Slack
huangruiteng/CS-Notes
A skill your agent uses when you need to control Slack from Clawdbot via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.
Extends a Slack-connected NanoClaw agent so it can create new agents that each appear in Slack as their own bot, with an operator DM and a shared three-way room.
$ npx skills add nanocoai/nanoclaw --skill slack-agent-flow -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nanocoai/nanoclaw slack-agent-flow --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/nanocoai/nanoclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/slack-agent-flow .claude/skills/slack-agent-flow && 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 "slack-agent-flow" agent skill from https://github.com/nanocoai/nanoclaw/tree/main/.claude/skills/slack-agent-flow into .claude/skills/slack-agent-flow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "slack-agent-flow", 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/nanocoai/nanoclaw/tree/main/.claude/skills/slack-agent-flowType 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 nanocoai/nanoclaw --skill slack-agent-flow -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nanocoai/nanoclaw slack-agent-flow --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nanocoai/nanoclaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/slack-agent-flow .agents/skills/slack-agent-flow && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "slack-agent-flow" agent skill from https://github.com/nanocoai/nanoclaw/tree/main/.claude/skills/slack-agent-flow into .agents/skills/slack-agent-flow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "slack-agent-flow", 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 nanocoai/nanoclaw --skill slack-agent-flow -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nanocoai/nanoclaw slack-agent-flow --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nanocoai/nanoclaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/slack-agent-flow .cursor/skills/slack-agent-flow && 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 "slack-agent-flow" agent skill from https://github.com/nanocoai/nanoclaw/tree/main/.claude/skills/slack-agent-flow into .cursor/skills/slack-agent-flow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "slack-agent-flow", 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/nanocoai/nanoclaw.git --path .claude/skills/slack-agent-flow--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 nanocoai/nanoclaw --skill slack-agent-flow -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nanocoai/nanoclaw slack-agent-flow --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nanocoai/nanoclaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/slack-agent-flow .gemini/skills/slack-agent-flow && 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 "slack-agent-flow" agent skill from https://github.com/nanocoai/nanoclaw/tree/main/.claude/skills/slack-agent-flow into .gemini/skills/slack-agent-flow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "slack-agent-flow", 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 nanocoai/nanoclaw slack-agent-flowInstalls 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 nanocoai/nanoclaw --skill slack-agent-flow -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nanocoai/nanoclaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/slack-agent-flow .github/skills/slack-agent-flow && 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 "slack-agent-flow" agent skill from https://github.com/nanocoai/nanoclaw/tree/main/.claude/skills/slack-agent-flow into .github/skills/slack-agent-flow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "slack-agent-flow", 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 nanocoai/nanoclaw --skill slack-agent-flow -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nanocoai/nanoclaw slack-agent-flow --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nanocoai/nanoclaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/slack-agent-flow .opencode/skills/slack-agent-flow && 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 "slack-agent-flow" agent skill from https://github.com/nanocoai/nanoclaw/tree/main/.claude/skills/slack-agent-flow into .opencode/skills/slack-agent-flow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "slack-agent-flow", 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.
slack-agent-flowExtends a Slack-connected NanoClaw agent so it can create new agents that each appear in Slack as their own bot, with an operator DM and a shared three-way room.
A user asks an existing agent to create one called Research, and the host provisions a Slack app for it through a managed broker or a workspace manager token, registers it as its own instance and starts the adapter without restarting the host. It then opens a DM between the new bot and the operator, plus a three-way group DM with the operator and both bots, registered as an agent-to-agent room.
The flow adds two agent-facing actions, create_room for one room with several agents and add_to_room to grow a room by one, and extends create_agent with purpose, allow_guests and room parameters. Sessions on other channels behave as before. Prerequisites are add-slack, slack-a2a-rooms, a provisioning credential in .env (NANOCLAW_INSTALL_TOKEN or SLACK_MANAGER_TOKEN) and at least one Slack owner or admin in user_roles.
9 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 66f0823. It shows what the files ask for, not the result of running them.
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.
