[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75YT0ASRHG4TYF99FNPN4YM":3,"skill-same:01M75YT0ASRHG4TYF99FNPN4YM":51},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M75YT0ASRHG4TYF99FNPN4YM","sprint-dashboard",null,"Build a visual read-only Jira sprint or board dashboard with atl. USE WHEN the user wants a standup view, WIP picture, or sprint snapshot. DO NOT USE WHEN the output is a narrative report, raw Jira list, or codebase dashboard.","isukharev\u002Fatl","isukharev","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4347261?v=4","01M75YQ67178RKPTQQKHF1V28G","Ivan Sukharev","01M75YQ68359TNKPGE26PY1Q33",7,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fisukharev\u002Fatl\u002Fblob\u002Fmain\u002Fskills-src\u002Fsprint-dashboard\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: sprint-dashboard\ndescription: Build a visual read-only Jira sprint or board dashboard with atl. USE WHEN the user wants a standup view, WIP picture, or sprint snapshot. DO NOT USE WHEN the output is a narrative report, raw Jira list, or codebase dashboard.\n---\n\n# Sprint dashboard with `atl`\n\nA decision-support dashboard, not a prose report: its job is to show an\nengineering manager or tech lead what needs attention. Strictly read-only —\nnever create, update, transition, assign, or comment from this recipe; offer\nwrites as follow-ups only. Command details live in the `jira` skill.\n\nMake `export ATL_READ_ONLY=1` the first statement of every Bash block in this\nrecipe so every later `atl` call and child process inherits the guard. A prefix\non one `atl` command does not protect later commands in the block. Never\noverride the export in this workflow.\n\n**Preflight:** `atl` must be installed and configured. If `command -v atl` fails\nor a command exits `7` (\"not configured\"), run `{{atl.setup_cmd}}` and stop.\n\n## Workflow\n\n### 1. Resolve scope\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl jira board list --project KEY --limit 50 # skip when the exact id is supplied\natl jira board config \u003Cid>                   # route by Scrum\u002FKanban and real columns\n```\n\nWhen discovery is ambiguous, follow each exact `next_cursor` until the returned\npage says `complete:true`; do not repeatedly list boards after the id is known.\nTreat that qualified flag, not merely an empty cursor, as evidence that the\ndiscovery list is terminal. If it is false when absence matters, ask for an\nexact id. For Scrum, read the active sprint; on exit 4 offer the latest closed\nsprint or a plain JQL scope.\nFor Kanban, do not invent a sprint—use the normalized board snapshot. If the\nuser gave a project or filter rather than a board, go straight to JQL.\n\n### 2. Fetch the data\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\n# Scrum\natl jira sprint current --board \u003Cid>\natl jira sprint issues \u003CsprintId> \\\n  --columns position,key,summary,status,assignee,priority,issuetype,updated \\\n  --limit 50\n\n# Kanban or another complete board-scope dashboard: keep bulk rows out of chat.\natl jira board export \u003Cid> --scope all --limit 0 \\\n  --columns position,key,summary,status,board.column,assignee,priority,issuetype,updated \\\n  --format jsonl --out \u003Cprivate-dir>\u002Fboard.jsonl\n```\n\nChoose one branch, not both. The sprint API caps each call at 50 — paginate\nwith `--cursor` until exhausted. A native board export returns a small receipt;\nprocess its qualified JSONL locally rather than printing the whole snapshot.\nJQL fallback: `atl jira issue search --jql 'project = KEY AND sprint in\nopenSprints()' --columns key,summary,status,assignee,priority,issuetype,updated\n--limit 100`.\nIf anything is still truncated, say so **on the dashboard** — never present a\npartial picture as complete.\n\n### 3. Compute locally (no further API calls)\n\n- Status columns: use the board's configured ordered columns and keep unmapped\n  statuses explicit. Only label a To Do \u002F In Progress \u002F In Review \u002F Done\n  grouping as heuristic when there is no board configuration.\n- **Attention signals**: in-progress items not updated for 2+ days; unassigned\n  non-Done work; high-priority items not started; WIP concentration (one\n  assignee holding several in-flight items).\n- Progress: done vs total. This is issue-count math — label it as such unless\n  story points were explicitly fetched (`--fields` with the instance's points\n  field).\n\n### 4. Render\n\nUse the richest renderer the current client supports, keeping content\nidentical across formats:\n\n1. An interactive HTML artifact, when the environment can host one.