Agent Academy is a free, source-linked library of skills, prompts, MCP servers and bot templates, organised into courses by profession, for people who hand real work to AI agents: 1,467 live resources, each with its original link, license and safety tags.
Skill
slack-search
Original text · EnglishGuidance for effectively searching Slack to find messages, files, channels, and people
Republished in full under its license, with attribution. The source is authoritative.
name: slack-search
description: Guidance for effectively searching Slack to find messages, files, channels, and people
Slack Search
This skill provides guidance for effectively searching Slack to find messages, files, and information.
When to Use
Apply this skill whenever you need to find information in Slack — including when a user asks you to locate messages, conversations, files, or people, or when you need to gather context before answering a question about what's happening in Slack.
Search Tools Overview
Tool
Use When
slack_search_public
Searching public channels only. Does not require user consent.
slack_search_public_and_private
Searching all channels including private, DMs, and group DMs. Requires user consent.
slack_search_channels
Finding channels by name or description.
slack_search_users
Finding people by name, email, or role.
Search Strategy
Start Broad, Then Narrow
Begin with a simple keyword or natural language question.
If too many results, add filters (in:, from:, date ranges).
If too few results, remove filters and try synonyms or related terms.
Choose the Right Search Mode
Natural language questions (e.g., "What is the deadline for project X?") — Best for fuzzy, conceptual searches where you don't know exact keywords.
Keyword search (e.g., project X deadline) — Best for finding specific, exact content.
Use Multiple Searches
Don't rely on a single search. Break complex questions into smaller searches:
Search for the topic first
Then search for specific people's contributions
Then search in specific channels
Search Modifiers Reference
Location Filters
in:channel-name — Search within a specific channel
in:<#C123456> — Search in channel by ID
-in:channel-name — Exclude a channel
in:<@U123456> — Search in DMs with a user
User Filters
from:<@U123456> — Messages from a specific user (by ID)
from:username — Messages from a user (by Slack username)
to:me — Messages sent directly to you
Content Filters
is:thread — Only threaded messages
has:pin — Pinned messages
has:link — Messages containing links
has:file — Messages with file attachments
has::emoji: — Messages with a specific reaction
Date Filters
before:YYYY-MM-DD — Messages before a date
after:YYYY-MM-DD — Messages after a date
on:YYYY-MM-DD — Messages on a specific date
during:month — Messages during a specific month (e.g., during:january)
Text Matching
"exact phrase" — Match an exact phrase
-word — Exclude messages containing a word
wild* — Wildcard matching (minimum 3 characters before *)
File Search
To search for files, use the content_types="files" parameter with type filters:
Use slack_read_thread to get the full thread context for any threaded message.
Use slack_read_channel with oldest/latest timestamps to read surrounding messages for context.
Use slack_read_user_profile to identify who a user is when their ID appears in results.
Common Pitfalls
Boolean operators don't work.AND, OR, NOT are not supported. Use spaces (implicit AND) and - for exclusion.
Parentheses don't work. Don't try to group search terms with ().
Search is not real-time. Very recent messages (last few seconds) may not appear in search results. Use slack_read_channel for the most recent messages.
Private channel access. Use slack_search_public_and_private when you need to include private channels, but note this requires user consent.
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`,…
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar…
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Use after generating code, after accepting AI suggestions, or when reviewing AI-written modules. Also use when code works but feels brittle, when error handling seems thin, when orphaned resources or missing cleanup are suspected, or when the agent claims done but hidden debt may exist. Catches the specific failure patterns AI agents produce that humans would not.