Ships 1 file in scripts/ (TypeScript, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
bashpnpmFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
NANOCLAW_INSTALL_TOKENSLACK_MANAGER_TOKENFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Slack Agent Creation Flow loads about 4.2k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 1,718 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.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
3. **A provisioning credential in `.env`** — `NANOCLAW_INSTALL_TOKEN` (managed`SLACK_INSTALL_URL_<NAME>` stay in `.env`, and asking the same agent for theThe a2a room allowlist is re-read from `.env` on aidempotently (tokens are reused from `.env`, rows are get-before-create,, and `SLACK_A2A_ROOMS` entries stay in `.env`;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); the scripts in this folder are not scanned.
The full file from nanocoai/nanoclaw at commit 66f0823, republished under its MIT licence (© nanocoai). 1,718 words, ~4,217 tokens.
.claude/skills/slack-agent-flow/SKILL.md (or your agent's skills folder). This skill also uses 23 other files; get the full folder from GitHub.Composes the Slack extension skills into one conversational flow: a user tells
an existing Slack-wired agent "create an agent called Research", and the new
agent doesn't just exist as a send_message destination — it arrives in Slack
as its own bot. The host provisions a Slack app for it (managed broker, or
a workspace manager token), registers it as a slack-<name> instance,
hot-starts the adapter in the running host, opens a DM between the new bot and
the operator, opens a three-way MPIM (operator + originating bot + new bot)
registered as an agent-to-agent room, and wires everything so both agents hear
the room. The flow also adds two agent-facing room actions — create_room
(one shared room with N agents at once, the team primitive) and add_to_room
(grow a room by one agent) — and extends the base create_agent tool with the
flow's purpose / allow_guests / room parameters. Non-Slack sessions are
untouched: create_agent from any other channel behaves exactly as upstream.
Canonical home. This directory on main is the skill's canonical source —
the setup wizard and any direct apply read it from the checkout. The copy on
the channels branch is a compatibility mirror for older checkouts whose
setup fetches companions from there; edits land here, never there. The
payload the Apply steps fetch with from-branch:channels stays on the
channels branch, exactly like /add-slack's own.
All prose below assumes these are already in place, in this order:
add-slack — the Slack channel install (src/channels/slack.ts and
the shared channel-layer lib src/channels/slack-lib.ts present, with
slack.ts exporting its SLACK_DEFAULTS declaration and the
multi-instance factory slackInstanceBridgeFactory — the adapter owns
SLACK_INSTANCES registration natively, and the flow writes each new
agent's tokens under that env-key scheme).slack-a2a-rooms — the bot-sender room policy
(src/channels/slack-a2a.ts present), so shared rooms admit the sibling
bots' posts..env — NANOCLAW_INSTALL_TOKEN (managed
broker) or SLACK_MANAGER_TOKEN (direct workspace-level app creation).
Without one, agent creation still works but the Slack leg reports
no-credentials and points at the finish script.user_roles — the flow resolves "the
operator" from the approver chain (scoped admins → global admins → owners)
and needs a slack:U… identity there to open the DM and the room.The flow imports the skill-installed Slack channel modules; verify they are in
the tree before copying anything. If slack-lib.ts, the SLACK_DEFAULTS
export, or the slackInstanceBridgeFactory export is missing, the installed
Slack channel payload predates this flow — re-apply the two skills above (or
/update-skills) first:
test -f src/channels/slack.ts && test -f src/channels/slack-lib.ts && test -f src/channels/slack-a2a.ts && grep -q "export const SLACK_DEFAULTS" src/channels/slack.ts && grep -q "export function slackInstanceBridgeFactory" src/channels/slack.tsEverything this flow plugs into is standard trunk API — the adapter hot-start
entry, the delivery batch preview, the mailbox delivery/session helpers, the
create-agent notify option, the decline-and-notify overrides, the container
tool-extension hook, and the setup wizard's channel registries. This is a
trunk version requirement, not an edit: if the check below fails, the
NanoClaw trunk is too old for this skill — bring the install up to date
(/update-nanoclaw) instead of patching any of these files by hand:
grep -q "export async function startChannelAdapter" src/channels/channel-registry.ts && grep -q "export function registerDeliveryBatchPreview" src/delivery.ts && grep -q "session: Session) => Promise<void>" src/delivery.ts && grep -q "trigger?: boolean" src/session-manager.ts && grep -q "findCliResponse" container/agent-runner/src/db/messages-in.ts && grep -q "Promise<number>" container/agent-runner/src/db/messages-out.ts && grep -q "suppressCreatedNotify" src/modules/agent-to-agent/create-agent.ts && grep -q "dedupeKey?: string" src/modules/permissions/sender-approval.ts && grep -q "declineText?: string" src/modules/permissions/sender-approval.ts && grep -q "fyiText?: string" src/modules/permissions/sender-approval.ts && grep -q "export function extendTool" container/agent-runner/src/mcp-tools/server.ts && grep -q "export function registerChannelPreStep" setup/channels/companions.ts && grep -q "instructions.md" src/project-doc-compose.ts && grep -q "await action.decide" src/guard/guard.tsThe last term requires an async-capable guard seam: the flow's create_agent
and room-action guards read container config asynchronously, and on a trunk
whose guard() does not await decide a returned Promise would be treated
as an allow — the check turns that silent fail-open into a fail-fast here.
