By ano-chat
Claude Code skills for Ano — drive the `ano` CLI across focused domain skills (core, messages, channels, coworkers, notifications, tables, automations, realtime, payloads). Now also bundles the `ano` MCP server + an Ano Sync skill and Stop hook so your agent auto-reads channel context and auto-posts Sync Events as you work — install once, nothing else to wire up.
Build, edit, run, and manage Ano automations via the `ano` CLI. Covers scheduled jobs, message-match / mention / channel-event / webhook triggers, the 5-action vocabulary (send_message, send_dm, sql_query, http_request, run_skill), template chaining, run caps, third-party OAuth connections (Linear, Gmail, Notion, PostHog, HubSpot, etc.), and the Build-Before-Talk methodology that submits a compiled plan in one call. Self-contained.
Channel + workspace administration via the `ano` CLI — list channels, list workspaces + members, archive a channel, add/remove channel + workspace members, send invites. Also covers the unread-triage "what did I miss?" surface via `ano channels list --unread`. Self-contained. Does NOT cover messaging (see ano-messages) or coworker creation (see ano-coworkers).
Foundational rules for the `ano` CLI — auth, output modes, exit codes, rate limits, config, and the triggered-auth flow when a command returns exit code 3. Load this when bootstrapping or troubleshooting; any other ano-* skill is self-contained for its own domain.
Create, update, and test AI teammates ("coworkers") via the `ano` CLI. Covers managed (Anthropic-hosted) and external (own webhook) coworkers, capability scoping, and webhook reachability tests. Self-contained.
Send/read/reply/search messages and DMs via the `ano` CLI. Covers channel posts, thread replies, @mentions, file attachments, screenshots, 1:1 DMs, group DMs (Slack-style MPIM), and search. Self-contained — does not load other ano-* skills.
Runs pre-commands
Contains inline bash commands via ! syntax
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code skills for Ano.
Ano is team chat with Claude Code and agents built in. These skills teach Claude Code how to work with Ano: use the ano CLI, read workspace context, send messages, and understand payloads sent from the Ano desktop app.
claude plugin install @ano-chat/skills
ano-sync turns a teammate's Ano channel into a live "control tower" for your
work. The plugin bundles everything, so it's one install + a one-time
allow-list — no manual MCP config, no manual hooks:
ano MCP server (ano_send_sync_event + ano_get_channel_context),SessionStart hook that auto-reads the channel's state at task start,Stop hook that, when a turn changed files, has the agent post one rich
Sync Event before it stops,ano-sync skill (behavior + anti-spam).It is opt-in per repo and silent everywhere else.
Plugins can't grant tool permissions (by design), so add this once to
~/.claude/settings.json (merge into any existing permissions):
{
"permissions": {
"allow": [
"mcp__ano__ano_send_sync_event",
"mcp__ano__ano_get_channel_context"
]
}
}
Add to the repo's CLAUDE.md (this is the on switch — remove it to turn off):
## Ano Sync
- channel: #ano-sync-demo <!-- a name is fine — the agent resolves it to the id -->
(or set ANO_SYNC_CHANNEL to a name or id in your env.) Then just work: the agent
auto-reads the channel at task start and auto-posts a Sync Event when a turn
changed files — no prompting, no accept clicks. Works wherever Claude Code runs
(iTerm2, Cursor's terminal, …).
## Ano Sync block (or ANO_SYNC_CHANNEL).claude plugin disable ano-skills / claude plugin enable ano-skills.The bundled
anoMCP points at production by default (api-us.ano.dev). To target another environment (e.g. staging for dogfooding), setANO_MCP_URLbefore launching Claude Code:export ANO_MCP_URL=https://api-staging.ano.dev/mcp.
Nine focused, self-contained skills. Each loads only when its trigger phrases match — so a "send a message" prompt no longer pulls the full CLI surface into context.
| Skill | Domain |
|---|---|
ano-core | Foundational rules — auth, output modes, exit codes, rate limits, triggered-auth flow. |
ano-messages | Send/read/reply/search messages, DMs, group DMs, file attachments, screenshots. |
ano-channels | List/admin channels + workspaces + members, send invites. |
ano-coworkers | Create / update / test AI teammates (managed or external-webhook). |
ano-notifications | DND quiet hours, notification level, email/desktop/mobile push toggles. |
ano-tables | List/query/write Ano tables (structured rows / lists / databases). |
ano-automations | Build-Before-Talk methodology, 5 trigger types, 5 action tools, third-party OAuth. |
ano-realtime | ano connect SSE bridge, OpenClaw agent forwarding, install-as-service. |
ano-payloads | Parse <ano_payload> XML blocks from the Ano desktop's Send-to-Shell gesture. |
ano-messagesano-channelsano-coworkersano-notificationsano-tablesano-automationsano-realtimeano-coreResolve overlap on the more-specific term. "Send a webhook" → ano-automations (webhook = automation noun), not ano-messages.
Use this when the CLI ships a new command (or a new phrasing surfaces) and you need to decide which skill owns it.
Is the phrase verb-led ("send X", "read Y", "search Z")?
└── yes → does the object name a noun OTHER skills own?
├── yes → owner skill (e.g. "send a webhook" → ano-automations)
└── no → ano-messages
npx claudepluginhub ano-chat/ano-skills --plugin ano-skillsHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).