[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75YVB9DFRMQ0P4SB1RWCH8D":3,"skill-same:01M75YVB9DFRMQ0P4SB1RWCH8D":45},{"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},"01M75YVB9DFRMQ0P4SB1RWCH8D","triage-issue",null,"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.","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\u002Ftriage-issue\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: triage-issue\ndescription: 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.\n---\n\u003C!-- Generated from skills-src\u002Ftriage-issue\u002FSKILL.md — edit the source and run 'make gen-plugins'. -->\n\n# Triage an issue with `atl`\n\nFind duplicates **before** filing. Never create a ticket without first showing\nthe user what already exists. Command details live in the `jira` skill.\n\n**Preflight:** `atl` must be installed and configured. If `command -v atl` fails\nor a command exits `7` (\"not configured\"), run `\u002Fatl:setup` and stop.\n\n## Workflow\n\n### 1. Extract the error signature\n\nFrom the report, pull: the exception\u002Ferror type, the failing\nclass\u002Ffunction\u002Fendpoint, and the stable message words. Strip volatile parts —\nids, timestamps, hostnames, line numbers — they poison text search. Build 2–3\nquery variants from specific to broad.\n\n### 2. Search for duplicates (parallel, one message)\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl jira issue search \\\n  --jql 'project = KEY AND text ~ \"NullPointerException PaymentProcessor\" AND type = Bug ORDER BY created DESC' \\\n  --limit 10 --columns key,summary,status,issuetype,updated\natl jira issue search \\\n  --jql 'project = KEY AND summary ~ \"timeout checkout\" ORDER BY updated DESC' \\\n  --limit 10 --columns key,summary,status,issuetype,updated\n```\n\nUseful refinements:\n\n- recent recurrence: `AND created >= -30d`\n- fixed before (regression check):\n  `AND status in (Done, Closed, Resolved) ORDER BY resolutiondate DESC`\n- open neighbours: `AND status not in (Done, Closed) AND component = \"X\"`\n- Quote multi-word phrases inside `text ~ \"...\"`; JQL reserved words must be\n  quoted too.\n\n### 3. Classify and present — no writes yet\n\nCompare promising hits before proposing any write:\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl jira issue get KEY-123 \\\n  --fields summary,status,issuetype,description,labels,components,updated,resolution\n```\n\nKeep the search `page` qualification and compare only the fields required by\nthe duplicate rule. A plausible positive hit can be inspected immediately, and\nonly a confirmed open-duplicate\u002Fcomment path may stop early. Before either\ncreate path—**Regression** or **New**—resume every search with its exact\n`page.next_cursor` until `page.complete:true`. If any search stays truncated or\nincomplete, report that duplicate absence is unproven and do not propose or\ncreate a new issue. Fetch comments separately only after an open duplicate is\nselected; do not pull comments or attachments into every candidate read.\n\nFor a closed candidate that may prove a regression, add one compact temporal\ncheck only after selecting it:\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl jira issue history KEY-123 --field status --summary-only\n```\n\nRequire `complete:true` and use `last_changes`; do not classify a regression\nfrom the current resolution alone or fetch raw history rows when the summary is\nsufficient.\n\nThen tell the user\nwhich case this is and what you propose:\n\n- **Duplicate (open)** → offer to add a comment with the new occurrence and any\n  new context.\n- **Regression (was fixed)** → offer a new bug linked to the old one\n  (`atl jira link-types` lists the instance's link names).\n- **New** → offer to create a ticket.\n\nStop and wait for the user's choice.