Wire First NanoClaw Agent
nanocoai/nanoclaw
Connects the first NanoClaw agent to a chat channel and proves delivery by having it send the operator a welcome direct message.
Drafts outbound messages (WhatsApp, SMS, email) in the user's voice.
Install Draft
$ npx skills add jigripokri/POHA --skill draft -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jigripokri/POHA draft --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jigripokri/POHA.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/draft .claude/skills/draft && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "draft" agent skill from https://github.com/jigripokri/POHA/tree/master/skills/draft into .claude/skills/draft/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "draft", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jigripokri/POHA/tree/master/skills/draftType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jigripokri/POHA --skill draft -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jigripokri/POHA draft --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jigripokri/POHA.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/draft .agents/skills/draft && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "draft" agent skill from https://github.com/jigripokri/POHA/tree/master/skills/draft into .agents/skills/draft/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "draft", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jigripokri/POHA --skill draft -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jigripokri/POHA draft --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jigripokri/POHA.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/draft .cursor/skills/draft && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "draft" agent skill from https://github.com/jigripokri/POHA/tree/master/skills/draft into .cursor/skills/draft/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "draft", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jigripokri/POHA.git --path skills/draft--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jigripokri/POHA --skill draft -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jigripokri/POHA draft --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jigripokri/POHA.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/draft .gemini/skills/draft && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "draft" agent skill from https://github.com/jigripokri/POHA/tree/master/skills/draft into .gemini/skills/draft/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "draft", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jigripokri/POHA draftInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jigripokri/POHA --skill draft -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jigripokri/POHA.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/draft .github/skills/draft && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "draft" agent skill from https://github.com/jigripokri/POHA/tree/master/skills/draft into .github/skills/draft/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "draft", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jigripokri/POHA --skill draft -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jigripokri/POHA draft --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jigripokri/POHA.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/draft .opencode/skills/draft && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "draft" agent skill from https://github.com/jigripokri/POHA/tree/master/skills/draft into .opencode/skills/draft/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "draft", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
draft- GitHub stars
- 120
- Token cost
- ~540 tokens
- SKILL.md length
- 285 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
Drafts outbound messages (WhatsApp, SMS, email) in the user's voice.
- Works in 10 steps: Identify the thread. User says "draft a… → Read the last 10–20 messages in the… → Study voice patterns. → …
- Agent Workflows work in your project
- SKILL.md covers Recipe, Voice rules (default —… and What this skill won't do
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Draft is an agent skill from jigripokri/POHA. Drafts outbound messages (WhatsApp, SMS, email) in the user's voice. Studies recent messages in a thread to mirror cadence. Never sends without explicit approval.
Its SKILL.md is about 540 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows. It works with WhatsApp. The repository describes itself as: Personal Overnight Helper Agent. Runs while you sleep. Serves up a morning brief before your alarm. The licence is MIT.
When your agent uses it
- Agent Workflows work in your project
Example prompts
- “Use the draft skill to draft outbound messages (WhatsApp, SMS, email) in the user's voice”
- “/draft”
Workflow steps
10 steps, taken from the first numbered list in SKILL.md.
- Identify the thread. User says "draft a reply to " or "draft a message to about ." If ambiguous, ask one clarifying question.
- Read the last 10–20 messages in the thread. Use the appropriate MCP (WhatsApp, Gmail, Android Messages).
- Study voice patterns.
- Read CLAUDE.md > Voice & Drafting Authorization.
- Read memory/people.md for context on the recipient (if available).
- NEVER read memory/private/carry-on.md. Do not reference anything from it.
- Draft 1–3 options. If user said "draft" (singular), give one. If user said "options" or the message is high-stakes, give 2–3 with brief…
- Show the draft(s). Do NOT send.
- Wait for approval. "Send it", "send A", "send the second one" = green light. Anything else means iterate.
- On approval, send via the appropriate MCP.
What it can do on your machine
Read from SKILL.md and the folder at commit 68f3e38. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Draft loads about 540 tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 285 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from jigripokri/POHA at commit 68f3e38, republished under its MIT licence (© jigripokri). 285 words, ~540 tokens.
Download SKILL.mdSave it as
.claude/skills/draft/SKILL.md (or your agent's skills folder).- name
- draft
- description
- Drafts outbound messages (WhatsApp, SMS, email) in the user's voice. Studies recent messages in a thread to mirror cadence. Never sends without explicit approval.
/draft
Write outbound messages in the user's voice. Used on demand for any thread.
Recipe
When invoked:
Identify the thread. User says "draft a reply to
<person>" or "draft a message to<group>about<topic>." If ambiguous, ask one clarifying question.Read the last 10–20 messages in the thread. Use the appropriate MCP (WhatsApp, Gmail, Android Messages).
Study voice patterns.
- Sentence length and structure
- Vocabulary level (formal vs. casual)
- Regional slang or in-group references
- Punctuation habits
- Use of emoji or not
- Greeting/sign-off patterns (or lack thereof)
Read CLAUDE.md > Voice & Drafting Authorization.
Read memory/people.md for context on the recipient (if available).
