failure without blaming the user.
  • State the exact recovery action.
  • Always attach an inline Cancel or Retry button to error messages to prevent conversational dead ends.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free