ticket-to-pr-pipeline
ticket-to-pr-pipeline: Jira ticket through plan, build, review-core, and PR in one continuous run.
Skill by lucavb
Chalk Labs
Need help deploying ticket-to-pr-pipeline?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/lucavb-ticket-to-pr-pipeline
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
Use cases: data
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 and code. Checked Nov 1, 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-to-pr-pipeline
What's inside
- Skill name
ticket-to-pr-pipeline- Description
- ticket-to-pr-pipeline: Jira ticket through plan, build, review-core, and PR in one continuous run. Requires review-core. Use for a Jira ticket or bug when the user wants a merge-ready PR or invokes /ticket-to-pr-pipeline. Use when the user approves the plan or says implement, execute, or go ahead after intake.
- License
- MIT
- Instructions
- 87 lines in SKILL.md · view on GitHub
Files (4)
- CONTINUITY.md
- PLAN-ALTERNATIVES.md
- README.md
- SKILL.md
SKILL.md (first lines)
# Ticket-to-PR pipeline
A **pipeline** runs the same **process** every ticket: intake → plan → build → **review-core** → ship.
**Requires [review-core](../review-core/SKILL.md).** **Continuity** rules: [CONTINUITY.md](CONTINUITY.md).
## When to run
Run all five phases with **continuity** when the user gives a ticket and expects a merge-ready PR.
Scope to named phases only when the user says so ("just plan", "build only", "review what we have", "stop before PR") — see [CONTINUITY.md](CONTINUITY.md).
## Phase 1 — Intake and plan
**Mode:** plan / read-only until the user approves.
1. Fetch the ticket (Jira MCP or pasted AC): summary, steps, expected vs actual, linked tickets.
2. Apply [discover-before-planning](../discover-before-planning/SKILL.md): do **legwork** in the codebase — find the flow, related tests, sibling implementations, prior tickets cited in AC. Use **Glob** → **Grep** → **Read** (see [review-core/EXPLORATION.md](../review-core/EXPLORATION.md)).
3. Reproduce or explain reproducibility from code + ticket steps. Say clearly if manual repro is still needed.
4. Survey **alternatives**: identify at least two viable implementation approaches (including "do nothing structural — patch locally"). For each: behaviour, scope, risk, consistency with sibling code, test cost. Name the recommended approach and why the others lose — see [PLAN-ALTERNATIVES.md](PLAN-ALTERNATIVES.md).
5. Produce a plan (`CreatePlan` in plan mode) that includes the alternatives comparison. Cite files and essential snippets. Note scope and non-goals.
6. Stop. Wait for user approval before editing.
7. Post the pipeline checklist (below); mark Phase 1 done.
**Completion criterion:** plan with ≥2 alternatives compared; user approved or waived planning; no product code edited yet; checklist posted.
## Phase 2 — Build
1. Implement the approved plan. Minimal diff; match repo conventions.
2. If **legwork** during build surfaces a clearly better alternative than the approved plan, stop and surface it to the user before continuing — see [PLAN-ALTERNATIVES.md](PLAN-ALTERNATIVES.md) Phase 2.
3. Add or extend tests that fail without the fix and pass with it.
4. Run targeted tests and fix failures.
5. Optional **regression proof:** stash only the fix (keep new tests), run tests — they should be **red** without the fix; restore stash.
**Completion criterion:** tests pass; regression proof done or skipped; **continuity** — Phase 3 begins in the same session.
## Phases 3–4 — Review core (`mode: implement`)
Run [review-core](../review-core/SKILL.md) Steps 1–3 with **`mode: implement`**.
**Phase 3 inputs** (blind critics):
- Ticket text and AC (and linked tickets if relevant)
- Source manifest from [review-core](../review-core/SKILL.md), populated with the exact branch or uncommitted diff and changed files
- Pointers to sibling/reference implementations in the repo
- Instruction: be skeptical; severity-tag findings; assume the fix may be wrong
- Hygiene critic when manifest lists commits — [review-core/COMMIT-HYGIENE.md](../review-core/COMMIT-HYGIENE.md)
**Withhold from critics:** implementer rationale, plan-file reasoning, chosen-approach narrative — see [review-core/BLIND-REVIEW.md](../review-core/BLIND-REVIEW.md). Tribunal alternatives: [review-core/ALTERNATIVES.md](../review-core/ALTERNATIVES.md).
**Phase 4 actions** (after adversarial validation):
- Implement **Holds up** items on the branch
- Re-run tests after accepted changes
- Summarize audit trail: what critics said, what you accepted/rejected/deferred, and why
**Completion criterion:** every material finding has hold/reject/defer; accepted items implemented and tested; **continuity** — Phase 5 begins in the same session unless user scoped "stop before PR".
