block-kit skill
Use proactively for structured or interactive Slack replies, and when asked to author or validate native Slack Block Kit JSON.
Is the block-kit skill safe?
Clean: nothing in its files matched our rules. We read 3 files in the folder on 2026-10-25.
No findings.
Install the block-kit skill
A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.
git clone --depth 1 https://github.com/openclaw/openclaw.git /tmp/openclaw mkdir -p ~/.claude/skills cp -r /tmp/openclaw/extensions/slack/skills/block-kit ~/.claude/skills/block-kit
In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub
The instructions your agent would load
SKILL.md as published, without the frontmatter. Read it on GitHub
Slack Block Kit
Make useful Slack replies feel native. When structure or one-click follow-up improves the outcome, send a rich message without waiting for the user to ask for Block Kit.
Choose the surface
Use a presentation when the reply has at least one of these shapes:
- a decision, confirmation, or next action that belongs on buttons or a select
- a status, comparison, report, or plan that scans better as titled sections, a table, or a chart
- important context that should be visually separated from the primary result
Use plain text for short answers and casual conversation where structure adds no value.
Send the result
For a reply in Slack, call the message tool with action: "send" and a portable presentation. The Slack plugin renders it as native Block Kit. Use the exact schema exposed by the current tool; supported block types can include text, context, divider, buttons, select, chart, and table.
- Put the outcome first. Keep titles, labels, and context concise.
- Give interactive controls real follow-up semantics. Use typed callback actions for conversational choices and url for an external destination. Do not use generic command actions for Slack controls; Slack renders them as text fallback rather than clickable controls.
- Include a useful message fallback that preserves the meaning without the rich layout.
- After the visible send succeeds, do not repeat the same content in the final response.
A control is complete only when its value is self-contained enough for the next agent turn to understand and act on. When an interaction returns, acknowledge the choice visibly and continue the requested workflow.
Native Block Kit authoring
When the user is building a Slack app or explicitly requests raw Block Kit JSON, read the adapted official Block Kit guide in full. For common message, modal, and App Home layouts, also read the official patterns.
Follow the adapted guide's live-documentation and blocks.validate workflow for native JSON. Do not pass native Slack blocks to OpenClaw's presentation field; the plugin owns that conversion.
More skills from openclaw/openclaw
- A1passwordSet up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.
- Aacp-routerRoute plain-language requests for Claude Code, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Grok Build, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or explicit ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). For coding-agent thread requests, read this skill first, then use only `sessions_spawn` for thread creation. Codex chat binding defaults to the native Codex app-server plugin unless ACP is explicit or background spawn needs ACP.
- Aadd-model-providerAdd and live-prove a model provider with non-interactive config one-liners, without exposing credentials.
- Aagent-transcriptRequested GitHub PR/issue agent transcripts: redact, trim, preview, and insert safely.
- Aapple-notesCreate, view, edit, delete, search, move, or export Apple Notes via the memo CLI on macOS.
- Aapple-remindersList, add, edit, complete, or delete Apple Reminders and reminder lists via remindctl.
- Aauto-qaRun OpenClaw-wide autonomous QA and live/stress campaigns across independent subsystem lanes, with verified fixes and a resumable evidence report.
- AautoreviewStructured code review through the shared OpenClaw agent-skills installation.
- Abear-notesCreate, search, and manage Bear notes via grizzly CLI.
- AblogwatcherMonitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
- AblucliBluOS CLI (blu) for discovery, playback, grouping, and volume.
- Abrowser-automationUse when controlling web pages with the OpenClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale refs/timeouts.