[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79DNZ2W6W4BFZW7WZ7SQ3ZP":3,"skill-same:01M79DNZ2W6W4BFZW7WZ7SQ3ZP":85},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":14,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":52,"updatedAt":53,"install":54,"resources":66},"01M79DNZ2W6W4BFZW7WZ7SQ3ZP","ba-story-verify",null,"Verify that BA-authored user stories are clear enough to build, and ask the BA the missing questions on the ticket. Takes a single ticket link or a list of tickets (or a JQL result set), scores each one independently against a user-story\u002Facceptance-criteria rubric, and drafts one comment of open questions per unclear ticket. When a comment is posted it also hands the ticket back: the reporter is @mentioned, made assignee, and the status is moved to a clarification state. Posted only after the operator approves; read-only until then, and it never plans, implements, or commits. An Epic link is routed to ba-epic-verify instead of expanded. Trigger: verify user story, check requirements clarity, is this ticket clear, ask the BA, DoR check, PROJ-123 clear enough. Do NOT load for: verifying an Epic (use ba-epic-verify), implementing a requirement (use harness-flow), bug triage (use harness-bugfix), code review, or release.","foden303\u002Fharness","foden303","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F77870743?v=4","01M79DK06BJVG7HTKT05FM221X","Foden Ngo","01M79DK071J1HMYV20FJSMG71X",0,"MIT","https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Fskills\u002Fba-story-verify\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ba-story-verify\ndescription: \"Verify that BA-authored user stories are clear enough to build, and ask the BA the missing questions on the ticket. Takes a single ticket link or a list of tickets (or a JQL result set), scores each one independently against a user-story\u002Facceptance-criteria rubric, and drafts one comment of open questions per unclear ticket. When a comment is posted it also hands the ticket back: the reporter is @mentioned, made assignee, and the status is moved to a clarification state. Posted only after the operator approves; read-only until then, and it never plans, implements, or commits. An Epic link is routed to ba-epic-verify instead of expanded. Trigger: verify user story, check requirements clarity, is this ticket clear, ask the BA, DoR check, PROJ-123 clear enough. Do NOT load for: verifying an Epic (use ba-epic-verify), implementing a requirement (use harness-flow), bug triage (use harness-bugfix), code review, or release.\"\ndescription-en: \"Verify that BA-authored user stories are clear enough to build, and ask the BA the missing questions on the ticket. Takes a single ticket link or a list of tickets (or a JQL result set), scores each one independently against a user-story\u002Facceptance-criteria rubric, and drafts one comment of open questions per unclear ticket. When a comment is posted it also hands the ticket back: the reporter is @mentioned, made assignee, and the status is moved to a clarification state. Posted only after the operator approves; read-only until then, and it never plans, implements, or commits. An Epic link is routed to ba-epic-verify instead of expanded. Trigger: verify user story, check requirements clarity, is this ticket clear, ask the BA, DoR check, PROJ-123 clear enough. Do NOT load for: verifying an Epic (use ba-epic-verify), implementing a requirement (use harness-flow), bug triage (use harness-bugfix), code review, or release.