The agents experience needs more than the base adapter: the room-membership
module (invite-to-room adoption, group-DM fork carry-over, detach on removal,
owner-presence access rule), canvas actions + the container canvas tool +
the canvas-work skill (section-scoped canvas edits/reads via the session's
own bot identity), DM onboarding (get-started prompts, per-thread DM titles),
and their env-file.ts dotenv plumbing. They live on the channels branch;
fetch and copy them into place (overwrite — the branch is canonical):
src/env-file.ts
src/env-file.test.ts
src/modules/slack-room-membership/index.ts
src/modules/slack-room-membership/membership.ts
src/modules/slack-room-membership/membership.test.ts
src/modules/slack-room-membership/env-file.ts
src/modules/slack-room-membership/env-file.test.ts
src/modules/canvas-actions/index.ts
src/modules/canvas-actions/handlers.ts
src/modules/canvas-actions/canvas-api.ts
src/modules/canvas-actions/canvas-actions.test.ts
src/modules/slack-onboarding/index.ts
src/modules/slack-onboarding/onboarding.test.ts
src/modules/slack-onboarding/thread-title.test.ts
container/agent-runner/src/mcp-tools/canvas.ts
container/agent-runner/src/mcp-tools/canvas.instructions.md
container/agent-runner/src/mcp-tools/canvas.test.ts
container/skills/slack-construct/SKILL.md
container/skills/slack-construct/instructions.md
container/skills/canvas-work/SKILL.md
container/skills/welcome/addenda/slack.mdThe welcome addendum rides with the agents feature deliberately: its tour
content describes rooms, canvases, suggested-prompt DMs, and the agents
access model — none of which exist on a base /add-slack install.
Register the three host modules in the modules barrel and the canvas tool in the container tool barrel (each append is skipped if already present; these must precede the flow module's own barrel line, which the fence order here guarantees):
import './slack-room-membership/index.js';
import './canvas-actions/index.js';
import './slack-onboarding/index.js';import './canvas.js';This skill ships its payload alongside this document; copy the files into the
tree at the same relative paths (overwrite; the skill's copies are canonical).
