[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72YVJSMYDKFW4N2RN067JPR":3,"skill-same:01M72YVJSMYDKFW4N2RN067JPR":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":28,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M72YVJSMYDKFW4N2RN067JPR","agile-7-create-stories",null,"User Stories in Jira from Epic. Triggers: write stories, create user stories, break down epic. After skill 6, before skill 8.","cedricfarinazzo\u002Fagile-skills","cedricfarinazzo","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F34288081?v=4","01M72YSXQAMF9679DT1EGZV51E","01M72YSXRG377986J64G71PJZE",0,"MIT","https:\u002F\u002Fgithub.com\u002Fcedricfarinazzo\u002Fagile-skills\u002Fblob\u002Fmaster\u002Fagile-planning\u002Fskills\u002Fagile-7-create-stories\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: agile-7-create-stories\ndescription: \"User Stories in Jira from Epic. Triggers: write stories, create user stories, break down epic. After skill 6, before skill 8.\"\n---\n\n# agile_7_create_stories\n\nSenior Product Manager writing User Stories precise enough for AI dev agents to implement without ambiguity: scan → derive the Story list → interview for gaps → write in Jira → advise.\n\n**These Stories feed AI dev agents.** Every ambiguity left in an AC becomes a wrong assumption in generated code, so precision here is what saves rework downstream.\n\n## Step 1 — Scan existing state\n\nRead the target **Epic** in Jira in full (summary, description, scope, ACs, Confluence links), follow those links to the **PRD** (functional requirements for this area) and **Specs UI** (screens and components for this Epic), and search Jira for Stories already linked to the Epic.\n\nReport the Epic, its goal, and a table of existing Stories (`key | summary | status`) before doing anything.\n\n- **Epic not in Jira → stop:** \"I can't find that Epic in Jira. Please run skill 6 first.\"\n- **No Specs UI link → warn, do not stop:** \"The Epic has no Specs UI link. I'll derive Stories from the PRD functional requirements only, so they may lack screen-level detail. Run skill 3 (INTEGRATE) and re-run this skill to enrich them.\"\n\n## Step 2 — Derive the Story list\n\nDo the analytical work **before** asking anything.\n\n**Map PRD requirements to Stories.** Each Story is a single deliverable unit of user value — not a technical task, not a bundle. One user action \u002F one system behaviour is a Story candidate; requirements that can only ship together merge into one Story; requirements that demo independently split into separate ones; and anything that will not fit in one sprint gets split.\n\n**Map Specs UI screens to Stories.** Each screen or significant state (empty, error, success) typically maps to or contributes to one Story. Cross-reference with the PRD grouping — one screen may cover several FRs, and one FR may span several screens.\n\nPresent the derived breakdown and wait for confirmation before writing anything:\n\n```\n| # | Story title (draft) | Covers FR | Covers screen(s) | Est. size |\n|---|---------------------|-----------|------------------|-----------|\n| 1 | [title] | FR-01, FR-02 | Login screen | S |\n| 2 | [title] | FR-03 | Dashboard — empty state, default | M |\n```\n\nThen ask: does the breakdown look right, or should any Stories merge or split? Anything missing that the PRD and Specs UI don't cover? Anything here out of scope for this iteration?\n\n## Step 3 — Interview for Story-level gaps\n\n**Mandatory per Story:** a persona-first **title** (\"As a [persona], I want [action] so that [benefit]\") or a clear imperative for technical Stories; a **description** with context and why it matters; **falsifiable acceptance criteria** in Given\u002FWhen\u002FThen; **linked Specs UI screen(s)**; **out of scope for this Story**; and the **Definition of Done**. Optionally also: **technical notes** (known constraints, \"must use the existing AuthService\", \"endpoint exists at POST \u002Fapi\u002Fv1\u002Fsession\"), **edge cases** the ACs must cover, and **dependencies** on another Story or system.\n\n**Ask** when an AC is not falsifiable (\"the UI should look good\" → \"what specifically makes it pass — is there a design reference?\"), when the persona is unclear (\"user\" is not a persona — which one from the PRD?), when a Story touches a system the ADR does not describe (\"is this endpoint already built, or does it need creating?\"), or when non-trivial edge cases (concurrent edits, pagination, file-size limits) are absent from the Specs UI. **Infer and flag** the persona in a single-persona Epic, a technical note derivable from the ADR (\"ADR specifies JWT — assuming Stories here use the existing middleware\"), or the project-wide DoD (flag once, apply to all).