OpenParable
Skip to content
← Back to skills

Ticket

Productivity
ticket

Ticket is an Agent Skill for productivity published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Use when a skill needs to persist output as a standardized artifact — research findings, plans, postmortems, reviews, design specs, decisions. Replaces bespoke output directories with a single canonical tk ticket system.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/documents/ticket-cygnusfear-agent-skills/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/ticket, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Ticket — Artifact Creation

All skill output that needs to persist goes into a ticket. No custom directories.

Tag Taxonomy

Every artifact ticket MUST use the appropriate tags:

Artifact typeTagsExample title
Oracle researchresearch, oracle"Oracle: Why API latency spiked"
Delphi investigation (epic)research, delphi"Delphi: Database migration strategy"
Delphi synthesisresearch, delphi-synthesis"Delphi synthesis: Database migration strategy"
Implementation planplan"Plan: Refactor auth middleware"
Architecture decisiondecision"ADR: Use Zustand for state management"
Postmortempostmortem"Postmortem: Agent skipped codebase exploration"
Code reviewreview"Review: PR #42 auth changes"
Design specdesign-spec"Design spec: Dashboard redesign"

Creating Artifact Tickets

Use tk (via todos_oneshot or todos tool):

todos_oneshot(
  title: "Oracle: <topic>",
  description: "<full findings>",
  tags: "research,oracle",
  type: "task"
)

Epics with Subtasks

For multi-part artifacts (e.g. Delphi = N oracles + synthesis):

  1. Create the epic ticket first
  2. Create subtask tickets linked to it
  3. Use teams delegate to run subtasks in parallel
  4. Update the epic with synthesized results
# 1. Epic
todos_oneshot(title: "Delphi: <topic>", tags: "research,delphi", type: "epic")

# 2. Subtasks (one per oracle)
todos_oneshot(title: "Oracle 1: <topic>", tags: "research,oracle", type: "task")
todos_oneshot(title: "Oracle 2: <topic>", tags: "research,oracle", type: "task")
todos_oneshot(title: "Oracle 3: <topic>", tags: "research,oracle", type: "task")

# 3. teams delegate to run in parallel
# 4. Synthesize into epic

Rules

  1. No custom output directories. No .oracle/, .plans/, .design-specs/, docs/postmortems/, docs/research/.
  2. Tags are mandatory. Every artifact ticket uses tags from the taxonomy above.
  3. Titles are descriptive. Prefix with artifact type (Oracle:, Plan:, ADR:, etc.).
  4. Full content in the ticket. The ticket body IS the artifact — not a pointer to a file elsewhere.
  5. Link related tickets. Subtasks link to epics. Plans link to implementation tickets. Postmortems link to the incident tickets.