Install
$ agentstack add skill-kouko-monkey-skills-slack-automate ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
slack-automate
Read-only Slack access via the official Slack MCP server (GA 2026-02). Tool calls return structured JSON — no UI scraping, no locale tables, no browser daemon.
> ⚠️ First-MCP-session verification needed (v0.2.0): the mcp__slack__find_user tool name is assumed against likely Slack MCP exposure but unverified — find-user may fail on first invocation if the actual tool name differs (e.g. mcp__slack__users_lookup). On first run of any protocol, ask Claude Code to list the slack MCP server's exposed tools and reconcile with allowed-tools + protocol bodies. See references/failure-modes.md §"Tool name verification needed" for the one-shot procedure.
Prerequisites
One-time setup:
- Run
/collab-setupand accept the slack row (records intent + verifies prerequisites). - Run
/mcp add slackonce — this triggers Claude Code's native OAuth pre-registration flow against the Slack MCP endpoint. Token refresh is handled automatically thereafter.
If a protocol fails with an auth error, re-run /mcp add slack to refresh the OAuth grant.
Hero protocols
protocols/search-messages.md— full-text search with Slack operators (from:,in:,before:,after:)protocols/channel-read.md— recent N messages in a channel, with thread-reply countprotocols/thread-read.md— parent + all replies for a threadprotocols/find-user.md— search workspace users by name / email / handle (see § failure-modes for tool-name verification status)
Workflow pattern
A typical search-messages invocation:
mcp__slack__search_messages({
"query": "OKR in:#engineering after:2026-05-01",
"count": 20,
"sort": "timestamp"
})
Returns a JSON array of message records. Format per the protocol's ## Output section.
Failure modes
See references/failure-modes.md — OAuth scope, workspace visibility (private vs public channels), rate limits, Real-Time Search API quotas, tool-name verification status.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: kouko
- Source: kouko/monkey-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.