The host module carries the wrapped create_agent handler and the room
actions; the container files carry the room tools, the create_agent
extension, the sibling-agent standing-context skill, and the welcome-tour
addendum. The two mcp-tools/*.instructions.md fragments and the
slack-construct-agents skill's instructions.md are picked up by the
CLAUDE.md compose scan; the welcome addendum is consumed by the host's
channel-matched addenda mechanism (inert on hosts that predate it) — so
copying the files is the whole install:
src/modules/slack-agent-flow/types.ts
src/modules/slack-agent-flow/env-file.ts
src/modules/slack-agent-flow/provision.ts
src/modules/slack-agent-flow/slack-deps.ts
src/modules/slack-agent-flow/orchestrate.ts
src/modules/slack-agent-flow/guard.ts
src/modules/slack-agent-flow/room-actions.ts
src/modules/slack-agent-flow/room-canvas.ts
src/modules/slack-agent-flow/index.ts
src/modules/slack-agent-flow/env-file.test.ts
src/modules/slack-agent-flow/provision.congruence.test.ts
src/modules/slack-agent-flow/provision.prefetch.test.ts
src/modules/slack-agent-flow/orchestrate.test.ts
src/modules/slack-agent-flow/room-actions.test.ts
src/modules/slack-agent-flow/room-canvas.test.ts
scripts/slack-agent-flow-finish.ts
container/agent-runner/src/mcp-tools/rooms.ts
container/agent-runner/src/mcp-tools/rooms.test.ts
container/agent-runner/src/mcp-tools/rooms.instructions.md
container/agent-runner/src/mcp-tools/create-agent-slack.instructions.md
container/skills/slack-construct-agents/SKILL.md
container/skills/slack-construct-agents/instructions.md
container/skills/welcome/addenda/teams-tour.mdAppend the self-registration import to the module barrel (skipped if the line
is already present). It must evaluate after the agent-to-agent module's own
registration, which appending at the end guarantees — the flow's create_agent
handler re-registers over upstream's:
import './slack-agent-flow/index.js';Append the tool-module import to the container MCP-tools barrel (skipped if
already present). The module registers create_room / add_to_room and
extends the base create_agent tool, so it must evaluate after the base
agents module — import order follows document order, and appending at the end
guarantees it:
import './rooms.js';The build guards every typed call the flow makes into trunk (delivery registration, DB helpers, channel defaults, the shared Slack lib) against drift:
pnpm run buildThe flow's own tests, the shared feature payload's module tests, and the trunk
hot-start seam's test run on the host. The room-tool tests run through the
already-built agent image, so setup does not require Bun on the host; they also
pin the create_agent extension:
pnpm exec vitest run src/modules/slack-agent-flow src/modules/slack-room-membership src/modules/canvas-actions src/modules/slack-onboarding src/env-file.test.ts src/channels/adapter-hot-start.test.tssource "$PWD/setup/lib/install-slug.sh" && "${CONTAINER_RUNTIME:-docker}" run --rm --entrypoint bun --workdir /app --volume "$PWD/container/agent-runner/src:/app/src:ro" "$(container_image_base):latest" test --preload /app/src/modules/index.ts src/mcp-tools/rooms.test.ts src/mcp-tools/canvas.test.tsThe flow module registers at boot, and container mounts are read-only at runtime — restart so the running host picks everything up (new sessions see the container-side files; no image rebuild):
bash setup/lib/restart.shGuard/approval flow is upstream's. The flow re-registers create_agent
with the same guard action and precheck as the agent-to-agent module; only
the hold question changes when the request originates from a Slack session
(it names the Slack provisioning side effects — new app, operator DM,
shared room). The room actions get the same trust split: global cli_scope
groups act directly, everything else holds for the admin chain, and
approved replays re-enter the wrapped handlers automatically.
Expected boot warning. Because the barrel imports the flow module after
the agent-to-agent module, every boot logs
Delivery action handler overwritten for create_agent. That warning is
the intended signal that the wrapper won the registry — its absence means
the barrel line is missing or ordered wrong.
What a successful run does. Provisions (or reuses) the app — agent-mode
by default; allow_guests: true selects the plain, guest-accessible
variant — writes SLACK_BOT_TOKEN_<NAME> / SLACK_APP_TOKEN_<NAME> and
unions the slug into SLACK_INSTANCES, hot-starts slack-<name>, opens
the operator DM and wires it to the new agent group (agent-mode DMs get
thread-per-conversation sessions straight from the channel declaration),
opens the three-way MPIM with the new bot's token, appends the room's
channel id to SLACK_A2A_ROOMS, creates one room messaging group per
instance (both mention-gated), creates the room's canvas-tab contract, then
posts the DM intro and nudges the originating agent to introduce the new
one in the room. The new bot typically answers within ~10 seconds; if it
stays silent for a minute, an operator can run bash setup/lib/restart.sh
as the fallback.
