AGENT SKILL

agile-6-create-epics

Epics in Jira from Roadmap. Triggers: create epics, set up Jira for MVP. After skill 5, before skill 7.

License 许可
MIT
最近更新
2026-11-13
Stars
★ 0
Forks
0

01 前言 Front Matter

name
agile-6-create-epics
description
Epics in Jira from Roadmap. Triggers: create epics, set up Jira for MVP. After skill 5, before skill 7.

03 SKILL.md 正文

agile_6_create_epics

Product Manager + Tech Lead structuring work in Jira so it is ready for Story writing: scan → interview on anything ambiguous → create/update Epics linked to Confluence → advise.

Confluence structure (canonical — identical across all agile-skills)

Every page is a child of the root folder created by agile-1. Read this tree before creating any page; never duplicate one that exists.

📁 [Project Name]                         (root — agile-1)
├── 📄 Vision Doc — [Project]             (agile-1)
├── 📄 PRD — [Project]                    (agile-2)
├── 📄 Design Brief — [Project]           (agile-3 BRIEF)
├── 📄 Specs UI — [Project]               (agile-3 INTEGRATE)
├── 📄 ADR — [Project]                    (agile-4; current architecture state)
├── 📄 Decision Log — [Project]           (agile-5; register, one row per decision)
│   └── 📄 Decisions D001–D099 — [Project] (full entries by ID range: D100–D199, …)
├── 📄 Working Agreements — [Project]     (agile-5 creates · agile-15 writes; rules in force: process, planning, operator, ops)
├── 📄 Roadmap — [Project]                (agile-5 — INDEX only)
│   ├── 📄 Parking Lot — [Project]        (agile-5; unscheduled and rejected ideas)
│   ├── 📄 MVP — [Project]                (agile-5; an iteration page)
│   │   └── 📄 Sprint 1 — [Project]       (agile-9 plans · agile-8 backlog · agile-15 closes)
│   └── 📄 Iteration N — [Project]        (agile-5 ITERATION)
│       └── 📄 Sprint N — [Project]
├── 📁 Retrospectives — [Project]         (container: page or Confluence folder, agile-15; one Retro page per sprint)
├── 📁 Closeouts — [Project]              (container: page or Confluence folder, agile-13; sibling of Retrospectives, never inside it)
└── 📁 Extras — [Project]                 (folder; Debt Register (agile-15) + every page this tree does not name)

Page placement. Before creating a page, pick its parent from this tree and pass that parent's page id. Under the Roadmap sit only Parking Lot, MVP and Iteration N; under an MVP / Iteration N page sit only its Sprint N pages. A closeout goes in Closeouts, a retro in Retrospectives, and any page the tree does not name (audit, coverage matrix, investigation, one-off report) in Extras. Reuse an existing folder whatever its exact title (Extras or Extras — [Project]); create it under the root only when absent. After creating, read the page back: a wrong parentId is fixed by moving the page (mcp__atlassian__updateConfluencePage with parentId), never by creating a second copy.

Page layouts. Every page keeps the ## headings below, in this order, and no others. A heading never carries a status, a date or a skill name, so a section is found by its name. Status lives in the page's ## Properties (the Roadmap's ## Status line); history lives in ## Change history (Date | Change | By, one row per edit) and in the edit's version message, never in a status line, a heading or a table cell. Planning-time text is rewritten to the outcome when the sprint closes, not left beside it. agile-planning skills read the field-level templates from agile-5-roadmap; other skills use the headings and columns below.

Page ## headings, in order (table columns in brackets)
Roadmap Status · Guiding principle · Iterations · Progress · Parking lot · Next step · Change history
MVP / Iteration N Properties · Goal · Success criteria · Epics in scope · Sprints · Scope changes · Dependencies and risks · Feedback carried in · Research record · Closing summary · Change history
Sprint N Properties · Goal · Scope · Decisions · Backlog · Build order · Success criteria · Risks · Conclusion · Notes · Change history
Decision Log Register (ID · Alias · Date · By · Title · Status · Scope · Supersedes / Amends · ADR § · Entry) · Change history
Decisions D###–D### one ## D### — <title> per decision: Decision · Why · Alternatives rejected · Consequences · Supersedes / Amends · Source
Parking Lot Ideas (Idea · Raised · Why parked · Earmark · Link) · Rejected (Idea · Date · By · Why) · Change history
Working Agreements Rules in force (Rule · Kind · Since · Source · Applies to) · Retired (Rule · Retired · Why) · Change history
Debt Register Open (Item · Source · Jira · Size · Target) · Closed (Item · Closed · How) · Change history
Retrospectives / Closeouts Index (one row per report) when the container is a page; a Confluence folder has no body and lists its children itself
Vision Doc · PRD · Design Brief · Specs UI · ADR the template in the owning skill, ending with Change history
Retro · Closeout the template in the owning skill (written once)

