/summarize-channelWhat it tells Claude to do
12 linesThe prompt this command injects, verbatim. Worth reading before you run it.
Given the channel name provided in $ARGUMENTS (strip any leading `#`):
1. Use the `slack_search_channels` tool to find the channel ID for the provided channel name. Strip any leading `#` from the argument before searching.
2. Use the `slack_read_channel` tool to read recent messages from the channel (default limit of 100 messages).
3. For any messages that have threads with replies, use `slack_read_thread` to read the thread contents so the summary captures threaded discussions.
4. Produce a concise summary organized by topic or theme. The summary should include:
- An overview of the main topics discussed
- Key decisions or action items mentioned
- Notable announcements or updates
- Active threads and their conclusions (if any)
5. Keep the summary scannable — use short bullet points grouped by topic. Mention who said what when it's relevant (e.g., decisions, action items).
6. If the channel has very little recent activity, say so and note the last time a message was posted.Shipped by 1 plugin
Installing any of these installs this command.
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
~11 tokens of context used while enabled, before you invoke anything
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 commands.
Commandssimilar to this one
All commands →channel-digest
Get a digest of recent activity across multiple Slack channels
ars-revision
ARS academic-paper `revision` mode — revised draft + R&R responses
migration-status
Parse + summarize the JOB_REPORT.md produced by a prior migration run. Surfaces cell pass/fail/fix counts per task, lists the failing cells, and recommends a next-step skill (fixup-cell, resume, or all-clear).
MCP Servers
All mcp servers →context7
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
60K stars
codebase-memory-mcp
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
36.7K stars
dbhub
Zero-dependency, token-efficient database MCP server for Postgres, MySQL, SQL Server, MariaDB, SQLite.
3.3K stars
Subagents
All subagents →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
agent-sdk-verifier-ts
Use this agent to verify that a TypeScript Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent should be invoked after a TypeScript Agent SDK app has been created or modified.
32.8K stars
comment-analyzer
Use this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. This includes (1) after generating large documentation comments or docstrings, (2) before finalizing a pull request that adds or modifies comments, (3) when reviewing existing comments fo
32.8K stars
Plugins
All plugins →discord
Discord messaging bridge with built-in access control. Manage pairing, allowlists, and policy via /discord:access.
32.9K stars
session-report
Generate an explorable HTML report of Claude Code session usage — tokens, cache efficiency, subagents, skills, and the most expensive prompts — from local ~/.claude/projects transcripts.
32.9K stars
telegram
Telegram messaging bridge with built-in access control. Manage pairing, allowlists, and policy via /telegram:access.
32.9K stars
Skills
All skills →ui-ux-pro-max-skill
An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms
111.3K stars
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
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
Hooks
All hooks →Notification
SessionStart
SessionStart nudge directing the agent to delegate data-engineering tasks to altimate-code via the altimate-code skill. The UserPromptSubmit pre-run hook was removed because it double-invoked altimate-code (once at hook time, once when the model fired the skill), doubling token consumption on the al