\n2. Otherwise a self-contained `dashboard.html` file (inline CSS, no external\n   assets) delivered to the user.\n3. Otherwise markdown in chat.\n\nLayout, in order: header (sprint name, dates, done\u002Ftotal progress bar);\na \"needs attention\" strip — each signal with issue key and one-line reason;\nstatus columns with compact cards (key, truncated summary, assignee, priority\nmarker); per-assignee load table; appendix (board\u002Fsprint id or JQL, fetch time,\ntruncation notes). Link keys to `\u003Cjira-url>\u002Fbrowse\u002FKEY`. Read only the base URL\nwith a failure-visible local projection:\n\n\u003C!-- atl:read-only-shell -->\n```bash\nexport ATL_READ_ONLY=1\nset -o pipefail\natl config show | jq -r '.jira_url'\n```\n\n### 5. Close the loop\n\nAfter the dashboard, give a three-bullet text digest of the top attention\nitems, then offer — without performing — follow-up writes (assign, move,\ncomment).\n","# Sprint dashboard with `atl`\n\nA decision-support dashboard, not a prose report: its job is to show an\nengineering manager or tech lead what needs attention. Strictly read-only —\nnever create, update, transition, assign, or comment from this recipe; offer\nwrites as follow-ups only. Command details live in the `jira` skill.\n\nMake `export ATL_READ_ONLY=1` the first statement of every Bash block in this\nrecipe so every later `atl` call and child process inherits the guard. A prefix\non one `atl` command does not protect later commands in the block. Never\noverride the export in this workflow.\n\n**Preflight:** `atl` must be installed and configured. If `command -v atl` fails\nor a command exits `7` (\"not configured\"), run `{{atl.setup_cmd}}` and stop.\n\n## Workflow\n\n### 1. Resolve scope\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl jira board list --project KEY --limit 50 # skip when the exact id is supplied\natl jira board config \u003Cid>                   # route by Scrum\u002FKanban and real columns\n```\n\nWhen discovery is ambiguous, follow each exact `next_cursor` until the returned\npage says `complete:true`; do not repeatedly list boards after the id is known.\nTreat that qualified flag, not merely an empty cursor, as evidence that the\ndiscovery list is terminal. If it is false when absence matters, ask for an\nexact id. For Scrum, read the active sprint; on exit 4 offer the latest closed\nsprint or a plain JQL scope.\nFor Kanban, do not invent a sprint—use the normalized board snapshot. If the\nuser gave a project or filter rather than a board, go straight to JQL.\n\n### 2. Fetch the data\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\n# Scrum\natl jira sprint current --board \u003Cid>\natl jira sprint issues \u003CsprintId> \\\n  --columns position,key,summary,status,assignee,priority,issuetype,updated \\\n  --limit 50\n\n# Kanban or another complete board-scope dashboard: keep bulk rows out of chat.\natl jira board export \u003Cid> --scope all --limit 0 \\\n  --columns position,key,summary,status,board.column,assignee,priority,issuetype,updated \\\n  --format jsonl --out \u003Cprivate-dir>\u002Fboard.jsonl\n```\n\nChoose one branch, not both. The sprint API caps each call at 50 — paginate\nwith `--cursor` until exhausted. A native board export returns a small receipt;\nprocess its qualified JSONL locally rather than printing the whole snapshot.\nJQL fallback: `atl jira issue search --jql 'project = KEY AND sprint in\nopenSprints()' --columns key,summary,status,assignee,priority,issuetype,updated\n--limit 100`.\nIf anything is still truncated, say so **on the dashboard** — never present a\npartial picture as complete.\n\n### 3. Compute locally (no further API calls)\n\n- Status columns: use the board's configured ordered columns and keep unmapped\n  statuses explicit. Only label a To Do \u002F In Progress \u002F In Review \u002F Done\n  grouping as heuristic when there is no board configuration.\n- **Attention signals**: in-progress items not updated for 2+ days; unassigned\n  non-Done work; high-priority items not started; WIP concentration (one\n  assignee holding several in-flight items).\n- Progress: done vs total. This is issue-count math — label it as such unless\n  story points were explicitly fetched (`--fields` with the instance's points\n  field).\n\n### 4. Render\n\nUse the richest renderer the current client supports, keeping content\nidentical across formats:\n\n1. An interactive HTML artifact, when the environment can host one.