ClaudeSuperPower
SubmitLog in

slack-api

Skill

Discover, navigate, and call Slack Web API methods (the family.method endpoints at slack.com/api like chat.postMessage, conversations.history, users.info, views.open). Use this skill whenever the developer asks which Slack API method does something, needs a method's required OAuth scopes or token ty

0Communication

Install

git clone https://github.com/slackapi/slack-mcp-plugin.git ~/.claude/skills/slack-api

What is slack-api?

Discover, navigate, and call Slack Web API methods (the family.method endpoints at slack.com/api like chat.postMessage, conversations.history, users.info, views.open). Use this skill whenever the developer asks which Slack API method does something, needs a method's required OAuth scopes or token type, wants to call or test a Web API method, is handling cursor pagination (next_cursor), hitting rate limits (tier/ratelimited/Retry-After), or debugging API errors like missing_scope, invalid_auth, or channel_not_found. Also trigger when they paste a slack.com/api/ URL or a docs.slack.dev/reference/methods link, or ask how to list/fetch/post/update Slack resources via the API. This skill covers the Web API method layer: finding the right method, reading its contract (scopes, arguments, errors), and calling it over raw HTTP with curl or through a Slack SDK.

What this can do

Capabilities declared in this component's own frontmatter — not inferred.

Inherit all session tools

Declares no tool restrictions — inherits every session tool

~216 tokens of context used while enabled, before you invoke anything

Documentation

README · ~9 min read

Slack Web API

Help the developer discover the right Web API method, read its contract, and call it correctly. Slack exposes hundreds of methods named in family.method dot notation (e.g. chat.postMessage, conversations.history) at https://slack.com/api/<method>. Every method's doc page follows a fixed URL pattern, so the contract for any method is always one fetch away.

If $0 is provided, it is either a full method.name (jump to Step 2 to read its contract) or a family name (go to Step 1 and find it in the index).

Critical rules:

  • Verify a method name and its required scopes against its doc page before calling it — never invent method names or guess scopes. Method names use family.method dot notation.
  • Every response has a top-level ok boolean. Always check ok before using the result; on ok: false, read the error string.
  • Method names, scopes, rate tiers, and arguments come from the live doc page (https://docs.slack.dev/reference/methods/<method-lowercased>.md). The docs are the source of truth — discover from the live index, read the contract from the method's own page.

DO NOT rules:

Reviews

Log in to leave a review.

No reviews yet — be the first.

Explore related

Other things in this space — across every part of the ecosystem, not just skills.

Skillssimilar to this one

All skills →

claude-mem

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

88.9K stars

plugin-structure

This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin director

32.8K stars

hook-development

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse,

32.8K stars

Subagents

All subagents →

architecture-critic

Reviews proposed target architectures and transformed code against modern best practice. Adversarial — looks for over-engineering, missed requirements, and simpler alternatives.

32.8K stars

code-architect

Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences

32.8K stars

claude-security

The dedicated Claude Security orchestrator. Hand it an unattended job — "fully scan this repository and patch what you find; I understand it will use a lot of tokens" — and it runs the whole thing itself: capturing the revision, driving the multi-agent scan through the claude-security:scan workflow,

32.8K stars