Workspaces that gate installs. Where an admin must approve every app
install, the workspace refuses the automatic one and the managed service
answers with an install link instead of a bot token. The flow does not fall
back to hand-building an app: it posts one line into the conversation the
create came from — as the ORIGINATING bot, since the origin agent's own
reply cannot be delivered while the handler is still running — naming the
link to approve, then polls the service (5s, up to 5 minutes) for the bot
token the completed install releases. On arrival the rest of the flow runs
exactly as if the install had been automatic. On timeout the app parks:
SLACK_APP_TOKEN_<NAME>, SLACK_APP_ID_<NAME> and
SLACK_INSTALL_URL_<NAME> stay in .env, and asking the same agent for the
same name again resumes THAT app — it never provisions a second one.
SLACK_INSTALL_WAIT_MS=0 skips the inline wait for installs that always go
through a slow approval queue; SLACK_INSTALL_POLL_MS moves the cadence.
Teams get one room. create_agent({ ..., room: 'none' }) skips the
shared room; the multi-agent pattern is N such creates followed by ONE
create_room naming all of them. When a batch of creates arrives together,
their avatar generations are prefetched in parallel, so N waits collapse to
roughly one.
A2A cache staleness. The a2a room allowlist is re-read from .env on a
≤30s cache. The room id is appended before any intro is posted, but the
originating agent's own bridge may still miss ingesting the intro inside
that window — harmless; the intro is for the human, and the originating
session is told the room id and wirings directly in its success message.
Failures are resumable. Any Slack-leg failure leaves the agent group
fully working via send_message, reports the exact step that failed, and
names the retry command. The finish script re-runs the whole leg
idempotently (tokens are reused from .env, rows are get-before-create,
intro posts fire only for newly created rows):
pnpm exec tsx scripts/slack-agent-flow-finish.ts --group <newAgentGroupId> --name <slug> --source-group <sourceGroupId> [--origin-instance <key>] [--room none] [--allow-guests] [--restart]It runs outside the host process, so it cannot hot-start the adapter:
--restart runs bash setup/lib/restart.sh for you, otherwise it prints
the restart instruction.
Setup-wizard leg. bash nanoclaw.sh does the whole install by default:
the managed-provisioning pre-step and the companion list (slack-a2a-rooms,
then this skill) register unconditionally at wizard boot
(setup/channels/slack-auto-register.ts → setup/channels/companions.ts),
so the wizard provisions the first app, applies /add-slack, then applies
both feature skills with one deferred restart. A plain-bot install is the
manual choice inside the flow. That leg ships with trunk, and this skill
does not touch it.
Everything the flow creates at runtime is user data, not skill payload: agent
groups, messaging groups, and wirings stay in the central DB; token lines,
SLACK_INSTANCES entries, and SLACK_A2A_ROOMS entries stay in .env;
provisioned Slack apps stay in the workspace. Removal (see REMOVE.md) never
touches any of it — for per-agent teardown of a provisioned bot, follow the
slack-managed-agents skill's teardown section.
© nanocoai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 23 other files (scripts) in .claude/skills/slack-agent-flow of nanocoai/nanoclaw.
Open the folder on GitHubat commit 66f0823
Slack Agent Creation Flow 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 |
|---|---|---|---|---|---|---|
| Slack Agent Creation Flow this skillnanocoai/nanoclaw | 31k | — | ~4.2k | Automated safety check: Notes | MIT | |
| Slackhuangruiteng/CS-Notes | 4k | 10 repos | ~578 | Automated safety check: Pass | MIT | |
| Openloomi Connectorsmelandlabs/openloomi | 1k | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | |
| Use Avibeavibe-bot/avibe | 620 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Agent Deep Linkscomposio-community/awesome-codex-skills | 17k | — | ~513 | Automated safety check: Pass | None | |
| Chat SDKdatabuddy-analytics/Databuddy | 1.2k | — | ~2.6k | Automated safety check: Pass | AGPL-3.0 |
huangruiteng/CS-Notes
A skill your agent uses when you need to control Slack from Clawdbot via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.