One fact, one home; every other page links to it. Tickets, points and statuses → Jira. Verdicts and severity counts → the Closeout. Lessons → the Retro. Current architecture → the ADR. Decision text → the Decision Log; elsewhere only its ID and title. Sprint figures → the Sprint page's Properties, rolled up into its Iteration page's ## Sprints and the Roadmap's ## Progress in the same run that changes them. A dated snapshot that quotes a figure beside a link to its home (a Retro's velocity line, a verdict as the label of a Closeout link) is allowed; a second copy that someone maintains is not. Size budgets, counted on the rendered text (markup excluded): Roadmap ≤ 10k characters, MVP / Iteration page ≤ 30k, Sprint page ≤ 50k.

A drifted page is fixed, not extended. A page that breaks its layout — other headings, a changelog in a status line, one fact in several places, contradictory figures, over budget, a page under the wrong parent — is never patched in its old shape and never ignored. Write your own change in the layout, then plan the fix: list the drift and propose agile-5-roadmap RESTRUCTURE before finishing, and run it when the user agrees.

Step 1 — Scan existing state

Read the Roadmap index to find the current iteration, then open its MVP — [Project] / Iteration N — [Project] child page and read the Epics in scope table there — the index itself only links to it. Read ADR §11 for complexity estimates and dependencies. Search Jira for Epics already created (by name, label, or Confluence link), and for each Epic in scope determine whether it exists and, if so, its current state.

Report before doing anything, then ask "Shall I proceed with this plan?":

Epic status for [Project Name]:
| Epic | In Jira? | Jira status | Action needed |
|------|----------|-------------|---------------|
| [Epic 1] | ✅ Yes | In Progress | No action — already active |
| [Epic 2] | ✅ Yes | To Do | Review description, may need update |
| [Epic 3] | ❌ No | — | Will create |

No approved Roadmap → stop: "I can't find an approved Roadmap for this project. Please complete skill 5 first."

Step 2 — Interview for Epic-level clarity

Per Epic to create or update: a short action-oriented name devs will recognise ("User Authentication", "Dashboard MVP"); a one-sentence goal naming the user problem it solves; the scope boundary, in and out, which is what stops scope creep at Story-writing time; Epic-level acceptance criteria (high level — Stories carry the detail); dependencies on other Epics or external systems; the owning team; and labels for filtering.

Ask when a name from the ADR is too vague to be a Jira card ("Auth stuff"), when two Epics have a blurry boundary ("User Profile" vs "Account Settings" — "where does one end and the other begin?"), when ownership is unspecified, or when an Epic has an implicit dependency nobody listed. Infer and flag a goal derivable from a detailed ADR description, a dependency obvious from the ADR data model ("Notifications requires the User model from Auth"), or labels implied by the Roadmap section (an MVP Epic → label mvp).

Only ask about the genuinely unclear Epics — never re-ask for ones the ADR already defines well. All questions in one message, every assumption stated. Never infer silently.

Step 3 — Create or update Epics in Jira

Summary: [Epic name] — [Project Name]. Labels: [project-slug], [iteration], [layer]. Status: To Do. Assignee: the owning team or person when known.

## Goal
[One sentence: the user problem completing this Epic solves]

## Scope
**In scope:** …
**Out of scope:** …

## Epic-level acceptance criteria
- [ ] [Criterion]

## Dependencies
- Depends on: … | Blocks: …

## References
Roadmap · PRD · ADR · Specs UI (Confluence links)
  • Create in dependency order — never create Epic B before the Epic A it depends on.
  • An existing Epic with outdated content is updated, never duplicated.
  • Never delete an Epic. Out of scope → add a comment explaining why and transition to Won't Do / Cancelled, after user confirmation.
  • Link each Epic back to the Confluence Roadmap via a remote link or a description reference.

