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

Ticket

ASecurity

Write or draft a minimal tracker ticket: a type/parent line, a terse "<Area>:" title, and 2 to 4 bullets of what should change and why in product language, and nothing else (no headings, no acceptance criteria, no Out-of-scope block, no verification gate). Project tokens read from .claude/harness/profile.md. Use when drafting any ticket or backlog markdown.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgobashgit

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add waqas1412/claude-harness --skill ticket --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ticket?

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

Security grade badge for Ticket
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/waqas1412-ticket/badge)](https://www.skillsdirectory.com/skills/waqas1412-ticket)

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

Download Zip
Files
SKILL.md
---
name: ticket
description: Write or draft a minimal tracker ticket: a type/parent line, a terse "<Area>:" title, and 2 to 4 bullets of what should change and why in product language, and nothing else (no headings, no acceptance criteria, no Out-of-scope block, no verification gate). Project tokens read from .claude/harness/profile.md. Use when drafting any ticket or backlog markdown.
argument-hint: "[bug | story | refactor]"
allowed-tools: Read, Grep, Glob, Bash
---

# Tracker ticket (minimal, profile-driven)

First, load `.claude/harness/profile.md` for this project's tokens (`TICKET_PREFIX`, `TRACKER`,
`TRACKER_BROWSE_URL`). If no profile exists, infer from the repo (run `/harness-init`) and proceed.
Ticket keys use `TICKET_PREFIX` (e.g. `PROJ-1234`); if the project has no tracker, write the ticket as
a backlog markdown file and link a GitHub issue instead.

## Body
A ticket is a type/parent line, a terse `<Area>: <imperative>` title, and 2 to 4 bullets (3 is
typical) of what should change and why. Nothing else: no section headings, no user-story formula, no
acceptance criteria, no Out-of-scope block, no implementation notes, no verification gate.

Write it in product language a non-engineer can act on: name the surface, the wrong behavior, and the
wanted behavior. No identifiers, file paths, function names, formulas, library names, or migration
numbers; those live in the PR and the code. When the work came from someone's report, close with
`Reported by <name> in [#channel](<url>).`

A ticket states only what is true now. Rewriting a stale or wrong ticket means replacing the text, not
appending a correction: carry no history of its own earlier versions and no "previously we thought".

The exact template, the Definition of Ready, and the deliberately-skipped list live in
`references/ticket-templates.md` (in this skill's directory). Read that file when actually drafting
and fill it from the profile tokens.

One template covers every type. The distinction lives in the type field and the title: a bug names the
reproduction and the wrong behavior in its prose, a refactor says in its prose that it is
behavior-preserving.

Verification is unchanged: when the work is done, lint, build, and change-scoped tests still run fresh
and are reported in chat. They are just not restated in the ticket.

## Composes with (does not override)
Avoid-em-dash rule; characterization-tests-first (still how a refactor is executed, just not spelled
out in the ticket); verify-before-git-ops.

## Gotchas
- No `.claude/harness/profile.md`: drafting against an assumed tracker prefix instead of falling back to a backlog markdown file plus a linked GitHub issue when no tracker is configured.
- Re-adding the old `## Acceptance criteria` / `## Out-of-scope` / `## Verification gate` headings out of habit. The body carries no headings at all now.
- Treating the dropped verification gate as permission to skip verification when the ticket is implemented.
- Padding the summary into a file-by-file implementation plan. It states what should change and why, and stops.
- Letting engineering vocabulary into the body: identifiers, file paths, formulas, or library names make it unreadable for the reporter and the product side. Describe the surface and the behavior instead.
- Appending a correction when a ticket turns out stale or wrong, or narrating what the ticket used to say. Replace the text with what is true now.
- Losing the reporter and the source thread when the ticket came from a colleague's report.

Attribution

waqas1412waqas1412
View sourceMore from waqas1412 →
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 →