slack-block-kit
Skill60 starsChanged 2 months agoMITView on GitHub
Build or debug Slack Block Kit payloads for messages, modals, App Home, streaming responses, and Work Object unfurls. Use for block layout, elements, or interaction schemas; not plain Slack text formatting alone.
In this repository10 other files it gives its agents.
- bazelSkill
- clean-ddd-hexagonalSkill
- feature-slicingSkill
- mermaid-diagramsSkill
- modern-cssSkill
- modern-javascriptSkill
- postgres-drizzleSkill
- slack-mrkdwnSkill
- teams-adaptive-cardsSkill
- teams-message-formattingSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Use the requested content, interaction, target Slack method/surface, and any existing payload as input.
- Distinctive: line 30
Check surface compatibility: for example, alerts are modal-only and message payloads have different limits from modal/Home views.
- Distinctive: line 31
Keep top-level fallback text semantically aligned with blocks when provided.
- Distinctive: line 37
Use the Slack Block Kit reference and the exact Web API method/SDK schema for current fields and limits that the bundled reference does not …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Slack Block Kit
Construct the requested Slack layout or interaction using the receiving surface's schema. The user's explicit instructions take precedence over this skill's guidelines.
Establish the surface
Use the requested content, interaction, target Slack method/surface, and any existing payload as input. Infer the surface from code when possible; ask if a missing choice changes the payload. Ordinary text replies do not require blocks.
| Work | Reference |
| Message, modal, App Home, or interaction lifecycle | SURFACES.md |
| Block choice, fields, limits, surface compatibility | BLOCKS.md |
| Buttons, inputs, menus, pickers | ELEMENTS.md |
| Text objects, options, confirmation dialogs | COMPOSITION.md |
| Structured rich-text nesting and inline elements | RICH-TEXT.md |
| start/append/stop streaming, chunks, SDK differences | STREAMING.md |
| Entity unfurls, flexpanes, edits, comments | WORK-OBJECTS.md |
| Compact block/element/limit lookup | CHEATSHEET.md |
Load only the relevant reference or section. Payload construction does not require a Slack connection. Use the separately installed slack-mrkdwn skill for detailed text-formatting questions when available; the composition and rich-text references here cover the required object shapes independently.
Preserve the payload contract
- Choose text syntax per field:
mrkdwnuses*bold*and<url|label>;plain_textis literal;markdownblocks use standard Markdown;rich_textuses structured elements. - Check surface compatibility: for example, alerts are modal-only and message payloads have different limits from modal/Home views.
- Keep top-level fallback text semantically aligned with blocks when provided. Screen readers and mobile notifications can depend on it.
- Escape untrusted text for its receiving field. Preserve supplied IDs and URLs; do not fabricate real channel, user, trigger, or entity identifiers.
- A modal needs a live trigger and interaction handling; a static preview does not prove the lifecycle works. Follow the current method/SDK contract when streaming schemas disagree.
Deliver valid JSON or integration code for the requested surface, with necessary fallback text and any unresolved runtime inputs. Verify payload structure and relevant limits; test live delivery only when requested or already authorized. Creating a payload does not itself authorize posting it.
Use the Slack Block Kit reference and the exact Web API method/SDK schema for current fields and limits that the bundled reference does not establish.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