NEVER read memory/private/carry-on.md. Do not reference anything from it.
Draft 1–3 options. If user said "draft" (singular), give one. If user said "options" or the message is high-stakes, give 2–3 with brief notes on the difference.
Show the draft(s). Do NOT send.
Wait for approval. "Send it", "send A", "send the second one" = green light. Anything else means iterate.
On approval, send via the appropriate MCP.
Voice rules (default — override in CLAUDE.md)
- Direct. No "Hope this finds you well."
- Match the recipient's tone — if they're casual, you're casual.
- Reference something specific from the recent conversation (callback, shared joke, thing they mentioned).
- Short. Two paragraphs maximum unless the topic genuinely requires more.
- No AI tells: "As an AI...", "I hope this helps...", "Let me know if you have any questions!" — never.
What this skill won't do
- Send before "send it" approval. Always wait.
- Quote anything from carry-on.md.
- Send to multiple recipients without confirming the list explicitly.
- Send if the draft contradicts something obvious from memory (e.g., agreeing to a date the user has a conflict on).
© jigripokri, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/draft of jigripokri/POHA.
Open the folder on GitHubat commit 68f3e38
Compare with similar skills
Draft next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Draft this skilljigripokri/POHA | 120 | — | ~540 | Automated safety check: Pass | MIT | |
| Wire First NanoClaw Agentnanocoai/nanoclaw | 31k | — | ~2.5k | Automated safety check: Notes | MIT | |
| Whatsapp Otpbighadj22/codflow | 346 | — | ~417 | Automated safety check: Pass | Apache-2.0 | |
| Hitl ProtocolLeoYeAI/openclaw-master-skills | 2.2k | — | ~5.3k | Automated safety check: Pass | Apache-2.0 | |
| Integrate Whatsappgokapso/agent-skills | 175 | — | ~4.8k | Automated safety check: Pass | None | |
| Greenapi Client Pythongreen-api/whatsapp-api-client-python | 209 | — | ~3.3k | Automated safety check: Pass | MIT |
Similar skills
Whatsapp Otp
bighadj22/codflow
CodFlow's WhatsApp OTP phone-verification feature (dzverify provider) — optional, off by default, per-store.
Hitl Protocol
LeoYeAI/openclaw-master-skills
HITL Protocol — the open standard for human decisions in autonomous agent workflows.
Integrate Whatsapp
gokapso/agent-skills
Connect WhatsApp to your product with Kapso: onboard customers with setup links, detect connections, receive events via webhooks, and send messages/templates/media.
Greenapi Client Python
green-api/whatsapp-api-client-python
Write correct Python code with the official GREEN-API SDK whatsapp-api-client-python (package whatsappapiclientpython).
Traul Message Search
dandaka/traul
Drives the traul CLI to sync, search and monitor messages from Slack, Telegram, Discord, Linear, Gmail, WhatsApp, Claude Code sessions and Markdown files.
More from jigripokri/POHA
Gsd
jigripokri/POHA
Generate a prioritized punch list from open commitments + tasks, right now.
Reply
jigripokri/POHA
Generate 3 reply options + a recommendation for any incoming message thread.
Wildcard
jigripokri/POHA
Generate one contrarian, non-obvious insight on whatever the user is thinking about.
Roast
jigripokri/POHA
Generate a group-chat roast on demand. An agent skill from jigripokri/POHA.
Related
Works with
Categories
Questions about Draft
What does Draft do?
Drafts outbound messages (WhatsApp, SMS, email) in the user's voice. Draft is an agent skill from jigripokri/POHA. Drafts outbound messages (WhatsApp, SMS, email) in the user's voice.
When should I use Draft?
Draft fits situations like: agent Workflows work in your project.
How do I install Draft in Claude Code?
Run `npx skills add jigripokri/POHA --skill draft -a claude-code`. Or copy the skill folder (skills/draft in jigripokri/POHA) into .claude/skills/draft in your project. Claude Code loads it when a task matches its description.
How do I install Draft in Codex?
Run `npx skills add jigripokri/POHA --skill draft -a codex`. Or copy the skill folder (skills/draft in jigripokri/POHA) into .agents/skills/draft in your project. Codex loads it when a task matches its description.
Can I use Draft in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jigripokri/POHA --skill draft -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/draft, .gemini/skills/draft, .github/skills/draft and .opencode/skills/draft in your project.
What does Draft need to run?
SKILL.md names no scripts, command-line tools or credentials: Draft is instructions for the agent only.
Does Draft access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Draft safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Draft use?
Draft is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Draft use?
About 540 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Draft?
Skills that share tags, products or a category with Draft: Wire First NanoClaw Agent (nanocoai/nanoclaw, 31k stars), Whatsapp Otp (bighadj22/codflow, 346 stars), Hitl Protocol (LeoYeAI/openclaw-master-skills, 2.2k stars) and Integrate Whatsapp (gokapso/agent-skills, 175 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Draft?
jigripokri (a GitHub user) maintains it in jigripokri/POHA, which has 120 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on June 2, 2026.
Source: jigripokri/POHA on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.