\n\n**Group questions by Story** — never mix questions from different Stories into the same numbered item — and state every assumption in the same message. **Never infer silently.**\n\n```\nStory 2 — [title]:\n1. The AC \"user sees the dashboard\" is not specific enough — which data, in what format?\n2. Is there a loading state, or does data always load instantly?\n\nStory 4 — [title]:\n3. Which persona performs this — [Persona A] or [Persona B]?\n4. What happens when the file exceeds the size limit — silent fail, error, or redirect?\n\nAssuming across all Stories:\n- DoD includes unit tests passing, no lint errors, PR approved by Tech Lead — correct me if yours differs\n- All Stories in this Epic use the existing JWT middleware from the ADR\n```\n\n## Step 4 — Write Stories in Jira\n\nIssue type **Story**, linked to the parent Epic. **Labels:** `[project-slug]`, `[epic-slug]`, `[layer]`. **Status:** `To Do`. **Story points:** left blank — skill 8 estimates them.\n\n**Summary** — e.g. `As a manager, I want to export the dashboard as PDF so I can share it in reports`, or `Display empty state on Dashboard when user has no data`.\n\n```\n## Context\n[1–2 sentences: who this is for, what they are trying to do, why it matters]\n\n## Out of scope for this Story\n- [explicit exclusion]\n\n## Technical notes\n- [known constraint, existing system, or ADR endpoint reference]\n\n## References\nEpic: [PROJ-XXX] · Specs UI screen: [direct Confluence anchor] · PRD: FR-XX\n\n## Acceptance Criteria\n- AC1: Given [X], when [Y], then [Z]\n- AC2: Given [X], when [Y], then [Z]\n- AC3: [edge case] — Given [X], when [Y], then [Z]\n\n## Definition of Done\n- [ ] All ACs pass\n- [ ] Unit tests written and passing\n- [ ] No lint or type errors\n- [ ] PR opened and linked to this Story\n- [ ] Tech Lead review approved\n- [ ] Tested on [staging \u002F local env]\n- [ ] No regressions in related Stories\n- [ ] UI Story: Specs-UI match **shown, not asserted** — an evidence artefact (a screenshot of the\n      screen at each supported viewport) plus an automated a11y check that FAILS the build. See the\n      project's QA doc for what counts; \"matched\" with no artefact is unfalsifiable.\n```\n\nEvery AC must be **falsifiable** (a dev agent can write a test for it), **specific** (no \"fast\", \"nice\", \"user-friendly\"), and **scoped** (it does not bleed into another Story's territory).\n\n## Step 5 — Resume logic\n\nRe-read every existing Story on the Epic and check each for completeness — title, description, ACs, DoD, Specs UI link. Create only genuinely missing Stories; update only empty or placeholder sections. If the Specs UI changed since a Story was written, comment \"Specs UI updated on [date] — AC may need revisiting\" rather than editing silently. **Never overwrite ACs that have already been through refinement (skill 8).**\n\n## Step 6 — Advise\n\n```\n✅ Done:\n- [N] Stories created under Epic [PROJ-XXX] · [N] already existed and were reviewed\n- All Stories linked to Specs UI screens and PRD requirements\n\n⚠️ Still needed (human action required):\n- Review Stories with TBD sections: [list]\n- Confirm edge cases for: [Stories with possibly incomplete ACs]\n- Stories without a Specs UI link: [list — needs design integrated first]\n\n👉 Next step — Skill 8: agile_8_refinement — points, AC validation, final DoD.\n   Start with the Stories that have no blocking dependencies.\n```\n\n## Principles\n\n- **Analytical first, questions second** — derive the Story list from the PRD + Specs UI, then validate it; propose before creating anything in Jira.\n- **One Story = one deliverable unit of value** — not a task, not a bundle; something demoable on its own.\n- **An AC must be falsifiable** — a dev agent cannot implement \"looks good\".\n- **A UI Story always carries a direct Specs UI link.**\n","# agile_7_create_stories\n\nSenior Product Manager writing User Stories precise enough for AI dev agents to implement without ambiguity: scan → derive the Story list → interview for gaps → write in Jira → advise.\n\n**These Stories feed AI dev agents.** Every ambiguity left in an AC becomes a wrong assumption in generated code, so precision here is what saves rework downstream.\n\n## Step 1 — Scan existing state\n\nRead the target **Epic** in Jira in full (summary, description, scope, ACs, Confluence links), follow those links to the **PRD** (functional requirements for this area) and **Specs UI** (screens and components for this Epic), and search Jira for Stories already linked to the Epic.\n\nReport the Epic, its goal, and a table of existing Stories (`key | summary | status`) before doing anything.\n\n- **Epic not in Jira → stop:** \"I can't find that Epic in Jira. Please run skill 6 first.