Skip to main content
hc
Submit
skillsSource-backedReview first Safety ✓ Privacy ✓

Claude Code Slack Triage Capability Pack Skill

Expert Claude Code Slack triage capability pack applying documented Slack integration steps to classify delegations, map repositories, gate risky auto-sessions, and draft human-approved replies before Claude Code acts.

by kiannidev·added 2026-06-16·
Claude CodeCodexWindsurfGeminiCursorCLI
HarnessClaude CodeCodexWindsurfGeminiCursorCLI
Level:expertType:capability-packVerified:validated
Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

  • Public Slack threads are not private—never paste secrets into delegations.
  • Auto-started sessions can race on shared branches—prefer worktrees.
  • Customer-facing bot replies require human approval.

Privacy notes

  • Slack threads may contain customer names and incident details.
  • Triage summaries for external channels need redaction.

Prerequisites

  • Claude Slack integration enabled per official Slack documentation.
  • Channel-to-repository mapping and CODEOWNERS rules documented.
  • Policy for which delegations may auto-start Claude Code sessions.

Schema details

Install type
package
Reading time
8 min
Difficulty score
70
Troubleshooting
Yes
Breaking changes
No
Source repository stats
Scope
Source repo
Package metadata
Skill and platform metadata
Skill type
capability-pack
Skill level
expert
Verification
validated
Verified at
2026-06-16
Retrieval sources
https://code.claude.com/docs/en/slackhttps://code.claude.com/docs/en/skillshttps://code.claude.com/docs/en/securityhttps://github.com/anthropics/claude-codehttps://developers.google.com/search/docs/fundamentals/creating-helpful-content
Tested platforms
Claude CodeClaudeCursorGeneric AGENTS
PlatformSupportInstall path
claude-codeNative.claude/skills/<skill-name>/SKILL.md
codexNative.agents/skills/<skill-name>/SKILL.md
windsurfNative.windsurf/skills/<skill-name>/SKILL.md
geminiNative.gemini/skills/<skill-name>/SKILL.md or .agents/skills/<skill-name>/SKILL.md
cursorAdapter.cursor/rules/<skill-name>.mdc
cliManualAGENTS.md or tool-specific context file
Full copyable content
# Trigger
"Apply the Claude Code Slack triage capability pack for this thread."

# Required output
1) Delegation classification and priority
2) Repository and branch routing recommendation
3) Risk flags and approval gates
4) Draft reply for human review
5) Privacy-safe triage summary

About this resource

Knowledge Freshness

Grounded in Claude Code Slack integration documentation verified on 2026-06-16.

Retrieval Sources

Source Verification Notes

Official Slack docs describe connecting Claude Code to Slack workspaces, delegating engineering work from channels, and starting sessions from Slack triggers with team policy considerations.

Scope Note

Community triage workflow skill applying documented Slack integration steps—not an official Anthropic product. Differs from claude-slack-delegation-triage-agent (agent prompt) by providing capability pack matrices and output contracts.

Core Workflow

  1. Classify delegation: bug, feature, question, incident, or out-of-scope.
  2. Map to repository, branch, and owner using channel conventions.
  3. Flag risks: destructive fixes, missing repro, secrets in thread.
  4. Draft reply requesting clarifications or approving session start.
  5. Require human send approval before bot posts or sessions launch.

Capability Scope

  • Slack delegation classification and priority tiers.
  • Repository and branch routing recommendations.
  • Risk flagging before autonomous sessions.
  • Human-approved reply drafting.
  • Privacy-safe triage summaries.

Production Rules

  • Never auto-post customer-facing replies without human approval.
  • Block session start when threads contain secrets or missing reproduction steps.
  • Prefer worktrees when parallel Slack delegations target the same repo.
  • Escalate destructive fix requests to CODEOWNERS in private threads.
  • Redact customer identifiers in cross-channel summaries.

Review Matrix

Delegation type Route Gate
Bug with repro Mapped repo + branch Human approves session
Vague feature ask Request clarification No session until scoped
Incident Private channel + owner No public exploit details
Out of scope Decline politely No session

Output Contract

  1. Classification and priority.
  2. Repo routing recommendation.
  3. Risk flags.
  4. Draft reply.
  5. Privacy-safe summary.

Duplicate Check

Agent prompt covers similar routing; this skill adds structured review matrix and output contract for capability-pack invocation.

Troubleshooting

Issue: Wrong repo routed from channel Fix: Update channel-to-repo map in team docs; confirm thread context links.

Issue: Session started without approval Fix: Tighten policy; require explicit human /approve step in runbook.

Editorial Disclosure

Independent entry by kiannidev from public docs.

