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

Post Ticket Summary

ASecurity

Posts a structured implementation summary comment to a Linear issue — what was built, key decisions, reuse patterns, and how to test. Use after completing work on a ticket to document the implementation for the team.

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

Works with

mcp

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add mostafa-drz/claude-skills --skill post-ticket-summary --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Post Ticket Summary?

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

Security grade badge for Post Ticket Summary
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mostafa-drz-post-ticket-summary/badge)](https://www.skillsdirectory.com/skills/mostafa-drz-post-ticket-summary)

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

Download Zip
Files
SKILL.md
---
name: post-ticket-summary
description: >-
  Posts a structured implementation summary comment to a Linear issue — what was built,
  key decisions, reuse patterns, and how to test. Use after completing work on a ticket
  to document the implementation for the team.
argument-hint: <issue-id> [--preview] [--minimal]
disable-model-invocation: true
allowed-tools:
  - AskUserQuestion
  - Bash
  - Read
  - Glob
  - Grep
  - mcp__claude_ai_Linear__get_issue
  - mcp__claude_ai_Linear__list_comments
  - mcp__claude_ai_Linear__create_comment
  - mcp__claude_ai_Linear__get_project
metadata:
  trigger: "After completing work on a ticket to document the implementation for the team."
  tags: "linear, documentation, communication"
---

# Post Ticket Summary

Add a structured implementation summary comment to a Linear issue after completing work.

## Preferences

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

## Context

_On startup, use Bash to detect: current git branch, recent commits (`git log --oneline -20`), and repo name (`gh repo view --json nameWithOwner -q .nameWithOwner`). Skip any that fail._

## Command routing

Check `$ARGUMENTS`:

- **`help`** → display help then stop
- **`config`** → interactive setup then stop
- **`reset`** → delete `~/.claude/skills/post-ticket-summary/preferences.md`, confirm, stop
- **`--preview <issue-id>`** → show comment without posting then stop
- **`--minimal <issue-id>`** → use minimal template
- **anything else** → post summary

### Help

```
Post Summary — Document implementation on a Linear issue

Usage:
  /post-ticket-summary <issue-id>               Post full summary
  /post-ticket-summary --preview <issue-id>     Show without posting
  /post-ticket-summary --minimal <issue-id>     Short summary (skip architecture/reuse)
  /post-ticket-summary config                   Set template preferences
  /post-ticket-summary reset                    Clear preferences
  /post-ticket-summary help                     This help

Examples:
  /post-ticket-summary AIS-810
  /post-ticket-summary --preview AIS-810
  /post-ticket-summary --minimal AIS-810

What it does:
  1. Reads the Linear issue and codebase
  2. Analyzes recent commits and changed files
  3. Builds structured summary comment
  4. Posts to the Linear issue

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

### Config

Use **`AskUserQuestion`**:

**Q1** — "Default template?" (full (default), minimal)
**Q2** — "Which sections to include?" (multiSelect: true)
- Implementation summary
- Key decisions / architecture
- What was reused
- How to test
- Notes

**Q3** — "Auto-detect issue from branch?" (Yes (default), No — always ask)

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

## First-time detection

If no preferences file exists, show:
"First time using /post-ticket-summary? Run `/post-ticket-summary config` to customize template sections, or continue with full template."

Then proceed.

## Steps

### 1. Resolve issue

- If issue ID provided in `$ARGUMENTS`, use it
- If no ID and auto-detect is on, extract from branch name (pattern: `user/ais-NNN-*`)
- If still no ID, ask via `AskUserQuestion`

Fetch the issue: title, description, project, status.

### 2. Check for existing summary

Fetch comments on the issue. If an implementation summary comment already exists, ask:
"An implementation summary already exists. Replace it, or skip?"

### 3. Gather implementation details

**From the codebase:**
- Recent commits on current branch (pre-injected)
- Key files changed: `git diff main...HEAD --stat` (or appropriate base)
- Read the main changed files to understand what was built

**From project context:**
- CLAUDE.md for conventions
- README.md for project overview

**Ask user** (optional — use `AskUserQuestion` with all optional):
- Loom URL or recording link (or placeholder)
- Live/staging URL for testing
- Any additional context worth documenting

If user says "skip", use placeholders.

### 4. Build comment

**Full template:**

```markdown
## Implementation Summary

{1-2 paragraphs: what was built and the product goal. Focus on business value.}

### What Was Reused

| Component | Source | Adaptation |
|-----------|--------|------------|
| {component} | {origin} | {what changed} |

---

## How to Test

**Branch:** `{branch}`
**Live URL:** {url or N/A}

### Steps
1. {step}
2. {step}
3. {step}

---

## Features

### 1. {Feature Name}

{2-3 sentences from user perspective. What they see, what they can do, business value.}

### 2. {Feature Name}

{Same structure}

---

## Key Decisions

| Decision | Rationale |
|----------|-----------|
| {decision} | {why} |

---

## Notes

- {Additional context}
```

**Minimal template:**

```markdown
## Implementation Summary

{1-2 paragraphs}

## How to Test

**Branch:** `{branch}`

1. {step}
2. {step}

## Notes

- {anything important}
```

Apply section toggles from preferences.

### Content guidelines

- **Summary**: Lead with the problem, then what the implementation does.
- **Features**: User perspective — what they see and do. No file paths.
- **Key Decisions**: Focus on the "why" behind non-obvious choices.
- **Reuse**: Show what was leveraged vs built new.

### 5. Post or preview

If `--preview`: display the comment and stop.

Otherwise: post via `create_comment`.

### 6. Report

```
Posted implementation summary to {issue-id}.

Sections: {list of included sections}

Next steps:
  1. Record Loom and update the link
  2. Add screenshots if relevant
  3. Replace any [PLACEHOLDER] markers
```

### 7. Learn

If user removes sections consistently, update preferences.
If user adds custom sections, note the pattern.

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 →