ce-slack-research
everyinc/compound-engineering-plugin
Search Slack for synthesized organizational context—decisions, constraints, and discussion arcs—not just raw messages.
What is ce-slack-research?
Searches Slack for interpreted organizational knowledge and produces a research digest with cross-cutting analysis. Use when you need to understand team decisions, constraints, and discussion patterns around a topic, rather than just finding individual messages.
- Searches Slack using keywords, natural language questions, or Slack modifiers (channel hints, date filters)
- Synthesizes raw messages into interpreted findings organized by topic
- Surfaces cross-cutting patterns and themes across multiple discussions
- Assesses research value (high/moderate/low/none) with justification
- Returns workspace identifier and source channels with dates
How to install ce-slack-research
npx skills add https://github.com/everyinc/compound-engineering-plugin --skill ce-slack-researchHow to use ce-slack-research
- 1.Call `/ce-slack-research [topic or question]` with a keyword, question, or Slack search modifiers
- 2.If no argument provided, respond to the blocking question prompt with your research topic
- 3.Wait for the agent to execute Slack search, read threads, and synthesize findings
- 4.Review the returned digest including research value assessment, organized findings, and cross-cutting analysis
Use cases
- Understanding team decisions and constraints around a feature or initiative
- Researching what the team discussed about a topic over time
- Finding organizational context before making a proposal or decision
- Identifying patterns in team thinking across multiple channels and discussions
- Gathering background on a project or problem before starting work
- Product managers gathering context for decisions
- Engineers researching team constraints and prior discussions
- Project leads understanding organizational knowledge
- Anyone needing synthesized team perspective rather than raw messages
ce-slack-research FAQ
ce-slack-research synthesizes messages into interpreted organizational context with cross-cutting analysis, while slack:find-discussions returns raw message results without synthesis.
Keywords, natural language questions, and Slack search modifiers like `in:#channel` for channel hints and `after:YYYY-MM-DD` for date filters.
The agent will report if Slack MCP is not connected or authentication has expired. No alternative research methods are attempted.
Yes, use the `in:#channel-name` modifier in your search query to limit results to specific channels.
Full instructions (SKILL.md)
Source of truth, from everyinc/compound-engineering-plugin.
name: ce-slack-research description: "Search Slack for interpreted organizational context -- decisions, constraints, and discussion arcs -- and produce a synthesized research digest with cross-cutting analysis. Use when the user says 'search slack for', 'what did we discuss about', 'slack context for', or 'what does the team think about'. Differs from slack:find-discussions, which returns raw message results without synthesis."
/ce-slack-research
Search Slack for organizational context and receive an interpreted research digest.
Usage
/ce-slack-research [topic or question]
/ce-slack-research
Examples
/ce-slack-research free trial
/ce-slack-research What did we say about free trial recently?
/ce-slack-research free trial in #proj-reverse-trial
/ce-slack-research onboarding flow after:2026-03-01
The input can be a keyword, a natural language question, or include Slack search modifiers like channel hints (in:#channel) and date filters (after:YYYY-MM-DD). The agent extracts the topic and formulates searches from whatever form the input takes.
Execution
If no argument is provided, ask what topic to research. Use the platform's blocking question tool: AskUserQuestion in Claude Code (call ToolSearch with select:AskUserQuestion first if its schema isn't loaded), request_user_input in Codex, ask_user in Gemini, ask_user in Pi (requires the pi-ask-user extension). Fall back to asking in plain text only when no blocking tool exists in the harness or the call errors (e.g., Codex edit modes) — not because a schema load is required. Never silently skip the question.
Dispatch ce-slack-researcher with the user's topic as the task prompt. Omit the mode parameter so the user's configured permission settings apply.
The agent handles everything from here -- Slack MCP discovery, search execution, thread reads, and synthesis. It returns a digest with:
- Workspace identifier so the user can verify the correct Slack instance was searched
- Research-value assessment (high / moderate / low / none) with justification
- Findings organized by topic with source channels and dates
- Cross-cutting analysis surfacing patterns across findings
If the agent reports that Slack is unavailable (MCP not connected or auth expired), relay the message to the user. Do not attempt alternative research methods.
Related skills
More from everyinc/compound-engineering-plugin and the wider catalog.
ce-strategy
Create and maintain STRATEGY.md as a durable anchor for product direction and team alignment.
ce-test-browser
Run end-to-end browser tests on pages affected by your PR or branch changes.
ce-test-xcode
Build, install, and test iOS apps on simulator with XcodeBuildMCP integration.
ce-update
Check if compound-engineering plugin is up to date and recommend updates.
ce-work
Execute implementation plans or work prompts end-to-end with systematic quality.
ce-work-beta
Execute work plans with optional Codex delegation for systematic feature delivery.