agentleFS
ccheneyccheney/robust-skills/skills/slack-block-kit/SKILL.md

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.

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
  1. Distinctive:

    Use the requested content, interaction, target Slack method/surface, and any existing payload as input.

    line 12
  2. Distinctive:

    Check surface compatibility: for example, alerts are modal-only and message payloads have different limits from modal/Home views.

    line 30
  3. Distinctive:

    Keep top-level fallback text semantically aligned with blocks when provided.

    line 31
  4. Distinctive:

    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 …

    line 37

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

WorkReference
Message, modal, App Home, or interaction lifecycleSURFACES.md
Block choice, fields, limits, surface compatibilityBLOCKS.md
Buttons, inputs, menus, pickersELEMENTS.md
Text objects, options, confirmation dialogsCOMPOSITION.md
Structured rich-text nesting and inline elementsRICH-TEXT.md
start/append/stop streaming, chunks, SDK differencesSTREAMING.md
Entity unfurls, flexpanes, edits, commentsWORK-OBJECTS.md
Compact block/element/limit lookupCHEATSHEET.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: mrkdwn uses *bold* and <url|label>; plain_text is literal; markdown blocks use standard Markdown; rich_text uses 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.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.