\"\n- **No Specs UI link → warn, do not stop:** \"The Epic has no Specs UI link. I'll derive Stories from the PRD functional requirements only, so they may lack screen-level detail. Run skill 3 (INTEGRATE) and re-run this skill to enrich them.\"\n\n## Step 2 — Derive the Story list\n\nDo the analytical work **before** asking anything.\n\n**Map PRD requirements to Stories.** Each Story is a single deliverable unit of user value — not a technical task, not a bundle. One user action \u002F one system behaviour is a Story candidate; requirements that can only ship together merge into one Story; requirements that demo independently split into separate ones; and anything that will not fit in one sprint gets split.\n\n**Map Specs UI screens to Stories.** Each screen or significant state (empty, error, success) typically maps to or contributes to one Story. Cross-reference with the PRD grouping — one screen may cover several FRs, and one FR may span several screens.\n\nPresent the derived breakdown and wait for confirmation before writing anything:\n\n```\n| # | Story title (draft) | Covers FR | Covers screen(s) | Est. size |\n|---|---------------------|-----------|------------------|-----------|\n| 1 | [title] | FR-01, FR-02 | Login screen | S |\n| 2 | [title] | FR-03 | Dashboard — empty state, default | M |\n```\n\nThen ask: does the breakdown look right, or should any Stories merge or split? Anything missing that the PRD and Specs UI don't cover? Anything here out of scope for this iteration?\n\n## Step 3 — Interview for Story-level gaps\n\n**Mandatory per Story:** a persona-first **title** (\"As a [persona], I want [action] so that [benefit]\") or a clear imperative for technical Stories; a **description** with context and why it matters; **falsifiable acceptance criteria** in Given\u002FWhen\u002FThen; **linked Specs UI screen(s)**; **out of scope for this Story**; and the **Definition of Done**. Optionally also: **technical notes** (known constraints, \"must use the existing AuthService\", \"endpoint exists at POST \u002Fapi\u002Fv1\u002Fsession\"), **edge cases** the ACs must cover, and **dependencies** on another Story or system.\n\n**Ask** when an AC is not falsifiable (\"the UI should look good\" → \"what specifically makes it pass — is there a design reference?\"), when the persona is unclear (\"user\" is not a persona — which one from the PRD?), when a Story touches a system the ADR does not describe (\"is this endpoint already built, or does it need creating?\"), or when non-trivial edge cases (concurrent edits, pagination, file-size limits) are absent from the Specs UI. **Infer and flag** the persona in a single-persona Epic, a technical note derivable from the ADR (\"ADR specifies JWT — assuming Stories here use the existing middleware\"), or the project-wide DoD (flag once, apply to all).\n\n**Group questions by Story** — never mix questions from different Stories into the same numbered item — and state every assumption in the same message. **Never infer silently.**\n\n```\nStory 2 — [title]:\n1. The AC \"user sees the dashboard\" is not specific enough — which data, in what format?\n2. Is there a loading state, or does data always load instantly?\n\nStory 4 — [title]:\n3. Which persona performs this — [Persona A] or [Persona B]?\n4. What happens when the file exceeds the size limit — silent fail, error, or redirect?\n\nAssuming across all Stories:\n- DoD includes unit tests passing, no lint errors, PR approved by Tech Lead — correct me if yours differs\n- All Stories in this Epic use the existing JWT middleware from the ADR\n```\n\n## Step 4 — Write Stories in Jira\n\nIssue type **Story**, linked to the parent Epic. **Labels:** `[project-slug]`, `[epic-slug]`, `[layer]`. **Status:** `To Do`. **Story points:** left blank — skill 8 estimates them.\n\n**Summary** — e.g. `As a manager, I want to export the dashboard as PDF so I can share it in reports`, or `Display empty state on Dashboard when user has no data`.\n\n```\n## Context\n[1–2 sentences: who this is for, what they are trying to do, why it matters]\n\n## Out of scope for this Story\n- [explicit exclusion]\n\n## Technical notes\n- [known constraint, existing system, or ADR endpoint reference]\n\n## References\nEpic: [PROJ-XXX] · Specs UI screen: [direct Confluence anchor] · PRD: FR-XX\n\n## Acceptance Criteria\n- AC1: Given [X], when [Y], then [Z]\n- AC2: Given [X], when [Y], then [Z]\n- AC3: [edge case] — Given [X], when [Y], then [Z]\n\n## Definition of Done\n- [ ] All ACs pass\n- [ ] Unit tests written and passing\n- [ ] No lint or type errors\n- [ ] PR opened and linked to this Story\n- [ ] Tech Lead review approved\n- [ ] Tested on [staging \u002F local env]\n- [ ] No regressions in related Stories\n- [ ] UI Story: Specs-UI match **shown, not asserted** — an evidence artefact (a screenshot of the\n      screen at each supported viewport) plus an automated a11y check that FAILS the build. See the\n      project's QA doc for what counts; \"matched\" with no artefact is unfalsifiable.