\"\nkind: workflow\npurpose: \"Verify a ticket list against the US\u002FAC rubric -> draft BA questions per unclear ticket -> operator approves -> post comments + hand the ticket back to its reporter -> track replies\"\ntrigger: \"verify user story, is this ticket clear, ask the BA, DoR check\"\nshape: delegate\nrole: orchestrator\nbase: harness-flow\npair: ba-epic-verify\nowner: harness-core\nsince: \"2026-07-20\"\nallowed-tools: [\"Read\", \"Write\", \"Edit\", \"Bash\", \"Grep\", \"Glob\", \"Task\", \"AskUserQuestion\", \"ScheduleWakeup\", \"mcp__claude_ai_Atlassian_Rovo__*\"]\nargument-hint: \"[\u003CISSUE-KEY>|\u003Curl> ...] [--jql \\\"...\\\"] [--ask-status \\\"\u003Cname>\\\"] [--no-handoff] [--resume] [--report-only] [--html] [--dry-run]\"\nuser-invocable: true\neffort: high\n---\n\n# ba-story-verify\n\nThe requirements-quality gate that runs **before** anyone starts building:\n\n> **Ticket link(s) → verify each story independently → draft the open questions\n> per ticket → operator approves → post to the BA + hand the ticket back to its\n> reporter → track replies → re-verify.**\n\nIt is the \"verify + ask the BA\" half of `harness-flow`, lifted out and scaled to\na list of stories. It stops at a clear\u002Funclear verdict — **it never plans, writes\ncode, or commits.** When a ticket comes back clear, hand it to `harness-flow` to\nbuild it.\n\n| | harness-flow | ba-story-verify | ba-epic-verify |\n|---|---|---|---|\n| Unit | one feature | **N independent stories** | one Epic |\n| Multiple links | merged into **one** feature | verified independently | n\u002Fa |\n| Epic link | not expanded | **routed out** to `ba-epic-verify` | the target |\n| Questions | one set | one set per ticket | **one set per lens** (BE\u002FFE\u002FBA) |\n| Ends at | committed change | **verdict + questions on the ticket** | verdict + questions on the Epic |\n\n## Core contract (read first)\n\n- **Read-only until you approve.** Fetching issues and scoring them writes\n  nothing to JIRA. The external writes — the clarification comment and the\n  reporter handoff (assignee + status) — are drafted, shown to you, and sent\n  **only** on an explicit approval\n  (`.claude\u002Frules\u002Fautonomous-confirmation-scope.md` case 1). Nothing auto-posts\n  and nothing auto-transitions.\n- **One ticket = one verdict = one comment.** Questions are never pooled across\n  tickets; a question about `PROJ-124` is posted on `PROJ-124`.\n- **Stories only.** An Epic ref is routed to `ba-epic-verify`, never scored\n  here — an Epic has no acceptance criteria of its own, so these gates would fail\n  for the wrong reasons.\n- **Questions must trace to a failing gate.** Every question in the draft comes\n  from a gate that failed. No gate failure, no question — this keeps the BA from\n  being asked things the ticket already answers.\n- **No requirement invention.** When a field is missing, ask; never fill in a\n  plausible acceptance criterion and proceed. A guessed AC is worse than a\n  missing one because it looks answered.\n- **Re-entrant.** Batch cursor + per-ticket records live under\n  `.claude\u002Fstate\u002Fstory-verify\u002F\u003Cbatch-id>\u002F`; a re-run resumes and never re-posts\n  a question already asked.\n- **MCP dependency.** JIRA access uses the Atlassian Rovo MCP tools. Absent\n  (headless\u002Fcron) → tri-state health reports `not-configured` and the skill\n  pauses at the first step that needs it rather than guessing.\n\n## Quick Reference\n\n| Input | Behavior |\n|------|------|\n| `\u002Fba-story-verify PROJ-123` | Verify that one story |\n| `\u002Fba-story-verify PROJ-123 PROJ-124 PROJ-125` | Verify all three **independently** (not merged) |\n| `\u002Fba-story-verify https:\u002F\u002F\u003Csite>\u002Fbrowse\u002FPROJ-123` | Same, from a URL |\n| `\u002Fba-story-verify PROJ-100` (an Epic) | **Route out**: recommend `\u002Fba-epic-verify PROJ-100`, verify nothing |\n| `\u002Fba-story-verify --jql \"parent = PROJ-100 AND status = 'To Do'\"` | Verify the JQL result set |\n| `\u002Fba-story-verify PROJ-123 --ask-status \"Waiting for BA\"` | Force the status the handoff moves to |\n| `\u002Fba-story-verify PROJ-123 --no-handoff` | Comment only; do not touch assignee or status |\n| `\u002Fba-story-verify --resume` | Re-check for BA replies, fold them in, re-verify |\n| `\u002Fba-story-verify PROJ-123 --report-only` | Verify + report, never offer to post (no JIRA writes at all) |\n| `\u002Fba-story-verify PROJ-123 --html` | Also render the report as a single-file HTML |\n| `\u002Fba-story-verify PROJ-123 --dry-run` | Walk the flow, write no state and no comments |\n\n## Options\n\n| Option | Description | Default |\n|--------|-------------|---------|\n| `\u003CISSUE-KEY>` \u002F `\u003Curl>` | Verification target(s) — stories, not Epics | required (unless `--resume` \u002F `--jql`) |\n| `--jql \"\u003Cquery>\"` | Use a JQL result set as the batch | - |\n| `--ask-status \"\u003Cname>\"` | Status the handoff transitions to | matched from a candidate list |\n| `--no-handoff` | Never change assignee or status | off (handoff on) |\n| `--resume` | Re-check BA replies on the existing batch | - |\n| `--report-only` | Never post; output the report only | off |\n| `--html` | Also render `story-verify-report.html` | off |\n| `--dry-run` | No state writes, no comments | off |\n| `--include-done` | Also verify tickets in a done\u002Fclosed status | off (skipped) |\n\n## Resolving the plugin bundle root\n\nSame as `harness-flow`: resolve `HARNESS_PLUGIN_ROOT` from `CLAUDE_PLUGIN_ROOT`\n(if it contains `scripts\u002F`), else from `CLAUDE_SKILL_DIR`\n(`${CLAUDE_SKILL_DIR}\u002F..\u002F..`, or `..\u002F..\u002F..` for a mirror). Call only\n`${HARNESS_PLUGIN_ROOT}\u002Fscripts\u002F...`; keep state under the host project's\n`.claude\u002Fstate\u002Fstory-verify\u002F`.\n\n## State machine\n\nBatch cursor: `.claude\u002Fstate\u002Fstory-verify\u002F\u003Cbatch-id>\u002Fbatch.json`, managed only\nthrough `${HARNESS_PLUGIN_ROOT}\u002Fscripts\u002Fstory-verify-batch.sh`.\nPer-ticket verdicts: `.claude\u002Fstate\u002Fstory-verify\u002F\u003Cbatch-id>\u002F\u003CKEY>.json`\n(`story-verification.v1`), written only through\n`${HARNESS_PLUGIN_ROOT}\u002Fscripts\u002Fstory-verify-record.sh`.\n`\u003Cbatch-id>` is derived from the root ref (a bare list → the first key\nlowercased, `PROJ-101` → `proj-101`; `--jql` → `jql-\u003Cn>` where `\u003Cn>` is the\nticket count; called from `ba-epic-verify --with-children` → the Epic key).\n\n```\n[Step 0] Resolve + probe\n  Resolve HARNESS_PLUGIN_ROOT.\n  Probe MCP once:\n    bash \"${HARNESS_PLUGIN_ROOT}\u002Fscripts\u002Fflow-mcp-health.sh\" --probe \u003Cresult>\n    (getAccessibleAtlassianResources: success -> healthy, error -> unreachable,\n     tools absent -> not-configured)\n  not-configured \u002F unreachable -> decision_needed.v1 and STOP. Never guess.\n  |\n  v\n[Step 1] Resolve targets -> batch.json\n  Reference: references\u002Ftarget-list.md\n  Ticket keys -> that exact list, deduped, order preserved\n  --jql       -> the query result set\n  Epic key    -> STOP and route to \u002Fba-epic-verify (do not expand, do not score)\n  Skip done\u002Fclosed tickets unless --include-done; skip sub-tasks of a listed ticket.\n  story-verify-batch.sh init --batch-id \u003Cid> --mode tickets \\\n    --root \u003Cref> --keys \u003Ck1,k2,...>\n  Report the target list (n in scope \u002F n skipped and why) BEFORE verifying.\n  |\n  v\n[Step 2] Verify each   -> \u003CKEY>.json (state: clear | needs-clarification | blocked)\n  Reference: references\u002Fus-rubric.md   (13 gates, 9 blocker + 4 advisory)\n  Per ticket: getJiraIssue (summary, description, AC field, labels, type, status,\n    reporter, parent, links, attachments\u002Fdesign links, comments).\n  Score every gate to pass | fail | n-a(+note). Each failing blocker contributes\n  >=1 concrete question. Persist via story-verify-record.sh (it derives the\n  verdict from the gates — do not hand-write it).\n  Tickets are independent: verify all of them before asking anything.\n  For a batch of >=6 tickets, fan out with Task (one sub-agent per ticket,\n  read-only) and collect the records; \u003C6 -> verify in-context.\n  |\n  v\n[Step 3] Report        Reference: references\u002Freport.md\n  One table: ticket | verdict | failing gates | #questions.\n  --html -> render a single-file HTML alongside it.\n  --report-only -> STOP here.\n  |\n  v\n[Step 4] Approve + post + handoff   state: needs-clarification -> awaiting-ba\n  Reference: references\u002Fba-comment.md\n  Draft ONE marked comment per unclear ticket (reporter @mentioned), show ALL\n  drafts to the operator in one AskUserQuestion (post all \u002F pick \u002F edit \u002F skip),\n  and post ONLY what was approved (addCommentToJiraIssue). Never auto-post.\n  Then per posted ticket, unless --no-handoff:\n    editJiraIssue       assignee = reporter\n    transitionJiraIssue status -> the one chosen by jira-status-match.sh\n  A missing transition or a missing reporter is a recorded skip, never a failure.\n  |\n  v\n[Step 5] Track replies    state: awaiting-ba -> answered | needs-clarification\n  Reference: references\u002Fba-comment.md (resume section)\n  ScheduleWakeup re-entry: re-fetch comments, match via flow-ba-match.sh, fold the\n  reply into the ticket record, re-run Step 2 for that ticket only.\n  Re-verify clear -> answered. Still failing -> follow-up (round cap 3) -> escalated.\n  |\n  v\n[Done] All tickets terminal -> final summary + next action\n  story-verify-batch.sh summary \u003Cbatch.json>\n```\n\n## Stop \u002F pause conditions\n\n| Condition | State | Response |\n|-----------|-------|----------|\n| MCP not-configured \u002F unreachable | unchanged | `decision_needed.v1`, stop |\n| A ticket cannot be read (permission) | `blocked` | Record verdict `blocked`, continue the rest, list them in the summary |\n| The ref is an Epic | n\u002Fa | Report the type, recommend `\u002Fba-epic-verify \u003CKEY>`, stop |\n| The target list is empty after filtering | n\u002Fa | Report the counts per reason and stop (do not fall back to a broader JQL) |\n| Operator declines to post | `needs-clarification` | Keep the draft in the report; the operator asks the BA themselves. No handoff |\n| Transition unavailable | `awaiting-ba` | Post + assign anyway, record `transition_skipped_reason`, name it in the summary |\n| Reporter missing on the ticket | `awaiting-ba` | Skip the assign, record `assign_skipped_reason`, still post and still transition |\n| BA reply not yet available | `awaiting-ba` | Auto-poll (ScheduleWakeup) or wait for `--resume` |\n| Clarification round cap (3) reached | `escalated` | `decision_needed.v1` — proceed on a stated assumption, keep waiting, or drop |\n\n## Silence policy\n\nReport on: the target list, per-ticket verdict, the draft set before approval,\nwhat was posted, the handoff result per ticket (assignee + status, or why\nskipped), replies folded in, final summary. Stay silent on: per-gate scoring\nnarration, pacing waits between reply checks with nothing new. Always end a\ncompleted run by naming the clear\u002Funclear\u002Fblocked counts and the next action\n(hand the clear tickets to `harness-flow`, or wait on the open questions).\n\n## Related skills\n\n- `ba-epic-verify` — the Epic sibling: epic rubric + BE\u002FFE\u002FBA lens questions\n- `harness-flow` — build a ticket once it is verified clear (Steps 4-9 there)\n- `harness-bugfix` — the bug sibling (triage vs source, QA ask-back)\n- `harness-plan` — turn verified stories into Plans.md tasks\n- `harness-accept` — acceptance decision after the work is delivered\n","# ba-story-verify\n\nThe requirements-quality gate that runs **before** anyone starts building:\n\n> **Ticket link(s) → verify each story independently → draft the open questions\n> per ticket → operator approves → post to the BA + hand the ticket back to its\n> reporter → track replies → re-verify.**\n\nIt is the \"verify + ask the BA\" half of `harness-flow`, lifted out and scaled to\na list of stories. It stops at a clear\u002Funclear verdict — **it never plans, writes\ncode, or commits.** When a ticket comes back clear, hand it to `harness-flow` to\nbuild it.\n\n| | harness-flow | ba-story-verify | ba-epic-verify |\n|---|---|---|---|\n| Unit | one feature | **N independent stories** | one Epic |\n| Multiple links | merged into **one** feature | verified independently | n\u002Fa |\n| Epic link | not expanded | **routed out** to `ba-epic-verify` | the target |\n| Questions | one set | one set per ticket | **one set per lens** (BE\u002FFE\u002FBA) |\n| Ends at | committed change | **verdict + questions on the ticket** | verdict + questions on the Epic |\n\n## Core contract (read first)\n\n- **Read-only until you approve.** Fetching issues and scoring them writes\n  nothing to JIRA. The external writes — the clarification comment and the\n  reporter handoff (assignee + status) — are drafted, shown to you, and sent\n  **only** on an explicit approval\n  (`.claude\u002Frules\u002Fautonomous-confirmation-scope.md` case 1). Nothing auto-posts\n  and nothing auto-transitions.\n- **One ticket = one verdict = one comment.** Questions are never pooled across\n  tickets; a question about `PROJ-124` is posted on `PROJ-124`.\n- **Stories only.** An Epic ref is routed to `ba-epic-verify`, never scored\n  here — an Epic has no acceptance criteria of its own, so these gates would fail\n  for the wrong reasons.\n- **Questions must trace to a failing gate.** Every question in the draft comes\n  from a gate that failed. No gate failure, no question — this keeps the BA from\n  being asked things the ticket already answers.\n- **No requirement invention.** When a field is missing, ask; never fill in a\n  plausible acceptance criterion and proceed. A guessed AC is worse than a\n  missing one because it looks answered.\n- **Re-entrant.** Batch cursor + per-ticket records live under\n  `.claude\u002Fstate\u002Fstory-verify\u002F\u003Cbatch-id>\u002F`; a re-run resumes and never re-posts\n  a question already asked.\n- **MCP dependency.** JIRA access uses the Atlassian Rovo MCP tools. Absent\n  (headless\u002Fcron) → tri-state health reports `not-configured` and the skill\n  pauses at the first step that needs it rather than guessing.\n\n## Quick Reference\n\n| Input | Behavior |\n|------|------|\n| `\u002Fba-story-verify PROJ-123` | Verify that one story |\n| `\u002Fba-story-verify PROJ-123 PROJ-124 PROJ-125` | Verify all three **independently** (not merged) |\n| `\u002Fba-story-verify https:\u002F\u002F\u003Csite>\u002Fbrowse\u002FPROJ-123` | Same, from a URL |\n| `\u002Fba-story-verify PROJ-100` (an Epic) | **Route out**: recommend `\u002Fba-epic-verify PROJ-100`, verify nothing |\n| `\u002Fba-story-verify --jql \"parent = PROJ-100 AND status = 'To Do'\"` | Verify the JQL result set |\n| `\u002Fba-story-verify PROJ-123 --ask-status \"Waiting for BA\"` | Force the status the handoff moves to |\n| `\u002Fba-story-verify PROJ-123 --no-handoff` | Comment only; do not touch assignee or status |\n| `\u002Fba-story-verify --resume` | Re-check for BA replies, fold them in, re-verify |\n| `\u002Fba-story-verify PROJ-123 --report-only` | Verify + report, never offer to post (no JIRA writes at all) |\n| `\u002Fba-story-verify PROJ-123 --html` | Also render the report as a single-file HTML |\n| `\u002Fba-story-verify PROJ-123 --dry-run` | Walk the flow, write no state and no comments |\n\n## Options\n\n| Option | Description | Default |\n|--------|-------------|---------|\n| `\u003CISSUE-KEY>` \u002F `\u003Curl>` | Verification target(s) — stories, not Epics | required (unless `--resume` \u002F `--jql`) |\n| `--jql \"\u003Cquery>\"` | Use a JQL result set as the batch | - |\n| `--ask-status \"\u003Cname>\"` | Status the handoff transitions to | matched from a candidate list |\n| `--no-handoff` | Never change assignee or status | off (handoff on) |\n| `--resume` | Re-check BA replies on the existing batch | - |\n| `--report-only` | Never post; output the report only | off |\n| `--html` | Also render `story-verify-report.html` | off |\n| `--dry-run` | No state writes, no comments | off |\n| `--include-done` | Also verify tickets in a done\u002Fclosed status | off (skipped) |\n\n## Resolving the plugin bundle root\n\nSame as `harness-flow`: resolve `HARNESS_PLUGIN_ROOT` from `CLAUDE_PLUGIN_ROOT`\n(if it contains `scripts\u002F`), else from `CLAUDE_SKILL_DIR`\n(`${CLAUDE_SKILL_DIR}\u002F..\u002F..`, or `..\u002F..\u002F..` for a mirror). Call only\n`${HARNESS_PLUGIN_ROOT}\u002Fscripts\u002F...`; keep state under the host project's\n`.claude\u002Fstate\u002Fstory-verify\u002F`.\n\n## State machine\n\nBatch cursor: `.claude\u002Fstate\u002Fstory-verify\u002F\u003Cbatch-id>\u002Fbatch.json`, managed only\nthrough `${HARNESS_PLUGIN_ROOT}\u002Fscripts\u002Fstory-verify-batch.sh`.\nPer-ticket verdicts: `.claude\u002Fstate\u002Fstory-verify\u002F\u003Cbatch-id>\u002F\u003CKEY>.json`\n(`story-verification.v1`), written only through\n`${HARNESS_PLUGIN_ROOT}\u002Fscripts\u002Fstory-verify-record.sh`.\n`\u003Cbatch-id>` is derived from the root ref (a bare list → the first key\nlowercased, `PROJ-101` → `proj-101`; `--jql` → `jql-\u003Cn>` where `\u003Cn>` is the\nticket count; called from `ba-epic-verify --with-children` → the Epic key).\n\n```\n[Step 0] Resolve + probe\n  Resolve HARNESS_PLUGIN_ROOT.\n  Probe MCP once:\n    bash \"${HARNESS_PLUGIN_ROOT}\u002Fscripts\u002Fflow-mcp-health.sh\" --probe \u003Cresult>\n    (getAccessibleAtlassianResources: success -> healthy, error -> unreachable,\n     tools absent -> not-configured)\n  not-configured \u002F unreachable -> decision_needed.v1 and STOP. Never guess.\n  |\n  v\n[Step 1] Resolve targets -> batch.json\n  Reference: references\u002Ftarget-list.md\n  Ticket keys -> that exact list, deduped, order preserved\n  --jql       -> the query result set\n  Epic key    -> STOP and route to \u002Fba-epic-verify (do not expand, do not score)\n  Skip done\u002Fclosed tickets unless --include-done; skip sub-tasks of a listed ticket.\n  story-verify-batch.sh init --batch-id \u003Cid> --mode tickets \\\n    --root \u003Cref> --keys \u003Ck1,k2,...>\n  Report the target list (n in scope \u002F n skipped and why) BEFORE verifying.\n  |\n  v\n[Step 2] Verify each   -> \u003CKEY>.json (state: clear | needs-clarification | blocked)\n  Reference: references\u002Fus-rubric.md   (13 gates, 9 blocker + 4 advisory)\n  Per ticket: getJiraIssue (summary, description, AC field, labels, type, status,\n    reporter, parent, links, attachments\u002Fdesign links, comments).\n  Score every gate to pass | fail | n-a(+note). Each failing blocker contributes\n  >=1 concrete question. Persist via story-verify-record.sh (it derives the\n  verdict from the gates — do not hand-write it).\n  Tickets are independent: verify all of them before asking anything.\n  For a batch of >=6 tickets, fan out with Task (one sub-agent per ticket,\n  read-only) and collect the records; \u003C6 -> verify in-context.\n  |\n  v\n[Step 3] Report        Reference: references\u002Freport.md\n  One table: ticket | verdict | failing gates | #questions.\n  --html -> render a single-file HTML alongside it.\n  --report-only -> STOP here.\n  |\n  v\n[Step 4] Approve + post + handoff   state: needs-clarification -> awaiting-ba\n  Reference: references\u002Fba-comment.md\n  Draft ONE marked comment per unclear ticket (reporter @mentioned), show ALL\n  drafts to the operator in one AskUserQuestion (post all \u002F pick \u002F edit \u002F skip),\n  and post ONLY what was approved (addCommentToJiraIssue). Never auto-post.\n  Then per posted ticket, unless --no-handoff:\n    editJiraIssue       assignee = reporter\n    transitionJiraIssue status -> the one chosen by jira-status-match.sh\n  A missing transition or a missing reporter is a recorded skip, never a failure.\n  |\n  v\n[Step 5] Track replies    state: awaiting-ba -> answered | needs-clarification\n  Reference: references\u002Fba-comment.md (resume section)\n  ScheduleWakeup re-entry: re-fetch comments, match via flow-ba-match.sh, fold the\n  reply into the ticket record, re-run Step 2 for that ticket only.\n  Re-verify clear -> answered. Still failing -> follow-up (round cap 3) -> escalated.\n  |\n  v\n[Done] All tickets terminal -> final summary + next action\n  story-verify-batch.sh summary \u003Cbatch.json>\n```\n\n## Stop \u002F pause conditions\n\n| Condition | State | Response |\n|-----------|-------|----------|\n| MCP not-configured \u002F unreachable | unchanged | `decision_needed.v1`, stop |\n| A ticket cannot be read (permission) | `blocked` | Record verdict `blocked`, continue the rest, list them in the summary |\n| The ref is an Epic | n\u002Fa | Report the type, recommend `\u002Fba-epic-verify \u003CKEY>`, stop |\n| The target list is empty after filtering | n\u002Fa | Report the counts per reason and stop (do not fall back to a broader JQL) |\n| Operator declines to post | `needs-clarification` | Keep the draft in the report; the operator asks the BA themselves. No handoff |\n| Transition unavailable | `awaiting-ba` | Post + assign anyway, record `transition_skipped_reason`, name it in the summary |\n| Reporter missing on the ticket | `awaiting-ba` | Skip the assign, record `assign_skipped_reason`, still post and still transition |\n| BA reply not yet available | `awaiting-ba` | Auto-poll (ScheduleWakeup) or wait for `--resume` |\n| Clarification round cap (3) reached | `escalated` | `decision_needed.v1` — proceed on a stated assumption, keep waiting, or drop |\n\n## Silence policy\n\nReport on: the target list, per-ticket verdict, the draft set before approval,\nwhat was posted, the handoff result per ticket (assignee + status, or why\nskipped), replies folded in, final summary. Stay silent on: per-gate scoring\nnarration, pacing waits between reply checks with nothing new. Always end a\ncompleted run by naming the clear\u002Funclear\u002Fblocked counts and the next action\n(hand the clear tickets to `harness-flow`, or wait on the open questions).\n\n## Related skills\n\n- `ba-epic-verify` — the Epic sibling: epic rubric + BE\u002FFE\u002FBA lens questions\n- `harness-flow` — build a ticket once it is verified clear (Steps 4-9 there)\n- `harness-bugfix` — the bug sibling (triage vs source, QA ask-back)\n- `harness-plan` — turn verified stories into Plans.md tasks\n- `harness-accept` — acceptance decision after the work is delivered\n",{"base":24,"kind":25,"name":5,"pair":26,"role":27,"owner":28,"shape":29,"since":30,"effort":31,"purpose":32,"trigger":33,"description":7,"allowed-tools":34,"argument-hint":45,"description-en":7,"user-invocable":46},"harness-flow","workflow","ba-epic-verify","orchestrator","harness-core","delegate","2026-07-20","high","Verify a ticket list against the US\u002FAC rubric -> draft BA questions per unclear ticket -> operator approves -> post comments + hand the ticket back to its reporter -> track replies","verify user story, is this ticket clear, ask the BA, DoR check",[35,36,37,38,39,40,41,42,43,44],"Read","Write","Edit","Bash","Grep","Glob","Task","AskUserQuestion","ScheduleWakeup","mcp__claude_ai_Atlassian_Rovo__*","[\u003CISSUE-KEY>|\u003Curl> ...] [--jql \"...\"] [--ask-status \"\u003Cname>\"] [--no-handoff] [--resume] [--report-only] [--html] [--dry-run]",true,"main","3517f6fc9c5159f32d585682386ed45e35c30ddf","skills\u002Fba-story-verify","https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness","https:\u002F\u002Fgithub.com\u002Ffoden303","Software Engineer","2026-11-06 10:59:21",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":46},[56,59,62],{"tool":57,"command":58},"npx","npx skills add foden303\u002Fharness --skill ba-story-verify",{"tool":60,"command":61},"bunx","bunx skills add foden303\u002Fharness --skill ba-story-verify",{"tool":63,"command":64},"pnpm","pnpm dlx skills add foden303\u002Fharness --skill ba-story-verify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Fskills\u002Fba-story-verify\u002FSKILL.md",[67,73,77,81],{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fba-comment.md","REFERENCE","参考文档",9318,"https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Fskills\u002Fba-story-verify\u002Freferences\u002Fba-comment.md",{"path":74,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Freport.md",4580,"https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Fskills\u002Fba-story-verify\u002Freferences\u002Freport.md",{"path":78,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Ftarget-list.md",4620,"https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Fskills\u002Fba-story-verify\u002Freferences\u002Ftarget-list.md",{"path":82,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fus-rubric.md",7159,"https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Fskills\u002Fba-story-verify\u002Freferences\u002Fus-rubric.md",[86,92,98,105,112,119],{"skillNo":87,"name":88,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M79DWR27RWW11HNKY0MRECPP","escape-skill","https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fzz-review-escape\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M79DWPSR8ZK3V4DQK5EWVJ3K","zz-review-empty","https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fzz-review-empty\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M79DWFV6PYV0QEZ3SC32VMCM","memory","Manage SSOT, memory, and cross-tool memory search. Guardian of decisions.md and patterns.md. Use when user mentions memory, SSOT, decisions.md, patterns.md, merging, migration, SSOT promotion, sync memory, save learnings, memory search, harness-mem, past decisions, or record this. Do NOT load for: implementation work, reviews, ad-hoc notes, or in-session logging.","https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Fskills\u002Fmemory\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M79DWB6MB7EQK2JT4A84NHJD","maintenance","File cleanup and archiving. Tidies up bloated Plans.md, session-log.md, old logs, and state files. Trigger: \u002Fmaintenance, cleanup, archive, organize, split session-log. Do NOT load for: implementation, review, release, new feature development.","https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Fskills\u002Fmaintenance\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":19},"01M79DW33AEPBCXFAMX8YH56PG","harness-work","HAR: Execute Plans.md tasks from single task to full parallel team run. Trigger: implement, execute, do everything, breezing, team run, parallel. Do NOT load for: planning, review, release, setup.","https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Fskills\u002Fharness-work\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":19},"01M79DVWV7PZC0E2GYC103QBYZ","harness-sync","HAR: Sync Plans.md with implementation. Drift detect, marker update, retrospective. Trigger: sync-status, where am I, check progress. --snapshot for snapshots. Do NOT load for: planning, implementation, review, release.","https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Fskills\u002Fharness-sync\u002FSKILL.md",[],[]]