Ce Slack Research
Pull synthesized Slack threads—decisions, constraints, and team sentiment—into one digest before you scope, plan, or answer stakeholder questions.
Overview
ce-slack-research is an agent skill most often used in Idea (also Build, Operate) that searches Slack and produces a synthesized research digest of decisions, constraints, and discussion arcs—not raw message results.
Install
npx skills add https://github.com/everyinc/compound-engineering-plugin --skill ce-slack-researchWhat is this skill?
- Natural-language or keyword queries with Slack modifiers (channel hints, after: date filters)
- Interpreted research digest with cross-cutting themes—not raw message dumps like find-discussions flows
- Blocking prompt when no topic is given (AskUserQuestion / request_user_input / ask_user by harness)
- Trigger phrases: search slack for, what did we discuss about, slack context for, what does the team think about
Adoption & trust: 1.5k installs on skills.sh; 20.5k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need team decisions and constraints buried in Slack threads, but scrolling channels or raw search hits do not give you an interpreted picture.
Who is it for?
Solo builders on small teams who need interpreted Slack context for a feature, policy, or incident before writing docs or code.
Skip if: Builders who only need verbatim message search without synthesis, or workspaces where Slack is not the system of record.
When should I use this skill?
User says search slack for, what did we discuss about, slack context for, or what does the team think about.
What do I get? / Deliverables
You get a cross-cutting Slack research digest you can paste into specs, retros, or stakeholder updates without manually stitching threads.
- Synthesized Slack research digest with cross-cutting themes
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Organizational memory lives in chat first; this skill’s canonical shelf is early research when you need interpreted context, not raw search hits. Matches discovery and internal research before committing to build or policy changes.
Where it fits
Before picking a monetization angle, digest how the team debated trials in Slack over the last quarter.
Confirm scope boundaries by summarizing constraint threads before prototyping.
Attach a Slack-derived decision log to an implementation plan for your coding agent.
Reconstruct prior incident or rollout discussions when writing a postmortem.
How it compares
Use for interpreted digests; pair with raw Slack discussion finders when you need unfiltered message lists.
Common Questions / FAQ
Who is ce-slack-research for?
Indie and solo builders (and small teams) who ship with agent harnesses and need organizational context from Slack synthesized into one brief.
When should I use ce-slack-research?
During Idea research, Validate scoping, Build PM checkpoints, or Operate retros—whenever you ask what we discussed about X, need slack context for a decision, or want team sentiment before committing.
Is ce-slack-research safe to install?
Review the Security Audits panel on this Prism page for install counts and audit signals; Slack access implies reading workspace messages your token can reach—scope tokens and channels deliberately.
SKILL.md
READMESKILL.md - Ce Slack Research
# /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.