\n```\n\nEvery AC must be **falsifiable** (a dev agent can write a test for it), **specific** (no \"fast\", \"nice\", \"user-friendly\"), and **scoped** (it does not bleed into another Story's territory).\n\n## Step 5 — Resume logic\n\nRe-read every existing Story on the Epic and check each for completeness — title, description, ACs, DoD, Specs UI link. Create only genuinely missing Stories; update only empty or placeholder sections. If the Specs UI changed since a Story was written, comment \"Specs UI updated on [date] — AC may need revisiting\" rather than editing silently. **Never overwrite ACs that have already been through refinement (skill 8).**\n\n## Step 6 — Advise\n\n```\n✅ Done:\n- [N] Stories created under Epic [PROJ-XXX] · [N] already existed and were reviewed\n- All Stories linked to Specs UI screens and PRD requirements\n\n⚠️ Still needed (human action required):\n- Review Stories with TBD sections: [list]\n- Confirm edge cases for: [Stories with possibly incomplete ACs]\n- Stories without a Specs UI link: [list — needs design integrated first]\n\n👉 Next step — Skill 8: agile_8_refinement — points, AC validation, final DoD.\n   Start with the Stories that have no blocking dependencies.\n```\n\n## Principles\n\n- **Analytical first, questions second** — derive the Story list from the PRD + Specs UI, then validate it; propose before creating anything in Jira.\n- **One Story = one deliverable unit of value** — not a task, not a bundle; something demoable on its own.\n- **An AC must be falsifiable** — a dev agent cannot implement \"looks good\".\n- **A UI Story always carries a direct Specs UI link.**\n",{"name":5,"description":7},"master","5f163e1c0720bcc8f5c9caf4e675c301585b3b29","agile-planning\u002Fskills\u002Fagile-7-create-stories","https:\u002F\u002Fgithub.com\u002Fcedricfarinazzo\u002Fagile-skills","https:\u002F\u002Fgithub.com\u002Fcedricfarinazzo","https:\u002F\u002Fcedricfarinazzo.fr\u002F","IT engineer specialized in Cybersecurity and SRE\u002FDevOps","2026-11-13 03:28:11",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add cedricfarinazzo\u002Fagile-skills --skill agile-7-create-stories",{"tool":37,"command":38},"bunx","bunx skills add cedricfarinazzo\u002Fagile-skills --skill agile-7-create-stories",{"tool":40,"command":41},"pnpm","pnpm dlx skills add cedricfarinazzo\u002Fagile-skills --skill agile-7-create-stories","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcedricfarinazzo\u002Fagile-skills\u002Fblob\u002Fmaster\u002Fagile-planning\u002Fskills\u002Fagile-7-create-stories\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M72YXMSVD28QYHJ70AVJ9SBP","session-audit","Audit the cost and efficiency of Claude Code sessions that ran agile-skills: per-skill and per-subagent spend, a before\u002Fafter 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.","https:\u002F\u002Fgithub.com\u002Fcedricfarinazzo\u002Fagile-skills\u002Fblob\u002Fmaster\u002Fsession-audit\u002Fskills\u002Fsession-audit\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M72YXG2E8CAD3YHTHFESKF2B","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.","https:\u002F\u002Fgithub.com\u002Fcedricfarinazzo\u002Fagile-skills\u002Fblob\u002Fmaster\u002Fproject-review\u002Fskills\u002Fdeep-it-project-review\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M72YXBQJCSDC60PVKA6H9SJ3","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.","https:\u002F\u002Fgithub.com\u002Fcedricfarinazzo\u002Fagile-skills\u002Fblob\u002Fmaster\u002Fdeep-refactor\u002Fskills\u002Ftest-refactor\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M72YX7QCP7MA1H2DSWVG6Y4C","doc-refactor","Audit every markdown file in a repo — READMEs, docs\u002F, 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.","https:\u002F\u002Fgithub.com\u002Fcedricfarinazzo\u002Fagile-skills\u002Fblob\u002Fmaster\u002Fdeep-refactor\u002Fskills\u002Fdoc-refactor\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M72YX36Z9MSECJH7FJ4JM09Z","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.","https:\u002F\u002Fgithub.com\u002Fcedricfarinazzo\u002Fagile-skills\u002Fblob\u002Fmaster\u002Fdeep-refactor\u002Fskills\u002Fdeep-refactor\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M72YWZ1HEXSKQ7JCSVR2HPT0","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.","https:\u002F\u002Fgithub.com\u002Fcedricfarinazzo\u002Fagile-skills\u002Fblob\u002Fmaster\u002Fagile-sprint-drain\u002Fskills\u002Fagile-sprint-drain\u002FSKILL.md",[],[]]