#claude-code#slack#triage#delegation#capability-pack

Source citations

Add this badge to your README

Show that Claude Code Slack Triage Capability Pack Skill is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/skills/claude-code-slack-triage-capability-pack.svg)](https://heyclau.de/entry/skills/claude-code-slack-triage-capability-pack)

How it compares

Claude Code Slack Triage Capability Pack Skill side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

FieldClaude Code Slack Triage Capability Pack Skill

Expert Claude Code Slack triage capability pack applying documented Slack integration steps to classify delegations, map repositories, gate risky auto-sessions, and draft human-approved replies before Claude Code acts.

Open dossier 		Claude Agent SDK Session Storage Capability Pack Skill

Expert Claude Agent SDK session storage capability pack for designing, reviewing, and rolling out Agent SDK session storage with source-backed checklists, production rules, and privacy-safe output contracts.

Open dossier 		Claude Code Chrome Browser QA Capability Pack Skill

Expert Claude Code Chrome browser QA capability pack applying documented Claude in Chrome enablement, browser automation boundaries, and web QA checkpoint workflows.

Open dossier 		Claude Code Computer Use GUI QA Capability Pack Skill

Expert Claude Code computer use GUI QA capability pack that applies documented computer-use MCP enablement, per-app session approval, screenshot checkpoints, and macOS permission workflows for native app validation—not an official Anthropic QA product.

Open dossier
Trust
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
Categoryskillsskillsskillsskills
Sourcesource-backedsource-backedsource-backedsource-backed
Authorkiannidevkiannidevkiannidevkiannidev
Added2026-06-162026-06-142026-06-162026-06-16
Platforms
Claude CodeCodexWindsurfGeminiCursorCLI
Claude CodeCodexWindsurfGeminiCursorCLI
Claude CodeCodexWindsurfGeminiCursorCLI
Claude CodeCodexWindsurfGeminiCursorCLI
Source repo————
Safety notes✓Public Slack threads are not private—never paste secrets into delegations. Auto-started sessions can race on shared branches—prefer worktrees. Customer-facing bot replies require human approval.✓This skill plans Agent SDK session storage; it must not execute destructive changes without explicit approval. Browser, computer-use, and remote surfaces can access sensitive UI state; scope tests carefully. MCP and SDK integrations may exfiltrate data if tool scopes are too broad. The public `anthropics/claude-code` repository ships documentation links to code.claude.com for settings, security, and integration surfaces. Scheduled or autonomous workflows compound risk; cap blast radius in staging first.✓Browser automation can access logged-in sessions—use staging accounts only. Claude chooses Chrome before computer use for web tasks when configured. Review permission prompts before approving navigation on sensitive pages.✓Computer use controls real desktop apps with per-app session approval—not sandboxed Bash. Review sentinel warnings before approving Terminal, Finder, or System Settings access. Press Esc or Ctrl+C to stop computer use and release the machine-wide lock immediately. Only one Claude Code session can hold the computer-use lock at a time.
Privacy notes✓Slack threads may contain customer names and incident details. Triage summaries for external channels need redaction.✓Reviews may expose integration tokens, customer metadata, and internal URLs related to Agent SDK session storage. Telemetry and analytics configs can include account emails; redact before sharing externally. Keep troubleshooting logs in internal channels unless explicitly sanitized. Third-party vendors remain outside Anthropic retention policies; document separately.✓Browser QA sends page content to the model—avoid customer PII in test flows. Screenshots and DOM snapshots may include session tokens in dev tools—close extras.✓Screenshots are downscaled before model upload but may still capture sensitive UI content. Your terminal window is excluded from screenshots per official documentation. Redact customer or proprietary UI details before sharing screenshot evidence externally. Other visible apps are hidden while Claude works; still minimize sensitive windows before starting.
Prerequisites
  • Claude Slack integration enabled per official Slack documentation.
  • Channel-to-repository mapping and CODEOWNERS rules documented.
  • Policy for which delegations may auto-start Claude Code sessions.
  • Access to Claude Code or Agent SDK environment where Agent SDK session storage will run.
  • Ability to read project, user, and managed settings relevant to the workflow.
  • Staging repository or sandbox account for safe validation.
  • Platform or security stakeholder available for policy-bound rollouts.
  • Claude in Chrome extension installed per official Chrome documentation.
  • Staging web app URL and test credentials scoped to non-production.
  • Team policy for browser automation on authenticated sessions.
  • Interactive Claude Code session on macOS v2.1.85+ with Pro or Max plan per computer-use docs.
  • computer-use MCP server enabled through /mcp for the project.
  • macOS Accessibility and Screen Recording permissions granted when prompted.
  • Disposable QA target app or simulator without live customer data on screen.
Install————
Config————
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.