melandlabs/openloomi
openloomi Connectors tools - manage the native 7 messaging integrations and pair with the composio skill for the 1000+ apps OAuth layer (Slack, Discord, X, Gmail, Outlook, Google…
avibe-bot/avibe
Safely inspect and modify local Avibe configuration, routing, runtime settings, watches, scheduled tasks, Avibe Cloud remote access, and operational state.
composio-community/awesome-codex-skills
Builds and checks clickable deep links that open a thread, file, folder or settings panel in tools like Codex, Cursor and VS Code, usually for sharing in Slack.
databuddy-analytics/Databuddy
Build multi-platform chat bots with Chat SDK (chat npm package).
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.
nanocoai/nanoclaw
Installs or refreshes Iron Proxy and its Iron Control web console for NanoClaw, with a local Docker setup, database, credentials and a human approval bridge.
nanocoai/nanoclaw
Drives a web browser from the shell with the agent-browser CLI: open pages, read an element snapshot, click and fill by reference, grab text and screenshots.
nanocoai/nanoclaw
Installs or refreshes OneCLI as the gateway provider for NanoClaw, copying the adapter files, registering the provider and running the setup script.
nanocoai/nanoclaw
Guides a conversational migration from an OpenClaw install to NanoClaw v2, carrying over identity, channel credentials, scheduled tasks and workspace files.
nanocoai/nanoclaw
Wires up an additional phone number onto an already-installed Dial channel, so one NanoClaw install answers SMS and AI voice calls on more than one line.
nanocoai/nanoclaw
Adds a persistent wiki knowledge base to a NanoClaw group following Karpathy's LLM Wiki pattern, with folders, a tailored container skill and a CLAUDE.md section.
Works with
Categories
Extends a Slack-connected NanoClaw agent so it can create new agents that each appear in Slack as their own bot, with an operator DM and a shared three-way room. A user asks an existing agent to create one called Research, and the host provisions a Slack app for it through a managed broker or a workspace manager token, registers it as its own instance and starts the adapter without restarting the host. It then opens a DM between the new bot and the operator, plus a three-way group DM with the operator and both bots, registered as an agent-to-agent room.
Slack Agent Creation Flow fits situations like: spinning up a new specialist agent that should appear as its own Slack bot; creating a shared room with several agents at once; adding another agent to an existing agent-to-agent room.
Run `npx skills add nanocoai/nanoclaw --skill slack-agent-flow -a claude-code`. Or copy the skill folder (.claude/skills/slack-agent-flow in nanocoai/nanoclaw) into .claude/skills/slack-agent-flow in your project. Claude Code loads it when a task matches its description.
Run `npx skills add nanocoai/nanoclaw --skill slack-agent-flow -a codex`. Or copy the skill folder (.claude/skills/slack-agent-flow in nanocoai/nanoclaw) into .agents/skills/slack-agent-flow in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nanocoai/nanoclaw --skill slack-agent-flow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/slack-agent-flow, .gemini/skills/slack-agent-flow, .github/skills/slack-agent-flow and .opencode/skills/slack-agent-flow in your project.
Going by SKILL.md and its folder, Slack Agent Creation Flow needs TypeScript for the scripts in its folder, the command-line tools its instructions call (bash and pnpm) and credentials named NANOCLAW_INSTALL_TOKEN and SLACK_MANAGER_TOKEN. Our summary lists: The add-slack and slack-a2a-rooms skills installed; NANOCLAW_INSTALL_TOKEN or SLACK_MANAGER_TOKEN in .env; A Slack owner or admin in user_roles.
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.
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Slack Agent Creation Flow is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.2k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Slack Agent Creation Flow: Slack (huangruiteng/CS-Notes, 4k stars), Openloomi Connectors (melandlabs/openloomi, 1k stars), Use Avibe (avibe-bot/avibe, 620 stars) and Agent Deep Links (composio-community/awesome-codex-skills, 17k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
nanocoai (a GitHub organization) maintains it in nanocoai/nanoclaw, which has 30,897 GitHub stars. The repository holds 59 skills in this directory. The repository was last updated on October 6, 2026.
Source: nanocoai/nanoclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.