\n\n### 4a. Comment on an existing issue\n\n```sh\nprintf '%s' \"$BODY_MD\" | ATL_READ_ONLY=1 atl jira issue comment preview KEY-123 --from-md -\n# After explicit approval, repeat the exact body once with:\nprintf '%s' \"$BODY_MD\" | env -u ATL_READ_ONLY atl jira issue comment add KEY-123 \\\n  --from-md - --apply --expected-proposal-hash '\u003Creviewed-hash>'\n```\n\n### 4b. Create a new bug\n\nCompose the description in markdown — Summary \u002F Steps to reproduce \u002F Expected \u002F\nActual \u002F Environment \u002F error excerpt in a code fence \u002F links to similar issues —\nthen:\n\n```sh\natl jira issue create preview --project KEY --type Bug --summary '\u003CComponent>: \u003Csymptom> \u003Ccondition>' --from-md desc.md\n# After explicit review, repeat the exact parent command with the reviewed hash:\natl jira issue create --project KEY --type Bug --summary '\u003CComponent>: \u003Csymptom> \u003Ccondition>' \\\n  --from-md desc.md --apply --expected-proposal-hash '\u003Creviewed hash>'\nATL_READ_ONLY=1 atl jira issue link add preview NEW-1 --to OLD-9 --type Relates\n# After explicit review, repeat without ATL_READ_ONLY and add --apply plus the proposal hash.\n```\n\nTitle formula: component + observable symptom + triggering condition — not the\nraw exception line.\n\n### 5. Report back\n\nReturn the created\u002Fupdated key, what was linked, and the duplicate-search\nqueries you ran, so a human can re-check the negative result.\n\n## Pitfalls\n\n| Symptom | Cause \u002F fix |\n|---|---|\n| exit 8 on `create --from-md` | a markdown construct isn't convertible — the error names it; simplify that block |\n| link add rejected | link type names are instance-specific — check `atl jira link-types` first |\n| assignee rejected | Server\u002FDC takes a **username**: find it with `atl jira user search '\u003Cname>'`, set via `--field 'assignee={\"name\":\"\u003Cusername>\"}'` |\n| `text ~` too noisy | add `type = Bug`, a component, or `created >= -90d` |\n","\u003C!-- Generated from skills-src\u002Ftriage-issue\u002FSKILL.md — edit the source and run 'make gen-plugins'. -->\n\n# Triage an issue with `atl`\n\nFind duplicates **before** filing. Never create a ticket without first showing\nthe user what already exists. Command details live in the `jira` skill.\n\n**Preflight:** `atl` must be installed and configured. If `command -v atl` fails\nor a command exits `7` (\"not configured\"), run `\u002Fatl:setup` and stop.\n\n## Workflow\n\n### 1. Extract the error signature\n\nFrom the report, pull: the exception\u002Ferror type, the failing\nclass\u002Ffunction\u002Fendpoint, and the stable message words. Strip volatile parts —\nids, timestamps, hostnames, line numbers — they poison text search. Build 2–3\nquery variants from specific to broad.\n\n### 2. Search for duplicates (parallel, one message)\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl jira issue search \\\n  --jql 'project = KEY AND text ~ \"NullPointerException PaymentProcessor\" AND type = Bug ORDER BY created DESC' \\\n  --limit 10 --columns key,summary,status,issuetype,updated\natl jira issue search \\\n  --jql 'project = KEY AND summary ~ \"timeout checkout\" ORDER BY updated DESC' \\\n  --limit 10 --columns key,summary,status,issuetype,updated\n```\n\nUseful refinements:\n\n- recent recurrence: `AND created >= -30d`\n- fixed before (regression check):\n  `AND status in (Done, Closed, Resolved) ORDER BY resolutiondate DESC`\n- open neighbours: `AND status not in (Done, Closed) AND component = \"X\"`\n- Quote multi-word phrases inside `text ~ \"...\"`; JQL reserved words must be\n  quoted too.\n\n### 3. Classify and present — no writes yet\n\nCompare promising hits before proposing any write:\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl jira issue get KEY-123 \\\n  --fields summary,status,issuetype,description,labels,components,updated,resolution\n```\n\nKeep the search `page` qualification and compare only the fields required by\nthe duplicate rule. A plausible positive hit can be inspected immediately, and\nonly a confirmed open-duplicate\u002Fcomment path may stop early. Before either\ncreate path—**Regression** or **New**—resume every search with its exact\n`page.next_cursor` until `page.complete:true`. If any search stays truncated or\nincomplete, report that duplicate absence is unproven and do not propose or\ncreate a new issue. Fetch comments separately only after an open duplicate is\nselected; do not pull comments or attachments into every candidate read.