ワンクリックで
add-github
Add GitHub channel integration via Chat SDK. PR and issue comment threads as conversations.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Add GitHub channel integration via Chat SDK. PR and issue comment threads as conversations.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Access comprehensive financial data - stocks, crypto, SEC filings, financial statements, and news via Financial Datasets API. Use for market research, fundamental analysis, and financial insights.
NanoClawd Wallet: self-custodial Solana wallet built into this agent. Every agent gets a unique keypair at birth, stored in its private workspace. Supports SOL transfers, SPL token balances, and token swaps via Jupiter v6. Use for on-chain payments, DeFi swaps, balance checks, and Solana interactions.
Add Bux browser agent to NanoClawd — gives a Clawd agent a real persistent Chromium session via Browser Use Cloud, plus agency Telegram action cards. Use when the user wants their agent to browse the web with a real browser (cookies persist, logins stick) or handle 2FA/CAPTCHA hand-off.
Integrate the OpenClawd Framework (sovereign lobster agents on Solana) into NanoClawd. Wires the Framework's pulse loop, identity, survival mechanics, and $CLAWD token payments into NanoClawd agent groups. Use when setting up a fully sovereign Clawd agent with on-chain identity, self-funding, and autonomous operation.
Launch an Upstash Box pre-packaged with NanoClawd and a Solana wallet at birth. Provisions a cloud box, clones NanoClawd, generates a Solana keypair, configures credentials, and starts the agent — wallet-at-birth, ready to be sovereign. Use when the user wants a one-command cloud NanoClawd deploy with on-chain identity from spawn.
Dark Ralph OODA Loop v0 — paper-trading, devnet-only, stdlib-Python agent that runs a safety-contract OODA cycle (Observe→Orient→Decide→Act) for Pump.fun bonding curves. Zero external deps, kill-switch on consecutive losses.
| name | add-github |
| description | Add GitHub channel integration via Chat SDK. PR and issue comment threads as conversations. |
Adds GitHub support via the Chat SDK bridge. The agent participates in PR and issue comment threads.
You need a dedicated GitHub bot account (not your personal account). The adapter uses this account to post replies and filters out its own messages to avoid loops. Create a free GitHub account for your bot (e.g. my-org-bot), then invite it as a collaborator with write access to the repos you want monitored.
NanoClawd doesn't ship channels in trunk. This skill copies the GitHub adapter in from the channels branch.
Skip to Credentials if all of these are already in place:
src/channels/github.ts existssrc/channels/index.ts contains import './github.js';@chat-adapter/github is listed in package.json dependenciesOtherwise continue. Every step below is safe to re-run.
git fetch origin channels
git show origin/channels:src/channels/github.ts > src/channels/github.ts
Append to src/channels/index.ts (skip if the line is already present):
import './github.js';
pnpm install @chat-adapter/github@4.27.0
pnpm run build
Log in as your bot account, then:
On each repo (logged in as the repo owner/admin):
https://your-domain/webhook/github (the shared webhook server, default port 3000)application/jsonopenssl rand -hex 20)Add to .env:
GITHUB_TOKEN=github_pat_...
GITHUB_WEBHOOK_SECRET=your-webhook-secret
GITHUB_BOT_USERNAME=your-bot-username
GITHUB_BOT_USERNAME must match the bot account's GitHub username exactly. This is used for @-mention detection — the agent responds when someone writes @your-bot-username in a PR or issue comment.
Sync to container: mkdir -p data/env && cp .env data/env/env
Ask the user: Is this a private or public repo?
unknown_sender_policy: 'public'. Only collaborators can comment anyway, so it's safe to let all comments through.unknown_sender_policy: 'strict'. Only registered members can trigger the agent, preventing strangers from consuming agent resources. Add trusted collaborators as members (see below).Run /manage-channels to wire the GitHub channel to an agent group, or insert manually:
-- Create messaging group (one per repo)
INSERT INTO messaging_groups (id, channel_type, platform_id, name, is_group, unknown_sender_policy, created_at)
VALUES ('mg-github-myrepo', 'github', 'github:owner/repo', 'owner/repo', 1, '<policy>', datetime('now'));
-- Wire to agent group
INSERT INTO messaging_group_agents (id, messaging_group_id, agent_group_id, trigger_rules, response_scope, session_mode, priority, created_at)
VALUES ('mga-github-myrepo', 'mg-github-myrepo', '<your-agent-group-id>', '', 'all', 'per-thread', 10, datetime('now'));
Replace <policy> with public or strict based on the user's choice above.
When using strict, add each GitHub user who should be able to trigger the agent:
-- Add user (kind = 'github', id = 'github:<numeric-user-id>')
INSERT OR IGNORE INTO users (id, kind, display_name, created_at)
VALUES ('github:<user-id>', 'github', '<username>', datetime('now'));
-- Grant membership to the agent group
INSERT OR IGNORE INTO agent_group_members (user_id, agent_group_id)
VALUES ('github:<user-id>', '<agent-group-id>');
To find a GitHub user's numeric ID: gh api users/<username> --jq .id
Use per-thread session mode so each PR/issue gets its own agent session.
If you're in the middle of /setup, return to the setup flow now.
Otherwise, restart the service (systemctl --user restart nanoclawd or launchctl kickstart -k gui/$(id -u)/com.nanoclawd) to pick up the new channel.
githubgithub:owner/repo (e.g. github:acme/backend). Each PR/issue becomes its own thread automatically.per-thread session mode. Each PR or issue gets its own isolated agent session. Typically wire to a dedicated agent group if the repo contains sensitive code.