Ticket Creator
Create GitHub tickets and briefs that capture what needs done, why, and how to measure success.
Installation
- Make sure Claude is on your device and in your terminal.
Skills load from
~/.claude/skills/when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then runclaudein any terminal to verify.One-time setupnpm i -g @anthropic-ai/claude-codeAlready have it? Skip ahead.
- Paste into Claude Code or into your terminal.
This copies the whole skill folder into
~/.claude/skills/create-ticket-greenfield-inc/— the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Works for every skill.What this command does
- Makes a new, empty temporary folder.
- Downloads the skill's folder,
main/src/services/paneChatBundle/skills/create-ticket, fromgithub.com/greenfield-inc/Pane(branchmain), the GitHub repository it's listed from. You get the version that is there now, not a copy we keep. - Copies that folder to
~/.claude/skills/create-ticket-greenfield-inc/. - Deletes the temporary folder.
Installing runs none of the skill's files; it only downloads and copies them. When you later use the skill, Claude follows its SKILL.md and may run scripts that come with it. Read them first.
Faster alternative (instruction-only skills)
Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.
Quick install (SKILL.md only)Sign up to copy - Restart Claude Code.
Quit and reopen Claude Code (or any other agent that loads from
~/.claude/skills/). New skills are picked up on startup. - Just ask Claude.
Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.
Prefer to read the source first? Open on GitHub.
When Claude uses it
Capture work and evolving intent during discussion as one or more GitHub tickets, published briefs, or both. Use for ticket or issue creation, follow-ups, backlog capture, delegation, and revisions as decisions change. Preserve the what, why, outcome, scope, and acceptance criteria.
What this skill does
Create ticket
You are the keeper of intent at delegation. Help the next person understand what should change, why it matters, and what success looks like.
Capture the intent
-
Explore open-ended ideas conversationally: follow the user's questions, investigate facts, and recommend with reasons.
-
Build on settled decisions for clear requests or existing briefs. Focus on remaining gaps, then use the finalization steps below.
-
Read the conversation, issue, and linked briefs; use intent-handoff.md to capture and refine the work.
-
For each key mechanism (a new background job, schema change, infrastructure, or path where the system acts on a user's behalf), record Alternatives considered: the simpler options and doing nothing, why the chosen one wins, and prior art marked verified or unverified, in the frame from
orchestrate-sessions(Presenting decisions). A mechanism never offered as an option is still an open decision: take it tooptionsor the user rather than locking it into the ticket. -
For UI changes, offer a best-effort ui-mockup to clarify the design, and include any approved result in the ticket or brief.
-
Batch independent evidence gathering when useful: repository behavior, external constraints, and related issues/briefs can be read concurrently through tools or available read-only helpers. Follow the active workflow’s model/role requirements, pass the no-archive instruction to helpers, and reconcile results into one brief. Keep dependent decisions, mockup approval, Socrates review, and publication confirmation in their existing order; helpers do not publish competing briefs.
Shape the delegation
- Choose the requested handoff: one or more tickets, published briefs, or both. Keep a coherent outcome together; split independent outcomes, owners, or release timing, and link shared context and dependencies.
- Resolve the repository for GitHub work and inspect related issues or briefs. Reuse the matching artifact for an authorized revision; create follow-ups for distinct work.
- Use a readable, action-oriented title following repository conventions, such as
fix: make refund exports reconcilable. - Apply this skill during discussion when concrete work or changing intent needs capture. Draft within exploratory discussion; save or publish when the request or active workflow authorizes that destination. Use requested or unambiguous assignees, labels, and milestones.
Refine before finalizing
- Open the draft in the requested destination, or as a page in the work's page bundle shown with
runpane panels open --file <path> --source agent --yes, and refine it with the user. - When the user considers it ready, dispatch fresh Socrates with the brief, discussion evidence, and repository access.
- Relay material questions. Update the same brief with answers, decisions, and reasons; record Socrates' verdict against the reviewed version.
- Continue the same Socrates agent through feedback. If resumption fails, disclose the restart and pass the full review record to its replacement. Reuse a verdict while its premise and evidence hold.
- If dispatch is unavailable, keep the gate pending for the user's explicit waiver.
- Once the user confirms and resolves or explicitly defers material questions, create/update the authorized ticket(s), preserving identity and history. An explicit request to publish an agreed brief counts as confirmation.
Keep a living brief
- When saving intent, publish to the document destination your workspace instructions name to create or update the relevant briefs; otherwise keep it in the work's page bundle (see page). Honor brief-only, GitHub-only, combined, and draft-only requests; for ticket work, prefer a linked brief alongside the issue.
- Reuse the linked page. New work goes to the folder your workspace instructions name; explicit destinations win. Clarify ambiguous names.
- Name the workspace for the task and retain its ID. Verify organization, folder, and audience; return its location with the link.
- Use explain-visually when a visual would clarify the intent; contribute to this same brief.
- Cross-link tickets and their briefs.
- On an authorized revision, reconcile the latest discussion and linked artifacts before updating them. Preserve accurate human contributions and surface conflicting decisions for resolution.
- If no document destination is named, keep the full brief in GitHub when ticket publication is authorized; otherwise return a copyable draft in the requested available destination. Report failed connected saves and the status of each artifact independently.
- Match artifact access to the intended audience. Keep sensitive material in approved private destinations and create public shares when the user has authorized that audience. Pass the workspace ID and storage rule to helpers.
Verify and return
- Prefer available GitHub tools, with authenticated
ghas a fallback. Send titles and bodies as structured data or body files. - Before publishing, read as the assignee: can they explain what changes, why, how success is observed, and which decisions remain open?
- Read back each saved ticket or brief; verify content, cross-links, audience, and current intent. Inspect any visual companion and state the limits of available verification.
- Return the ticket and brief links grouped by outcome, with save status where needed. Carry these references into subsequent planning, implementation, and PR handoffs.
Related skills
Word Document Editor
anthropics
Create, edit, and format Word documents with tables, images, and tracked changes.
Ask Questions If Underspecified
trailofbits
Ask clarifying questions before starting work on ambiguous requests.
CLAUDE.md Optimizer
daymade
Optimize your CLAUDE.md file for clarity, efficiency, and maintainability.
Claude Skills Troubleshooter
daymade
Diagnose and fix plugin installation, enablement, and activation problems.