ticket-plan
Start and plan a Jira ticket: load context, summarize scope, evaluate split, and produce an approved plan.
Skill by enricogolfieri
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/enricogolfieri-ticket-plan
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/ticket-plan
What's inside
- Skill name
ticket-plan- Description
- Start and plan a Jira ticket: load context, summarize scope, evaluate split, and produce an approved plan. Sets ticket_kind and next_skill (implement or analyse). Use when invoking /ticket-plan <TICKET> or starting ticket work. Every session runs PRECHECK → LOAD_MEMORY → EXECUTION (plan phases only).
- License
- Unlicense
- Instructions
- 139 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Ticket Plan
Plan a Jira ticket through context, split evaluation, and an approved plan.
Does **not** implement or analyse.
Read shared rules: [`../ticket-shared/reference.md`](../ticket-shared/reference.md).
## Invocation
`/ticket-plan <TICKET>`
Optional: `user_instructions`, `extra_context`, `work_kind` (`original` | `sub-work`).
## Session
```text
PRECHECK → LOAD_MEMORY → EXECUTION (plan phases only)
```
1. Follow **PRECHECK** and **LOAD_MEMORY** in the shared reference (`state.json` only).
2. EXECUTION covers only the phases below. Stop at user gates. Dump on every checkpoint.
## EXECUTION phases
```text
LOAD_TICKET_CONTEXT
→ PHASE_1_CONTEXT_SUMMARY
→ SPLIT_DECISION
→ SPLIT_TICKET_CREATION? # optional
→ PHASE_2_PLAN_MODE
```
If `work_kind` is `sub-work`, skip `SPLIT_DECISION` / `SPLIT_TICKET_CREATION`.
Do not re-run earlier phases unless `phase_reached` still points there. Legacy states with old order (plan before split) should continue from stored `phase_reached` without rewriting history; new tickets use the order above.
### LOAD_TICKET_CONTEXT
**Purpose:** Load Jira/product context.
**Steps:**
1. Read ticket description and all comments (devprod MCP).
2. If an epic is present: load technical design and titles of committed and non-committed epic tickets.
3. Call out exactly what is missing.
**Dump:** `--phase LOAD_TICKET_CONTEXT --design "…"`.
**Exit:** advance to `PHASE_1_CONTEXT_SUMMARY`.
### PHASE_1_CONTEXT_SUMMARY
**Purpose:** Prove understanding before split/plan.
**Steps:**
1. Summarize goal, comments/constraints, epic goal, gotchas, and how user context changes interpretation.
2. Ask the user to confirm. Do **not** propose an implementation plan yet.
**Dump:** `--phase PHASE_1_CONTEXT_SUMMARY --context "…"`.
**Exit:** user confirms → `SPLIT_DECISION` (or `PHASE_2_PLAN_MODE` if sub-work).
### SPLIT_DECISION
**Purpose:** Decide whether to split into sub-tickets.
**Steps:**
1. Skip if `work_kind` is `sub-work`.
2. Propose keep one ticket vs split. Every split ticket must include implementation **and** tests.
3. Ask: keep one ticket, accept the split, or skip split-ticket creation.
4. If the user says "implement" / "continue" without a split discussion, record `keep one ticket`.
**Dump:** `--phase SPLIT_DECISION --split-decision "…"`.
**Exit:** split accepted → `SPLIT_TICKET_CREATION`; else → `PHASE_2_PLAN_MODE`.
### SPLIT_TICKET_CREATION
**Purpose:** Create sub-tickets when split was accepted.
**Steps:**
1. Follow `/create-jira-ticket`.
2. Concise titles; Jira Wiki Markup descriptions; reuse project/team/priority/epic.
3. Assign to current user; set current sprint; link to parent.
4. Mark each new ticket memory as `work_kind: sub-work`.
5. If assignee/sprint cannot be set via tools, stop and report the missing capability.
**Dump:** `--phase SPLIT_TICKET_CREATION --extra-json '{"created_tickets":[…]}'`.
**Exit:** → `PHASE_2_PLAN_MODE` (parent) or hand off sub-tickets via `ticket-plan` / `ticket-resume`.
### PHASE_2_PLAN_MODE
**Purpose:** Approved plan with tests (or analysis plan for PERF).
**Steps:**
1. Switch to Plan Mode before producing the plan.
2. Set `ticket_kind` to `server` or `perf` (from project/type or user).
3. Propose implementation **and** tests together (or analysis steps + experiment linkage for PERF). Never detach testing from implementation for SERVER work.
