Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
terrylica avatar

Draft Message

  • 46 installs
  • 62 repo stars
  • Updated August 3, 2026
  • terrylica/cc-skills

Helps with ai & agent building tasks.

About

draft-message is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted development.

  • draft-message
  • AI & Agent Building
  • AI-coding skill

Draft Message by the numbers

  • 46 all-time installs (skills.sh)
  • +1 installs in the week ending Jul 27, 2026 (Skillselion tracking)
  • Ranked #7,568 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
  • Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/terrylica/cc-skills --skill draft-message

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs46
repo stars62
Last updatedAugust 3, 2026
Repositoryterrylica/cc-skills

What it does

Helps with ai & agent building tasks.

Files

SKILL.mdMarkdownGitHub ↗

Draft a Telegram Message (via Saved Messages)

Send a message to the user's Saved Messages so the user can review it, optionally edit it, then copy-paste it into the target chat's compose area before sending. Saved Messages is every Telegram account's built-in private chat with itself — it syncs across all clients automatically.

Why Saved Messages, not MTProto cloud drafts? The official Telegram clients have a known unfixed race condition (tdesktop#29111, closed "not planned") where the local empty-draft state silently overwrites cloud drafts pushed via SaveDraftRequest from another authorization. We observed this in practice: the server confirmed the draft, but the user's compose area stayed empty. Saved Messages bypasses this entirely — full HTML formatting is preserved, and Telegram's native copy-paste between compose areas preserves rich text across iOS, Android, Desktop, and Web.
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.

When To Use Draft vs. Send

SituationUse
Long or multi-paragraph message an agent composed autonomouslyDraft — let the human eyeball it before it lands
Message carries sensitive wording (hiring, firing, contract terms)Draft — one typo or wrong name is expensive
Reply where tone matters (addressing a peer or an external party)Draft — AI-generated tone can be subtly off
Short confirmations, status updates, routine responsesSend — friction of drafting exceeds value
Automated notifications, alerts, scheduled pingsSend — no human-in-the-loop needed
Time-critical message where draft→review→send round-trip is too slowSend — accept the risk

Default when uncertain: draft. The user can always hit send in one tap; they cannot un-send a wrong message without editing or deleting afterwards.

Preflight

Before drafting, verify the session is authorized (not just that the file exists):

bun "$SCRIPT" check-auth

If EXPIRED, run /tlg:setup first.

Usage: tg-cli.ts draft

/usr/bin/env bash << 'DRAFT_EOF'
SCRIPT="${CLAUDE_PLUGIN_ROOT:-$HOME/.claude/plugins/marketplaces/cc-skills/plugins/tlg}/scripts/tg-cli.ts"

# Draft a plain-text message labelled for a group
bun "$SCRIPT" draft -1003958083153 "Plain text draft goes here"

# Draft an HTML-formatted message
bun "$SCRIPT" draft --html -1003958083153 "<b>Bold heading</b>

Body text with <code>inline code</code> and a <a href=\"https://example.com\">link</a>."

# Draft labelled for a user
bun "$SCRIPT" draft @someusername "Quick question: does this framing land right?"
DRAFT_EOF

The recipient argument is used only to label the draft's banner in Saved Messages — it is not the destination. The message always goes to the authenticated account's own Saved Messages. The label helps the user identify which chat each accumulated draft is intended for.

How It Appears in Saved Messages

Two messages are sent per draft:

1. Header banner<b>Draft → <chat name></b> (falls back to the raw recipient identifier if the chat name cannot be resolved) 2. Body — the drafted content with the requested formatting

Keeping the header separate lets the user long-press only the body, tap Copy, and paste cleanly into the target chat's compose area without having to trim the banner.

Workflow Pattern For AI Agents

1. Compose the message in your response 2. Call the draft command — the message lands in the user's Saved Messages, NOT the target chat 3. Tell the user: _"Draft for <chat name> saved to your Saved Messages. Open Saved Messages → long-press the body → Copy → paste into the target chat's compose area → review → send."_ 4. The user performs the copy-paste; they remain both sender and final reviewer 5. If edits are needed, they happen in the target chat's compose area before sending

Drafts are your reviewer safety net — a deliberate pause between AI authorship and human publication.

Parameters

ParameterTypeDescription
recipientstring/intTarget chat ID/username — used only to label the Saved Messages banner
messagestringDraft text (required)
--htmlflagParse message as HTML (bold/code/links)
-p/--profilestringAccount profile (eon default)

Behavior Details

  • Drafts append, they do not replace. Each draft call sends a new (header, body) pair to Saved Messages. Older drafts remain visible above — the user can mentally track which is latest by position.
  • Long drafts auto-split. The body is auto-split at ~3900 plain chars per Telegram's 4096 hard limit. Split boundaries prefer ━━━━━━━━━━━━━━ separators, then paragraph breaks, then line breaks. Each continuation part is labelled <i>(Part N/M)</i>. See send-message SKILL.md "Auto-split for long messages" for the full algorithm.
  • Formatting is preserved end-to-end. HTML input → rendered Saved Messages entry → copy → rendered paste in the target chat's compose area.
  • No cloud-draft race conditions. Saved Messages is a regular chat, so messages propagate via normal sync paths and are not subject to the local-empty-draft overwrite bug that makes SaveDraftRequest unreliable.
  • Silent from the target chat's perspective. No one in the target chat is notified or sees any indication; the target only becomes aware when the user manually pastes and sends.

Anti-Patterns

Anti-PatternWhy It Fails
Drafting when the message is short and boilerplateWastes the user's time — they could send directly and edit in the compose area
Drafting many messages in rapid successionSaved Messages becomes a wall of stale drafts; hard to tell which is current
Using draft for time-critical alerts (downtime, outages)User may not open Saved Messages until hours later
Claiming a draft was "sent to the group"Be explicit: "Draft saved to Saved Messages for your review" vs. "Message sent"
Forgetting to tell the user to paste into the target chatThe draft sits in Saved Messages forever if the user doesn't know the next step

Error Handling

ErrorCauseFix
Cannot find any entityBad username/chat IDLabel falls back to raw identifier — draft still saves to Saved Messages
Session expiredSession no longer validRun /tlg:setup

Relationship to Other TLG Skills

  • `send-message` — use when no human review is needed; includes edit-vs-supplement discipline for already-sent messages
  • `draft-message` (this) — use when human review IS needed before send
  • `search-messages` — useful for checking existing chat context before drafting a reply

Post-Execution Reflection

After this skill completes, check before closing:

1. Did the draft land in Saved Messages? Confirm by asking the user to check their Saved Messages. 2. Did the user paste into the target chat successfully? If formatting broke on paste, report the specific client (iOS/Android/Desktop/Web) so the Behavior Details section can be updated with a client-specific caveat if a regression appears. 3. Was draft the right choice vs. send? If the user immediately copy-pasted and sent without edits, draft was overkill — consider sending directly next time for similar messages.

Only update this SKILL.md if the issue is real and reproducible.

Related skills

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.