\n\nFor a closed candidate that may prove a regression, add one compact temporal\ncheck only after selecting it:\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl jira issue history KEY-123 --field status --summary-only\n```\n\nRequire `complete:true` and use `last_changes`; do not classify a regression\nfrom the current resolution alone or fetch raw history rows when the summary is\nsufficient.\n\nThen tell the user\nwhich case this is and what you propose:\n\n- **Duplicate (open)** → offer to add a comment with the new occurrence and any\n  new context.\n- **Regression (was fixed)** → offer a new bug linked to the old one\n  (`atl jira link-types` lists the instance's link names).\n- **New** → offer to create a ticket.\n\nStop and wait for the user's choice.\n\n### 4a. Comment on an existing issue\n\n```sh\nprintf '%s' \"$BODY_MD\" | ATL_READ_ONLY=1 atl jira issue comment preview KEY-123 --from-md -\n# After explicit approval, repeat the exact body once with:\nprintf '%s' \"$BODY_MD\" | env -u ATL_READ_ONLY atl jira issue comment add KEY-123 \\\n  --from-md - --apply --expected-proposal-hash '\u003Creviewed-hash>'\n```\n\n### 4b. Create a new bug\n\nCompose the description in markdown — Summary \u002F Steps to reproduce \u002F Expected \u002F\nActual \u002F Environment \u002F error excerpt in a code fence \u002F links to similar issues —\nthen:\n\n```sh\natl jira issue create preview --project KEY --type Bug --summary '\u003CComponent>: \u003Csymptom> \u003Ccondition>' --from-md desc.md\n# After explicit review, repeat the exact parent command with the reviewed hash:\natl jira issue create --project KEY --type Bug --summary '\u003CComponent>: \u003Csymptom> \u003Ccondition>' \\\n  --from-md desc.md --apply --expected-proposal-hash '\u003Creviewed hash>'\nATL_READ_ONLY=1 atl jira issue link add preview NEW-1 --to OLD-9 --type Relates\n# After explicit review, repeat without ATL_READ_ONLY and add --apply plus the proposal hash.\n```\n\nTitle formula: component + observable symptom + triggering condition — not the\nraw exception line.\n\n### 5. Report back\n\nReturn the created\u002Fupdated key, what was linked, and the duplicate-search\nqueries you ran, so a human can re-check the negative result.\n\n## Pitfalls\n\n| Symptom | Cause \u002F fix |\n|---|---|\n| exit 8 on `create --from-md` | a markdown construct isn't convertible — the error names it; simplify that block |\n| link add rejected | link type names are instance-specific — check `atl jira link-types` first |\n| assignee rejected | Server\u002FDC takes a **username**: find it with `atl jira user search '\u003Cname>'`, set via `--field 'assignee={\"name\":\"\u003Cusername>\"}'` |\n| `text ~` too noisy | add `type = Bug`, a component, or `created >= -90d` |\n",{"name":5,"description":7},"main","c6ed32ed384aa5e9a3e86d4528f16dc13833ce66","skills\u002Ftriage-issue",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 triage-issue",{"tool":37,"command":38},"bunx","bunx skills add isukharev\u002Fatl --skill triage-issue",{"tool":40,"command":41},"pnpm","pnpm dlx skills add isukharev\u002Fatl --skill triage-issue","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fisukharev\u002Fatl\u002Fblob\u002Fmain\u002Fskills\u002Ftriage-issue\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":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"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":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M75YV57J2G080TFCV6QYWK2B","sprint-dashboard","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.","https:\u002F\u002Fgithub.com\u002Fisukharev\u002Fatl\u002Fblob\u002Fmain\u002Fskills\u002Fsprint-dashboard\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"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":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"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",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M75YTPGAKF9MZTA48QE1SK19","onboarding","Build a reviewed private atl workflow profile from approved Jira\u002FConfluence samples. USE WHEN the user explicitly asks to onboard, personalize atl, or refresh saved preferences. DO NOT USE WHEN handling ordinary service, search, report, or setup work; explicit-only.","https:\u002F\u002Fgithub.com\u002Fisukharev\u002Fatl\u002Fblob\u002Fmain\u002Fskills\u002Fonboarding\u002FSKILL.md",[],[]]