4. Include validation commands and expected confidence.
5. Re-dump on revision without advancing phase.
6. Ask for explicit plan approval.
Plan format:
```markdown
## Context Summary
<short refreshed summary>
## Implementation Plan
- <change area, files/symbols, intended behavior>
(for PERF: analysis steps and experiment plan)
## Test Plan
- <unit/integration/jstest coverage paired with the change>
(for PERF: how experiments will be compared / noise checks)
## Validation
- <compile / unit / resmoke or perf comparison commands>From enricogolfieri/workspace-mongo, Unlicense.
More from enricogolfieri/workspace-mongo
- 0.552score
trace-function
enricogolfieri
Statically trace what happens when a C++ function is called, including verified call edges, max-depth stack trace, and branch gates.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ticket-analyse
enricogolfieri
Analyse PERF tickets and register each new experiment in state.json (patch, comparison links, notes paths).
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ticket-flush
enricogolfieri
Persist durable ticket session truth mid-chat: update state.json and create any memory files needed (context, session notes, experiment notes), indexed from…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
write-mongo-jstests
enricogolfieri
Write focused MongoDB jstests with explicit mocha cases, small mechanical topology helpers, purposeful comments, robust teardown, and correct ownership.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ticket-resume
enricogolfieri
Resume a ticket from durable state and continue from its recorded phase.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ticket-implement
enricogolfieri
Implement an approved SERVER ticket plan: create branch, code+tests, validate, open a draft PR.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
ticket-shared
enricogolfieri
Shared reference and state_memory.py for ticket-plan, ticket-implement, ticket-analyse, ticket-resume, and ticket-flush.
SkillBFreshness: B★ 1Claude Code +9 - 0.497score
mongo-pr-review
enricogolfieri
Performs deep pull request reviews by quickly explaining code changes and identifying potential bugs grouped by severity (critical, non-critical, nit).
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
distributed-code-flow-diagrams
enricogolfieri
Generate scoped Mermaid diagrams for distributed code flows.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
extract-author-changes
enricogolfieri
Loads context for the current branch's PR-scope changes (merge-base to HEAD), including uncommitted edits, then confirms without summarizing.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
hot-bf-pings
enricogolfieri
Drafts Slack ping messages for hot Build Failures (BFs) from a Jira filter, listing the assignee, the SERVER dependency ticket, the GitHub PR, and a one-line…
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
mongo-failure-investigator
enricogolfieri
Investigates MongoDB test failures from a local log file (./tests.log).
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 12, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Unlicense
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from enricogolfieri
- 0.552score
trace-function
enricogolfieri
Statically trace what happens when a C++ function is called, including verified call edges, max-depth stack trace, and branch gates.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ticket-resume
enricogolfieri
Resume a ticket from durable state and continue from its recorded phase.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ticket-analyse
enricogolfieri
Analyse PERF tickets and register each new experiment in state.json (patch, comparison links, notes paths).
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ticket-flush
enricogolfieri
Persist durable ticket session truth mid-chat: update state.json and create any memory files needed (context, session notes, experiment notes), indexed from…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ticket-implement
enricogolfieri
Implement an approved SERVER ticket plan: create branch, code+tests, validate, open a draft PR.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
write-mongo-jstests
enricogolfieri
Write focused MongoDB jstests with explicit mocha cases, small mechanical topology helpers, purposeful comments, robust teardown, and correct ownership.
SkillBFreshness: B★ 1Claude Code +9
Cite this page
ticket-plan skill. Agent Mart. https://agentmart.dev/skills/enricogolfieri-ticket-plan (last updated 2026-10-24)