## Phase 5 — Ship
1. Branch from `main` (not an unrelated feature branch) unless the user specifies otherwise.
2. Stage **only** files for this ticket — exclude unrelated local changes (`package.json`, debug logs, etc.).
3. Commit using [writing-commit-messages](../writing-commit-messages/SKILL.md) style for this repo. Unresolved hygiene Holds from Phase 3–4 block ship.
4. Push and open PR with `gh pr create` (summary, test plan). Return the PR URL.
**Completion criterion:** PR URL delivered; branch contains only intentional ticket changes.
## Pipeline checklist
Update after each phase. Pipeline-complete when Phase 5 is checked **or** the user scoped out remaining phases.
```
- [ ] Phase 1: Plan approved (alternatives compared; legwork via Glob/Grep/Read)
- [ ] Phase 2: Build + tests green (+ regression proof optional)
- [ ] Phase 3: review-core blind review (≥2 subagents, no implementer rationale)
- [ ] Phase 4: review-core tribunal + adversarial — findings resolved (incl. alternatives)
- [ ] Phase 5: Branch, commit, PR
```
## Related skills
- [discover-before-planning](../discover-before-planning/SKILL.md) — close answerable questions during Phase 1 planning
- [review-core](../review-core/SKILL.md) — required; blind review, tribunal, adversarial validation
- [writing-commit-messages](../writing-commit-messages/SKILL.md) — commit messages on ship
- [conversation-handoff](../conversation-handoff/SKILL.md) — if delegating a single phase to another agent
- [refining-jira-tickets](../refining-jira-tickets/SKILL.md) — if the ticket itself is not ready (before Phase 1)
- [review-tribunal](../review-tribunal/SKILL.md) — reviewing a PR or local diff without implementing it (`mode: review`)From lucavb/skills, MIT.
More from lucavb/skills
- 0.604score
scrum-next
lucavb
Scrum board next-work triage.
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
review-tribunal
lucavb
Review tribunal for pull requests or local Git diffs: intake, review-core blind critics (including alternatives), tribunal, adversarial validation, then local…
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
review-core
lucavb
Shared adversarial review engine: blind parallel critics (including alternatives), tribunal adjudication, and adversarial re-validation.
SkillAFreshness: A★ 3Claude Code +9 - 0.569score
refining-jira-tickets
lucavb
Pre-scrum refinement of Jira stories for engineering readiness.
SkillBFreshness: B★ 3Claude Code +9 - 0.569score
atlassian-jira-adf-formatting
lucavb
Round-trip Jira story descriptions via Atlassian MCP ADF — fetch full doc, edit in files, validate, file-backed editJiraIssue.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
conversation-handoff
lucavb
Summarize the current conversation into a copy-pasteable handoff message for a fresh chat.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
gh-fetch
lucavb
GitHub fetch — gh CLI for GitHub URLs; checkout when multiple file accesses are foreseen.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
closing-ritual
lucavb
Closing ritual — surface doubts, blind spots, and unverified claims before work is accepted.
SkillBFreshness: B★ 3Claude Code +9 - 0.561score
angular
lucavb
Angular zoneless conventions — signals, toSignal, shells, encapsulated styles.
SkillBFreshness: B★ 3Claude Code +9 - 0.561score
writing-commit-messages
lucavb
Required before every git commit.
SkillBFreshness: B★ 3Claude Code +9 - 0.559score
discover-before-planning
lucavb
Do discovery during planning — explore the codebase and close open questions before presenting a plan.
SkillBFreshness: B★ 3Claude Code +9 - 0.558score
tldr
lucavb
Condense the immediately preceding assistant answer into a direct TL;DR.
SkillBFreshness: B★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 19, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/lucavb/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from lucavb
- 0.604score
review-tribunal
lucavb
Review tribunal for pull requests or local Git diffs: intake, review-core blind critics (including alternatives), tribunal, adversarial validation, then local…
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
scrum-next
lucavb
Scrum board next-work triage.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
review-core
lucavb
Shared adversarial review engine: blind parallel critics (including alternatives), tribunal adjudication, and adversarial re-validation.
SkillAFreshness: A★ 3Claude Code +9 - 0.569score
atlassian-jira-adf-formatting
lucavb
Round-trip Jira story descriptions via Atlassian MCP ADF — fetch full doc, edit in files, validate, file-backed editJiraIssue.
SkillBFreshness: B★ 3Claude Code +9 - 0.569score
refining-jira-tickets
lucavb
Pre-scrum refinement of Jira stories for engineering readiness.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
conversation-handoff
lucavb
Summarize the current conversation into a copy-pasteable handoff message for a fresh chat.
SkillBFreshness: B★ 3Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get ticket-to-pr-pipeline running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
ticket-to-pr-pipeline skill. Agent Mart. https://agentmart.dev/skills/lucavb-ticket-to-pr-pipeline (last updated 2026-10-24)