Step 4 — Update the MVP/Iteration page

Update the ## Epics in scope table on the current MVP / Iteration N page — not the Roadmap index, since epic-level detail lives on the iteration page:

| Epic | Jira | Why | Complexity | Owner | Sprint | Status |

This keeps the two in sync: the child page is the human-readable view of what is in Jira, and the Roadmap index just links to it.

Step 5 — Resume logic

Re-scan live Jira Epic statuses — never assume the previous state still holds. Create only what is still missing; update only Epics whose description has drifted from the Roadmap/ADR; re-sync the Epics-in-scope table with current links and statuses; report what changed versus what was already correct.

Step 6 — Advise

✅ Done:
- [N] Epics created in Jira: [keys] · [N] already existed and were reviewed
- MVP/Iteration page Epics table updated with Jira links

⚠️ Still needed (human action required):
- Assign owners to: [Epics without assignees]
- Resolve scope boundary questions: [if any remain]
- Validate dependency order with the Tech Lead

👉 Next step — Skill 7: agile_7_create_stories — start with the Epic that has no blocking dependencies.
   Input: Jira Epic key + the Specs UI page for the relevant screens.

Principles

  • Ask before writing — clarify vague names, blurry scope boundaries, and ownership first; all questions in one message, every assumption stated.
  • Create in dependency order, and never duplicate an existing Epic — update it.
  • Never delete an Epic — Won't Do / Cancelled, with a comment and user confirmation.
  • Confluence and Jira stay in sync — every Epic links back on the MVP/Iteration page.

04 同仓库更多 Skills

cedricfarinazzo
cedricfarinazzo/agile-skills

session-audit

Audit the cost and efficiency of Claude Code sessions that ran agile-skills: per-skill and per-subagent spend, a before/after delta normalised by work shipped, and ranked skill improvements. Triggers: audit this session's cost, analyze the session transcripts, compare before and after sessions, is the new version more efficient, where do the tokens go, subagent cost breakdown, find efficiency improvements.

★ 0
cedricfarinazzo
cedricfarinazzo/agile-skills

deep-it-project-review

Autonomously perform a deep, evidence-backed technical review of a software or IT project across applicable architecture, code, security, delivery, operations, and lifecycle domains without modifying project files. Triggers: deep IT project review, technical project review, architecture audit, repository assessment, assess this codebase, review this project.

★ 0
cedricfarinazzo
cedricfarinazzo/agile-skills

test-refactor

Audit one test suite at a time for dead weight, duplication, parallel-unsafety and runtime cost, or characterize behavior before a risky refactor — with production code frozen and good coverage kept, proven per module rather than assumed. Triggers: test refactor, characterize before refactor, characterization tests, clean the tests, refactor the tests, test suite audit, DRY the tests, parallelize the test suite, speed up the tests.

★ 0
cedricfarinazzo
cedricfarinazzo/agile-skills

doc-refactor

Audit every markdown file in a repo — READMEs, docs/, and agent-instruction files — for lies, drift, duplication and bloat, then ticket and ship the cleanup as a sequenced PR train, with source code frozen and every surviving claim verified against the repo rather than read. Triggers: doc refactor, refactor the docs, clean the docs, documentation audit, README audit, docs are stale, DRY the docs, audit every markdown file.

★ 0
cedricfarinazzo
cedricfarinazzo/agile-skills

deep-refactor

Audit an entire codebase for defects, waste and debt, then ticket and ship the findings as a sequenced PR train — without breaking the test contract. Triggers: deep refactor, refactor audit, clean the codebase, DRY pass, audit and fix everything.

★ 0
cedricfarinazzo
cedricfarinazzo/agile-skills

agile-sprint-drain

Drain the active sprint to a fixed point: auto-alternate agile-10-implement (build) and agile-11-merge-train (merge) until both empty (DRAINED) or blocked (STUCK). Optional concurrency=N, dispatch=session, max-merges=N. Triggers: drain the sprint, run the sprint to completion, implement and merge until done, clear the whole board, ship the sprint.

★ 0