Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Slack To Ticket

ASecurity

Creates a Linear issue from a pasted Slack thread. Parses the conversation, infers title, priority, category, and description, checks for duplicates, and creates a clean ticket. Use when pasting a Slack thread to turn it into a trackable issue.

4 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgo

Works with

mcp

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add mostafa-drz/claude-skills --skill slack-to-ticket --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Slack To Ticket?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Slack To Ticket
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mostafa-drz-slack-to-ticket/badge)](https://www.skillsdirectory.com/skills/mostafa-drz-slack-to-ticket)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: slack-to-ticket
description: >-
  Creates a Linear issue from a pasted Slack thread. Parses the conversation,
  infers title, priority, category, and description, checks for duplicates, and creates a clean ticket.
  Use when pasting a Slack thread to turn it into a trackable issue.
argument-hint: <paste slack thread here>
disable-model-invocation: true
context: fork
allowed-tools:
  - AskUserQuestion
  - mcp__claude_ai_Linear__create_issue
  - mcp__claude_ai_Linear__list_projects
  - mcp__claude_ai_Linear__list_teams
  - mcp__claude_ai_Linear__list_issues
  - mcp__claude_ai_Linear__list_issue_labels
  - mcp__claude_ai_Linear__list_issue_statuses
metadata:
  trigger: "Pasting a Slack thread to turn it into a trackable issue."
  tags: "slack, linear, productivity"
---

# Slack Thread → Linear Ticket

Creates a structured Linear issue from a pasted Slack conversation.

## Preferences

_Read `~/.claude/skills/slack-to-ticket/preferences.md` using the Read tool. If not found, no preferences are set._

## Command routing

Check `$ARGUMENTS`:

- **`help`** → display help then stop
- **`config`** → interactive setup then stop
- **`reset`** → delete `~/.claude/skills/slack-to-ticket/preferences.md`, confirm, stop
- **anything else** → process as Slack thread

### Help

```
Slack to Ticket — Create a Linear issue from a Slack thread

Usage:
  /slack-to-ticket <paste thread>    Parse and create issue
  /slack-to-ticket config            Set default team, project, preferences
  /slack-to-ticket reset             Clear preferences
  /slack-to-ticket help              This help

What it does:
  1. Parses the thread for topic, urgency, action items
  2. Checks Linear for duplicate issues
  3. Shows inferred fields for review
  4. Asks for team and project
  5. Creates issue with natural description

Current preferences:
  (shown above under Preferences)
```

### Config

Use **`AskUserQuestion`**:

**Q1** — "Default Linear team?" (options from `list_teams`, max 4, + "Ask each time")
**Q2** — "Default project?" (options from `list_projects`, max 4, + "None", + "Ask each time")
**Q3** — "Default priority when no urgency signals?" (Normal (default), Low, Ask each time)

Save to `~/.claude/skills/slack-to-ticket/preferences.md`.

## First-time detection

If no preferences file exists, show:
"First time using /slack-to-ticket? Run `/slack-to-ticket config` to set default team/project, or continue — I'll ask as needed."

Then proceed normally.

## Steps

### 1. Parse the Slack thread

Analyze `$ARGUMENTS` and extract:
- **Topic**: Core subject being discussed
- **Category**: `Bug`, `Feature`, `Improvement`, or `Task`
- **Action items**: Concrete next steps mentioned or implied
- **Participants**: Names/handles of people involved
- **Reporter**: Who started the thread
- **Urgency**: Map signals (urgent, blocking, ASAP, P0, deadlines) to Linear priority: Urgent (1), High (2), Normal (3), Low (4). Default from preferences or Normal (3).

### 2. Fetch Linear context

In parallel:
- **`list_teams`** — get available teams
- **`list_projects`** — get active projects

Then search for duplicates:
- **`list_issues`** — search with keywords from the parsed topic

If duplicate found, warn the user and let them decide.

### 3. Validate labels

Use **`list_issue_labels`** to check if inferred category label exists. Include only if valid match. If no match, omit.

### 4. Present summary and ask questions

Show inferred fields:

```
Inferred from Slack thread:
- Title: {title}
- Category: {category}
- Priority: {priority} ({reason})
- Action items: {count} found
- Participants: {names}
{if duplicate: ⚠️ Possible duplicate: {issue ID} — {title}}
```

Use a **single `AskUserQuestion`** call to ask:
- **Team**: Which team? (use saved default as first option if set, otherwise options from `list_teams`)
- **Project**: Which project? (use saved default if set)
- **Assignee** (only if someone volunteered): Assign to {name}?

Do NOT ask about title, priority, description, or labels — those are inferred.

### 5. Create the issue

Use **`create_issue`** with:
- **title**: Concise, imperative (e.g., "Fix timeout in data pipeline sync")
- **team**: From user's answer
- **project**: From user's answer (omit if "None")
- **priority**: Inferred priority number (1-4)
- **labels**: Validated label (if found)
- **assignee**: From user's answer (if applicable)
- **state**: Find "Todo" state from `list_issue_statuses`. If not found, omit.
- **description**: Natural ticket description (see guidelines below)

#### Description guidelines

Write like a human engineer wrote it:
1. **Why** — What's the problem and why does it matter?
2. **What** — What needs to happen? (action items as checkboxes)
3. **How** — Only if thread contains agreed approach

Rules:
- No "Context (from Slack)" headers or AI framing
- Don't paste the full conversation
- No participant lists or "Reported by" lines
- Concise and scannable
- If Slack thread link provided, add as reference: `_ref: [Slack thread](url)_`

### 6. Report

Show:
- Issue identifier (e.g., `AIS-123`)
- Direct URL to the issue
- Team, project, priority, labels applied

### 7. Learn

If user chose a team/project different from saved preferences, update silently.
Mention: "Noted: you prefer team {X}. Saved for next time."

Attribution

mostafa-drzmostafa-drz
View sourceMore from mostafa-drz →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →