[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DXRE57JMP1NMZ2MM241NW1":3,"skill-same:01M6DXRE57JMP1NMZ2MM241NW1":93},{"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":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":61,"ownerHtmlUrl":62,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":63,"install":64,"resources":76},"01M6DXRE57JMP1NMZ2MM241NW1","create-jira-issue",null,"Use this skill only when the user explicitly invokes \u002Fcreate-jira-issue to create a new Jira issue. This is a write skill with irreversible side effects — it must never be auto-invoked from conversational context. Accepts a project key, issue type, summary, optional Markdown body, and optional fields (assignee, reporter, priority, labels, components, parent, custom fields). Previews the resolved intent, requires explicit confirmation, then POSTs to Jira and returns the new issue key.","atomicinnovation\u002Faccelerator","atomicinnovation","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F65866524?v=4","01M6DXP513JV585FN2QPNR6079","Atomic","01M6DXP55MPK99YVZ2HGMEN991",34,"MIT","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fintegrations\u002Fjira\u002Fcreate-jira-issue\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"jira","create","create jira issue","issue","new","components","when","effects","jira-issue","labels","posts","id","type","project","me","intent","only","never","auto","use","confirmation","text","markdown","Bash","file","component","2026-11-10 10:12:30",false,"---\nname: create-jira-issue\ndescription: >\n  Use this skill only when the user explicitly invokes \u002Fcreate-jira-issue to\n  create a new Jira issue. This is a write skill with irreversible side effects\n  — it must never be auto-invoked from conversational context. Accepts a project\n  key, issue type, summary, optional Markdown body, and optional fields\n  (assignee, reporter, priority, labels, components, parent, custom fields).\n  Previews the resolved intent, requires explicit confirmation, then POSTs to\n  Jira and returns the new issue key.\nargument-hint: \"[--project KEY] --type NAME --summary TEXT [--body TEXT | --body-file PATH] [--assignee @me|ACCTID] [--reporter @me|ACCTID] [--priority NAME] [--label NAME]... [--component NAME]... [--parent KEY] [--custom SLUG=VALUE]... [--issuetype-id ID]\"\ndisable-model-invocation: true\nallowed-tools:\n  - Bash\n  - Read\n  - Write\n---\n\n# Create Jira Issue\n\n!`accelerator config context --skill create-jira-issue --fail-safe`\n\n> **Configuration**: Set `work.integration: jira` and\n> `jira.project_key: \u003CKEY>` in `.accelerator\u002Fconfig.md` to\n> enable auto-scoping. See the\n> [`### work` section of `configure\u002FSKILL.md`](..\u002F..\u002Fconfig\u002Fconfigure\u002FSKILL.md#work)\n> for the full reference.\n\nCreate a new Jira issue via `POST \u002Frest\u002Fapi\u002F3\u002Fissue`. Work through the steps\nbelow in order. This skill never auto-invokes — it only runs when the user\nexplicitly types `\u002Fcreate-jira-issue`.\n\nThis skill never synthesises `--body` content from upstream context (issue\ndescriptions, web fetches, prior tool output) without explicit user approval —\nbody content always comes from the user's prompt or a path the user named.\n\n## Two modes\n\nThis skill accepts **either** a work-item file or the explicit flag set:\n\n- **Work-item-file mode** — the argument is a path to a `meta\u002Fwork\u002F` work item.\n  The summary, body, type, and project are derived from the work item, and the\n  created issue's key is written back into its `external_id`. Follow the\n  **Work-item-file mode** section.\n- **Flag-driven mode** — the argument is the `--project\u002F--type\u002F--summary\u002F…` flag\n  set (no work-item file). Follow **Steps 1–9**; it writes nothing back to any\n  file.\n\nBoth modes share one create contract: read\u002Fpreview\u002Fconfirm\u002Fcreate, mirroring\n`\u002Fcreate-linear-issue` in shape.\n\n## Work-item-file mode\n\n### WF-1: Resolve the issue type and project\n\nRun the read-only resolver against the work-item file (pass `--project KEY` only\nif the user explicitly overrode it):\n\n```\naccelerator jira resolve-fields --file \u003Cwork-item-file>\n```\n\nRun the bare launcher **directly** as an executable; never prefix it with\n`bash`\u002F`sh`\u002F`env` and never pipe its output. It prints one tab-separated line\n`\u003Cissue_type>\\t\u003Cissue_type_source>\\t\u003Cproject>\\t\u003Cproject_source>`. This is the\nkind→issue-type map and project resolution read from the `config` crate — the\n**same resolution path** `accelerator work create --push --dry-run` renders (it\nemits the same fields prefixed by the tracker name), so the two entry points can\nnever disagree. Handle a non-zero exit **before** any preview or create:\n\n- `E_RESOLVE_ALREADY_SYNCED` — the work item already carries a non-empty\n  `external_id`. STOP; tell the user it is already synced and name the existing\n  identifier. Make no API call.\n- `E_RESOLVE_NO_PROJECT` — the project is unresolvable. STOP and tell the user\n  to pass `--project KEY` or set `jira.project_key`. This is a\n  pre-create failure — do not proceed to the confirm gate.\n\nOn success, capture the four resolved values and continue.\n\n### WF-2: Preview the resolved intent\n\nRead the work item's `title` (the summary) and Markdown body (the description).\nShow, under **Proposed Jira write — review before sending**:\n\n- the resolved **issue type**, and — when `issue_type_source` is `default` —\n  that the kind fell through, e.g. `kind \"spike\" → Task (default)`;\n- the resolved **project** and which source it came from (`project_source`);\n- the summary and the (≤500-char-truncated) description.\n\n### WF-3: Confirm before writing\n\nAsk the user to reply **y** to confirm, or anything else to abort:\n`Create this Jira issue and set the work item's external_id?` Exactly `y`\u002F`yes`\nproceeds; anything else aborts with \"Aborted — no Jira write was made.\"\n\n### WF-4: Create and write back\n\nOn confirmation, create via the bare-key projection, writing the work item's\nbody to a file for `--body-file`:\n\n```\naccelerator jira create --project \u003Cproject> --type \u003Cissue_type> \\\n  --summary \"\u003Ctitle>\" --body-file \u003Cbody-path> --emit key\n```\n\n`--emit key` prints **only** the bare issue key on success. Branch **fail-closed**:\n\n- a bare key on a clean run — the issue exists remotely. Write it into the work\n  item's `external_id` (insert the line if absent):\n\n  ```\n  accelerator work link-external-id \u003Cwork-item-file> \u003CKEY>\n  ```\n\n  Then report `Issue created: \u003CKEY> — the work item's external_id is now \u003CKEY>.`\n- `E_REQ_BAD_RESPONSE` on stderr — the issue **was** created remotely but its\n  key is unusable. Do **not** write `external_id`; surface this loudly, give the\n  user the key, and tell them NOT to re-run (it would create a duplicate) and to\n  reconcile `external_id` by hand.\n- any other non-zero exit — no issue was created. Do **not** write\n  `external_id`; report the error. The file is unchanged, so it is safe to fix\n  and retry.\n\nThe create-then-writeback sequence is **non-atomic**: if the create succeeds but\nthe `work link-external-id` writeback fails, surface it loudly — the\nissue exists remotely as `\u003CKEY>`, the user must NOT blindly re-run (it would\nduplicate), and they should set `external_id: \u003CKEY>` by hand.\n\n## Step 1: Parse the flag set\n\nRead the argument string and note each flag:\n\n- `--project KEY` — Jira project key (e.g. `ENG`)\n- `--type NAME` \u002F `--issuetype-id ID` — issue type by name or numeric id (the id\n  wins); one is required\n- `--summary TEXT` — single-line summary (required)\n- `--body TEXT` \u002F `--body-file PATH` — Markdown description\n- `--assignee @me|ACCTID` \u002F `--reporter @me|ACCTID` — `@me` resolves via\n  `site.json`; an email is refused\n- `--priority NAME`, `--label NAME` (repeatable), `--component NAME`\n  (repeatable), `--parent KEY`\n- `--custom SLUG=VALUE` — repeatable; custom field by slug, `@json:\u003Cliteral>`\n  for arrays\u002Fobjects\n\n## Step 2: Resolve --project\n\nIf `--project` was not supplied, the subcommand reads `jira.project_key`\nfrom config. If neither is set the create refuses before any call; warn the user\nto supply `--project KEY` or run `\u002Finit-jira` and set a default project.\n\n## Step 3: Trust-boundary enforcement\n\nBefore assembling `--body`, verify that any body content comes ONLY from text the\nuser typed in this turn or a file path they explicitly named this turn — never a\npreviously-fetched description, a web fetch, or a prior assistant message. If\ntheir phrasing implies \"use the description from above\", ask them to paste or\nconfirm the literal text first.\n\n## Step 4: Preview the resolved intent\n\nShow, under **Proposed Jira write — review before sending**: the project, issue\ntype, summary, the (≤500-char-truncated) description, and every resolved field\n(assignee\u002Freporter\u002Fpriority\u002Flabels\u002Fcomponents\u002Fparent\u002Fcustom). `@me` and custom\nslugs resolve inside the subcommand and are refused before any write if\nunresolvable.\n\n## Step 5: Confirm before writing\n\nAsk the user:\n\n> Send this to Jira? Reply **y** to confirm, **n** to revise, anything else\n> to abort.\n\nA clear `y`\u002F`yes` proceeds; a `n`\u002Frevise stays in review (re-apply Step 3 to any\nrevised body); anything ambiguous aborts with \"Aborted — no Jira write was\nmade.\"\n\n## Step 6: Send the request\n\n```\naccelerator jira create [all flags from Steps 1-2]\n```\n\n## Step 7: Render the response\n\nThe subcommand emits a JSON envelope `{key}` with a top-level `outcome` keyword.\nOn the `created` keyword, present:\n\n> Issue created: **\u003CKEY>**\n\n## Step 8: Error handling\n\nOn a non-zero exit, show the error, which names its cause on stderr:\n- `E_CREATE_NO_SUMMARY` — `--summary` is required;\n- `E_CREATE_BAD_FIELD` — a `--custom` value failed validation; run\n  `\u002Finit-jira --refresh-fields` if a field id was rejected;\n- `E_CREATE_NO_SITE_CACHE` — `@me` was used but `site.json` is missing; run\n  `\u002Finit-jira`;\n- `E_CREATE_BAD_ASSIGNEE` — `--assignee`\u002F`--reporter` accepts `@me` or a raw\n  accountId, not an email;\n- an auth or transport failure — suggest checking credentials with `\u002Finit-jira`.\n\n## Step 9: Examples\n\n**Example — minimal task**\nUser: `\u002Fcreate-jira-issue --project ENG --type Task --summary \"Fix login timeout\"`\nSkill previews the resolved intent, waits for `y`, then creates and renders\n`Issue created: ENG-456`.\n\n**Example — custom field with @json escape**\nUser: `\u002Fcreate-jira-issue --project ENG --type Task --summary \"Sprint task\" --custom sprint=@json:[42]`\nSkill coerces the sprint field as a JSON array literal, previews, confirms.\n\n!`accelerator config instructions create-jira-issue --fail-safe`\n","# Create Jira Issue\n\n!`accelerator config context --skill create-jira-issue --fail-safe`\n\n> **Configuration**: Set `work.integration: jira` and\n> `jira.project_key: \u003CKEY>` in `.accelerator\u002Fconfig.md` to\n> enable auto-scoping. See the\n> [`### work` section of `configure\u002FSKILL.md`](..\u002F..\u002Fconfig\u002Fconfigure\u002FSKILL.md#work)\n> for the full reference.\n\nCreate a new Jira issue via `POST \u002Frest\u002Fapi\u002F3\u002Fissue`. Work through the steps\nbelow in order. This skill never auto-invokes — it only runs when the user\nexplicitly types `\u002Fcreate-jira-issue`.\n\nThis skill never synthesises `--body` content from upstream context (issue\ndescriptions, web fetches, prior tool output) without explicit user approval —\nbody content always comes from the user's prompt or a path the user named.\n\n## Two modes\n\nThis skill accepts **either** a work-item file or the explicit flag set:\n\n- **Work-item-file mode** — the argument is a path to a `meta\u002Fwork\u002F` work item.\n  The summary, body, type, and project are derived from the work item, and the\n  created issue's key is written back into its `external_id`. Follow the\n  **Work-item-file mode** section.\n- **Flag-driven mode** — the argument is the `--project\u002F--type\u002F--summary\u002F…` flag\n  set (no work-item file). Follow **Steps 1–9**; it writes nothing back to any\n  file.\n\nBoth modes share one create contract: read\u002Fpreview\u002Fconfirm\u002Fcreate, mirroring\n`\u002Fcreate-linear-issue` in shape.\n\n## Work-item-file mode\n\n### WF-1: Resolve the issue type and project\n\nRun the read-only resolver against the work-item file (pass `--project KEY` only\nif the user explicitly overrode it):\n\n```\naccelerator jira resolve-fields --file \u003Cwork-item-file>\n```\n\nRun the bare launcher **directly** as an executable; never prefix it with\n`bash`\u002F`sh`\u002F`env` and never pipe its output. It prints one tab-separated line\n`\u003Cissue_type>\\t\u003Cissue_type_source>\\t\u003Cproject>\\t\u003Cproject_source>`. This is the\nkind→issue-type map and project resolution read from the `config` crate — the\n**same resolution path** `accelerator work create --push --dry-run` renders (it\nemits the same fields prefixed by the tracker name), so the two entry points can\nnever disagree. Handle a non-zero exit **before** any preview or create:\n\n- `E_RESOLVE_ALREADY_SYNCED` — the work item already carries a non-empty\n  `external_id`. STOP; tell the user it is already synced and name the existing\n  identifier. Make no API call.\n- `E_RESOLVE_NO_PROJECT` — the project is unresolvable. STOP and tell the user\n  to pass `--project KEY` or set `jira.project_key`. This is a\n  pre-create failure — do not proceed to the confirm gate.\n\nOn success, capture the four resolved values and continue.\n\n### WF-2: Preview the resolved intent\n\nRead the work item's `title` (the summary) and Markdown body (the description).\nShow, under **Proposed Jira write — review before sending**:\n\n- the resolved **issue type**, and — when `issue_type_source` is `default` —\n  that the kind fell through, e.g. `kind \"spike\" → Task (default)`;\n- the resolved **project** and which source it came from (`project_source`);\n- the summary and the (≤500-char-truncated) description.\n\n### WF-3: Confirm before writing\n\nAsk the user to reply **y** to confirm, or anything else to abort:\n`Create this Jira issue and set the work item's external_id?` Exactly `y`\u002F`yes`\nproceeds; anything else aborts with \"Aborted — no Jira write was made.\"\n\n### WF-4: Create and write back\n\nOn confirmation, create via the bare-key projection, writing the work item's\nbody to a file for `--body-file`:\n\n```\naccelerator jira create --project \u003Cproject> --type \u003Cissue_type> \\\n  --summary \"\u003Ctitle>\" --body-file \u003Cbody-path> --emit key\n```\n\n`--emit key` prints **only** the bare issue key on success. Branch **fail-closed**:\n\n- a bare key on a clean run — the issue exists remotely. Write it into the work\n  item's `external_id` (insert the line if absent):\n\n  ```\n  accelerator work link-external-id \u003Cwork-item-file> \u003CKEY>\n  ```\n\n  Then report `Issue created: \u003CKEY> — the work item's external_id is now \u003CKEY>.`\n- `E_REQ_BAD_RESPONSE` on stderr — the issue **was** created remotely but its\n  key is unusable. Do **not** write `external_id`; surface this loudly, give the\n  user the key, and tell them NOT to re-run (it would create a duplicate) and to\n  reconcile `external_id` by hand.\n- any other non-zero exit — no issue was created. Do **not** write\n  `external_id`; report the error. The file is unchanged, so it is safe to fix\n  and retry.\n\nThe create-then-writeback sequence is **non-atomic**: if the create succeeds but\nthe `work link-external-id` writeback fails, surface it loudly — the\nissue exists remotely as `\u003CKEY>`, the user must NOT blindly re-run (it would\nduplicate), and they should set `external_id: \u003CKEY>` by hand.\n\n## Step 1: Parse the flag set\n\nRead the argument string and note each flag:\n\n- `--project KEY` — Jira project key (e.g. `ENG`)\n- `--type NAME` \u002F `--issuetype-id ID` — issue type by name or numeric id (the id\n  wins); one is required\n- `--summary TEXT` — single-line summary (required)\n- `--body TEXT` \u002F `--body-file PATH` — Markdown description\n- `--assignee @me|ACCTID` \u002F `--reporter @me|ACCTID` — `@me` resolves via\n  `site.json`; an email is refused\n- `--priority NAME`, `--label NAME` (repeatable), `--component NAME`\n  (repeatable), `--parent KEY`\n- `--custom SLUG=VALUE` — repeatable; custom field by slug, `@json:\u003Cliteral>`\n  for arrays\u002Fobjects\n\n## Step 2: Resolve --project\n\nIf `--project` was not supplied, the subcommand reads `jira.project_key`\nfrom config. If neither is set the create refuses before any call; warn the user\nto supply `--project KEY` or run `\u002Finit-jira` and set a default project.\n\n## Step 3: Trust-boundary enforcement\n\nBefore assembling `--body`, verify that any body content comes ONLY from text the\nuser typed in this turn or a file path they explicitly named this turn — never a\npreviously-fetched description, a web fetch, or a prior assistant message. If\ntheir phrasing implies \"use the description from above\", ask them to paste or\nconfirm the literal text first.\n\n## Step 4: Preview the resolved intent\n\nShow, under **Proposed Jira write — review before sending**: the project, issue\ntype, summary, the (≤500-char-truncated) description, and every resolved field\n(assignee\u002Freporter\u002Fpriority\u002Flabels\u002Fcomponents\u002Fparent\u002Fcustom). `@me` and custom\nslugs resolve inside the subcommand and are refused before any write if\nunresolvable.\n\n## Step 5: Confirm before writing\n\nAsk the user:\n\n> Send this to Jira? Reply **y** to confirm, **n** to revise, anything else\n> to abort.\n\nA clear `y`\u002F`yes` proceeds; a `n`\u002Frevise stays in review (re-apply Step 3 to any\nrevised body); anything ambiguous aborts with \"Aborted — no Jira write was\nmade.\"\n\n## Step 6: Send the request\n\n```\naccelerator jira create [all flags from Steps 1-2]\n```\n\n## Step 7: Render the response\n\nThe subcommand emits a JSON envelope `{key}` with a top-level `outcome` keyword.\nOn the `created` keyword, present:\n\n> Issue created: **\u003CKEY>**\n\n## Step 8: Error handling\n\nOn a non-zero exit, show the error, which names its cause on stderr:\n- `E_CREATE_NO_SUMMARY` — `--summary` is required;\n- `E_CREATE_BAD_FIELD` — a `--custom` value failed validation; run\n  `\u002Finit-jira --refresh-fields` if a field id was rejected;\n- `E_CREATE_NO_SITE_CACHE` — `@me` was used but `site.json` is missing; run\n  `\u002Finit-jira`;\n- `E_CREATE_BAD_ASSIGNEE` — `--assignee`\u002F`--reporter` accepts `@me` or a raw\n  accountId, not an email;\n- an auth or transport failure — suggest checking credentials with `\u002Finit-jira`.\n\n## Step 9: Examples\n\n**Example — minimal task**\nUser: `\u002Fcreate-jira-issue --project ENG --type Task --summary \"Fix login timeout\"`\nSkill previews the resolved intent, waits for `y`, then creates and renders\n`Issue created: ENG-456`.\n\n**Example — custom field with @json escape**\nUser: `\u002Fcreate-jira-issue --project ENG --type Task --summary \"Sprint task\" --custom sprint=@json:[42]`\nSkill coerces the sprint field as a JSON array literal, previews, confirms.\n\n!`accelerator config instructions create-jira-issue --fail-safe`\n",{"name":5,"description":50,"allowed-tools":51,"argument-hint":54,"disable-model-invocation":55},"Use this skill only when the user explicitly invokes \u002Fcreate-jira-issue to create a new Jira issue. This is a write skill with irreversible side effects — it must never be auto-invoked from conversational context. Accepts a project key, issue type, summary, optional Markdown body, and optional fields (assignee, reporter, priority, labels, components, parent, custom fields). Previews the resolved intent, requires explicit confirmation, then POSTs to Jira and returns the new issue key.\n",[42,52,53],"Read","Write","[--project KEY] --type NAME --summary TEXT [--body TEXT | --body-file PATH] [--assignee @me|ACCTID] [--reporter @me|ACCTID] [--priority NAME] [--label NAME]... [--component NAME]... [--parent KEY] [--custom SLUG=VALUE]... [--issuetype-id ID]",true,"main","007b2dd695b63c2f097cdc40e54229b6e8b4596a","skills\u002Fintegrations\u002Fjira\u002Fcreate-jira-issue",2,"https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator","https:\u002F\u002Fgo-atomic.io","https:\u002F\u002Fgithub.com\u002Fatomicinnovation","2026-11-13 08:45:04",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":55},[66,69,72],{"tool":67,"command":68},"npx","npx skills add atomicinnovation\u002Faccelerator --skill create-jira-issue",{"tool":70,"command":71},"bunx","bunx skills add atomicinnovation\u002Faccelerator --skill create-jira-issue",{"tool":73,"command":74},"pnpm","pnpm dlx skills add atomicinnovation\u002Faccelerator --skill create-jira-issue","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fintegrations\u002Fjira\u002Fcreate-jira-issue\u002FSKILL.md",[77,83,87],{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"evals\u002Fbenchmark.json","REFERENCE","参考文档",3312,"https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fintegrations\u002Fjira\u002Fcreate-jira-issue\u002Fevals\u002Fbenchmark.json",{"path":84,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":85,"sourceHtmlUrl":86},"evals\u002Fevals.json",3292,"https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fintegrations\u002Fjira\u002Fcreate-jira-issue\u002Fevals\u002Fevals.json",{"path":88,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":91,"sourceHtmlUrl":92},"scripts\u002Fcanvas_api.py","SCRIPT","脚本",5099,"https:\u002F\u002Fgithub.com\u002Fgjbvsjjvgm-sketch\u002Fhermes-sovereign-unified-v13.6\u002Fblob\u002Fmain\u002Fhermes-agent\u002Foptional-skills\u002Fproductivity\u002Fcanvas\u002Fscripts\u002Fcanvas_api.py",[94,129,153,172,190,215],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":110,"publishedAt":45},"01M70S7PFGVATJREBFEGPJB718","explore-pr","Build an interactive, design-first and picture-first exploration page for a pull request — its architecture, abstractions and design decisions drawn as diagrams, a guided tour in reading order with code as the evidence, an attention map of where the risk sits, a ledger of its riskiest operations, prior review findings re-checked against the code, and simulations specific to the PR — with the reviewer's verdicts and notes saved. Use when the user wants to explore, understand or review a large pull request or its design, asks for a review page, walkthrough or visual explanation of a PR, or is struggling to review a big change.","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fexplore-pr\u002FSKILL.md",[100,105],{"categoryNo":101,"categoryName":102,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":106,"categoryName":107,"taxonomyType":108,"taxonomyTypeDesc":109},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[111,112,113,114,115,116,117,118,119,120,25,121,122,42,123,124,125,126,127,128],"explore pr","explore","pr","diagrams","exploration","re","review findings","walkthrough","design","map","number","URL","code","architecture","reviewer","review","notes","change",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":45},"01M6DY04WBTMFV96JMBP5ZXVFX","update-work-item","Update fields (status, priority, tags, parent, etc.) of an existing work item. Use to transition status, change priority, manage tags, or edit any frontmatter field. No transition enforcement — arbitrary changes are allowed.","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fupdate-work-item\u002FSKILL.md",[],[136,137,138,139,140,141,38,42,128,142,143,144,145,146,147,148,149,150,151,152],"work","update","update work item","work item","enforcement","manage","config","edit","validate","status","transition","frontmatter","Existing","tags","changes","fields","op",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":45},"01M6DY0106CF15CYEJHZM14GBZ","sync-work-items","Reconcile local work items in meta\u002Fwork\u002F with the active remote tracker named by work.integration. Use when the user wants to sync, push, or pull work items to or from Jira or Linear, preview what a sync would change, or reconcile divergent local and remote state.","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fsync-work-items\u002FSKILL.md",[],[136,160,161,162,163,164,35,42,165,128,166,167,168,19,169,20,170,142,171,147,25],"sync","sync work items","promote","Meta","local","preview","active","tracker","max","remote","adopt","reconcile",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":178,"publishedAt":45},"01M6HNF86984S4XK21Q26VZA21","sync-work-items-recovery","Recovery procedures for work sync failures that need a person — terminal rows, refused pending pushes and refused orders. Read by sync-work-items — not invoked directly.","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fsync-work-items-recovery\u002FSKILL.md",[],[179,136,180,160,161,181,182,183,184,185,186,187,188,189],"sync work items recovery","recovery","work-items","for","terminal","read","person","true","false","orders","pending",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":199,"publishedAt":45},"01M6DXZWH7PR72VCEXSSD4XNK4","stress-test-work-item","Interactively stress-test a work item by grilling the user on scope, assumptions, acceptance criteria, edge cases, and dependencies to surface issues, gaps, and flawed assumptions before implementation is planned.","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fstress-test-work-item\u002FSKILL.md",[196],{"categoryNo":197,"categoryName":198,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000008","测试与质量",[200,201,136,202,139,203,204,205,206,207,208,42,209,210,142,144,211,212,213,121,214,147],"stress test","test","stress test work item","stress","scope","issues","edge","stress-test","acceptance","acceptance criteria","dependencies","implementation","grilling","user","gaps",{"skillNo":216,"name":217,"nameZh":6,"description":218,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":219,"categories":220,"keywords":221,"publishedAt":45},"01M6DXZRQWHTWV1G9PTTHCGGYA","review-work-item","Review a work item through multiple quality lenses and collaboratively iterate based on findings. Use when the user wants to evaluate a work item before implementation or escalation.","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Freview-work-item\u002FSKILL.md",[],[126,136,222,139,223,224,38,42,43,225,142,144,211,213,226,25,227,228,147,229],"review work item","review work","escalation","quality","metadata","iterate","evaluate","path"]