\n2. Otherwise a self-contained `dashboard.html` file (inline CSS, no external\n   assets) delivered to the user.\n3. Otherwise markdown in chat.\n\nLayout, in order: header (sprint name, dates, done\u002Ftotal progress bar);\na \"needs attention\" strip — each signal with issue key and one-line reason;\nstatus columns with compact cards (key, truncated summary, assignee, priority\nmarker); per-assignee load table; appendix (board\u002Fsprint id or JQL, fetch time,\ntruncation notes). Link keys to `\u003Cjira-url>\u002Fbrowse\u002FKEY`. Read only the base URL\nwith a failure-visible local projection:\n\n\u003C!-- atl:read-only-shell -->\n```bash\nexport ATL_READ_ONLY=1\nset -o pipefail\natl config show | jq -r '.jira_url'\n```\n\n### 5. Close the loop\n\nAfter the dashboard, give a three-bullet text digest of the top attention\nitems, then offer — without performing — follow-up writes (assign, move,\ncomment).\n",{"name":5,"description":7},"main","c6ed32ed384aa5e9a3e86d4528f16dc13833ce66","skills-src\u002Fsprint-dashboard",1,"https:\u002F\u002Fgithub.com\u002Fisukharev\u002Fatl","https:\u002F\u002Fgithub.com\u002Fisukharev","2026-09-14 23:56:52",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add isukharev\u002Fatl --skill sprint-dashboard",{"tool":37,"command":38},"bunx","bunx skills add isukharev\u002Fatl --skill sprint-dashboard",{"tool":40,"command":41},"pnpm","pnpm dlx skills add isukharev\u002Fatl --skill sprint-dashboard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fisukharev\u002Fatl\u002Fblob\u002Fmain\u002Fskills-src\u002Fsprint-dashboard\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"agents\u002Fopenai.yaml","REFERENCE","参考文档",228,"https:\u002F\u002Fgithub.com\u002Fisukharev\u002Fatl\u002Fblob\u002Fmain\u002Fskills-src\u002Fsprint-dashboard\u002Fagents\u002Fopenai.yaml",[52,59,66,71,78,85],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M75YVB9DFRMQ0P4SB1RWCH8D","triage-issue","Triage a bug against Jira with atl before proposing a ticket. USE WHEN an error or stack trace comes with duplicate, prior-fix, or file-a-bug intent. DO NOT USE WHEN debugging code only, inspecting a known issue, or creating an ordinary task.","https:\u002F\u002Fgithub.com\u002Fisukharev\u002Fatl\u002Fblob\u002Fmain\u002Fskills\u002Ftriage-issue\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M75YV7K5C8A8NV1SYHM413B7","status-report","Draft an audience-oriented Jira status report with atl. USE WHEN the user wants a weekly\u002Fdaily progress narrative, blocker summary, or period report. DO NOT USE WHEN the output is a visual dashboard, direct Jira query, knowledge search, or codebase summary.","https:\u002F\u002Fgithub.com\u002Fisukharev\u002Fatl\u002Fblob\u002Fmain\u002Fskills\u002Fstatus-report\u002FSKILL.md",[],[],{"skillNo":67,"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":68,"categories":69,"keywords":70,"publishedAt":19},"01M75YV57J2G080TFCV6QYWK2B","https:\u002F\u002Fgithub.com\u002Fisukharev\u002Fatl\u002Fblob\u002Fmain\u002Fskills\u002Fsprint-dashboard\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M75YV2JNBA9PTQA06JJSZGW5","spec-to-backlog","Convert a specification into a reviewed Jira epic and backlog with atl. USE WHEN decomposing requirements, RFCs, or designs into linked Jira work. DO NOT USE WHEN the source is meeting notes, only a summary is wanted, or the task is a direct service operation.","https:\u002F\u002Fgithub.com\u002Fisukharev\u002Fatl\u002Fblob\u002Fmain\u002Fskills\u002Fspec-to-backlog\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M75YTWKKWHKGZ0XQACM7VXNR","setup","Install and configure atl authentication, backends, and mirror defaults. USE WHEN the user explicitly requests install, authentication, setup repair, or \u002Fatl:setup. DO NOT USE WHEN handling normal Jira, Confluence, search, reporting, or mirror work; explicit-only.","https:\u002F\u002Fgithub.com\u002Fisukharev\u002Fatl\u002Fblob\u002Fmain\u002Fskills\u002Fsetup\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"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},"01M75YTSX670SW6NSBA1HGAG65","search-knowledge","Answer from qualified Jira and Confluence evidence with atl. USE WHEN organizational knowledge is unknown or split across both services. DO NOT USE WHEN one exact resource is known, the task is a report\u002Fdashboard, or the answer belongs in the codebase.","https:\u002F\u002Fgithub.com\u002Fisukharev\u002Fatl\u002Fblob\u002Fmain\u002Fskills\u002Fsearch-knowledge\u002FSKILL.md",[],[]]