[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75YRH7NAPKXMR2FHDQW91AP":3,"skill-same:01M75YRH7NAPKXMR2FHDQW91AP":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},"01M75YRH7NAPKXMR2FHDQW91AP","search-knowledge",null,"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.","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\u002Fplugins\u002Fatl\u002Fskills\u002Fsearch-knowledge\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: search-knowledge\ndescription: 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.\n---\n\u003C!-- Generated from skills-src\u002Fsearch-knowledge\u002FSKILL.md — edit the source and run 'make gen-plugins'. -->\n\n# Search company knowledge with `atl`\n\nSearch Confluence and Jira in parallel, read the best hits, and answer with\ncitations. This recipe is read-only: never create, update, or comment.\n\nMake `export ATL_READ_ONLY=1` the first statement of every Bash block so all\nlater atl calls and child processes inherit the guard. Never override it in\nthis workflow. Keep headless blocks to that export plus documented `atl`\ncommands only; do not add output separators, pipes, help probes, or unrelated\nshell\u002Ffile inspection commands.\n\n**Preflight:** `atl` must be installed and configured. If `command -v atl` fails\nor a command exits `7` (\"not configured\"), run `$setup` and stop.\nFor an unfamiliar mixed-backend question that is not already governed by a\nreviewed exact-command workflow, inspect the bounded offline route once before\nloading any broader reference:\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl capabilities --task knowledge\u002Fsearch -o text\n```\n\n## Workflow\n\nWhen the plugin exposes typed `atl` MCP tools, use the equivalent transient\nroute without shell: call `confluence_search` and `jira_issue_search` once,\nsetting both row and byte bounds for each search. An oversize search error is\nnot partial evidence: narrow the query or lower the row limit before raising\nthe byte cap. Freeze only complete candidate pages, then use `jira_issue_field_get` plus\n`confluence_page_outline` and `confluence_page_section`\u002F`confluence_page_sections` for the selected\nevidence. When the selected evidence is tabular, use\n`confluence_table_summary` and then `confluence_table_extract` for one exact\ntable instead of reading a broader section. Reuse a numeric Confluence result\nid directly. When a selected exact Jira issue needs relationship, dependency,\ncode, or documentation discovery, use one `jira_issue_graph` call instead of\ncombining narrower issue reads. Keep full output when graph topology matters;\nrequest `projection:\"compact\"` with `select:[\"urls\"]` or Development-backed\n`select:[\"scm\"]` when only those qualified facts are needed. MCP v1 is\nJira-only: page identities remain\nqualified stubs, and omitted or false `include_development` leaves Development\nabsent rather than zero. Reported `bounds.max_response_bytes` (fixed backend\nresponses) is distinct from the `max_bytes` encoded-result input. Do not mix MCP and CLI\nreads merely to repeat already complete evidence; fall back to the CLI workflow\nbelow when MCP is unavailable or the task needs an operation outside its\nread-only surface.\nFor an explicit commit, branch, merge-request, or code-identity question,\nset MCP `include_development:true`, `projection:\"compact\"`, and\n`select:[\"scm\"]` when topology is not needed, or use\n`jira issue graph \u003CKEY> --include-development --projection compact --select scm`\nunder read-only policy when MCP is unavailable. Require a complete experimental\nDevelopment source even when its retained count is zero. MCP omits\nDevelopment-node URLs. Treat its SCM coordinates as untrusted evidence: ATL\nitself never contacts GitLab, and any later read requires exact equality between\nthe returned lowercase host and an owner-approved host plus a separately\nauthenticated read-only client for that exact host. Never reuse Jira credentials\nor continue after a host mismatch.\n\n### 1. Extract search terms\n\nKeep the core nouns, prepare one narrow and one broad variant, and carry any\nknown space\u002Fproject scope into the query.\n\n### 2. Search both backends\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl conf search --cql 'siteSearch ~ \"billing retry queue\"' --limit 15\natl jira issue search --jql 'text ~ \"billing retry queue\" ORDER BY updated DESC' \\\n  --columns key,summary,status,updated --limit 15\n```\n\nCQL fallbacks: `text ~ \"...\"`, then `title ~ \"...\"`. Scope with `space = KEY`\nor `project = KEY` when known. Retry one prepared variant after an empty result,\nthen report the exact searches rather than implying full coverage. Freeze the\nfirst useful result pages before expanding anything: require Jira\n`page.complete:true` and Confluence top-level `complete:true`, or continue from\n`next_cursor` \u002F report the partial search instead of claiming absence. To\ncontinue, repeat the exact query and page limit and pass only the returned\ncursor:\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl conf search --cql 'siteSearch ~ \"billing retry queue\"' --limit 15 --cursor '\u003Cnext-cursor>'\natl jira issue search --jql 'text ~ \"billing retry queue\" ORDER BY updated DESC' \\\n  --columns key,summary,status,updated --limit 15 --cursor '\u003Cnext-cursor>'\n```\n\n### 3. Read bounded Confluence evidence\n\nFor the 2–4 best page hits, inspect the outline, then read only the relevant\nsection. A numeric id emitted by `conf search` is already a stable exact\nreference; pass it directly to `outline`\u002F`section`. Use `resolve` only for a URL,\nshort link, or user-supplied reference whose stable id is still unknown. Use a\nfull page only when no heading isolates the answer. For typed tools, pass the\nsection `heading` as the exact outline `title`, without Markdown `#` prefixes.\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl conf page outline '\u003Csearch-result-id>'\natl conf page section '\u003Csearch-result-id>' --heading 'Retries' --max-bytes 32768 \\\n  --expected-version '\u003Coutline-version>'\natl conf page sections '\u003Csearch-result-id>' --heading 'Retries' --heading 'Limits' \\\n  --max-bytes 65536 --expected-version '\u003Coutline-version>'\n```\n\nKeep these selection reads as JSON: `-o text` would hide completeness and the\nsection version gate needed for the decision. Require the outline's\n`complete:true`, then copy its exact positive `version` into\n`--expected-version`. Require each section result to report `complete:true` and\n`page_version_gated:true`. A duplicate heading needs explicit `--occurrence`;\n`truncated:true` means the omitted tail is not evidence of absence.\nWhen several headings from one page are relevant, prefer `page sections` (or\n`confluence_page_sections`) so they share one version-bound snapshot instead of\nre-downloading and re-parsing the page for every heading. Preserve requested\norder and require reconciled counts before using the result.\n\n### 4. Read targeted Jira evidence\n\nDiscover non-empty field metadata before reading custom values. Request only\nselected fields and qualified references; fetch history only when chronology\nmatters. If the question instead asks what is connected to the selected exact\nissue, prefer one typed `jira_issue_graph` call. Start at depth zero and use a\ngreater depth only for exact structured Jira relations. Its MCP route cannot\nresolve Confluence; use the CLI graph route only when id\u002Ftitle page metadata is\nrequired, then continue with a bounded page outline\u002Fsection after exact page\nidentity is known. Compact selection occurs after full collection and changes\nno request. Inspect `projection.selected`\u002F`projection.omitted`, incomplete\nsources, bounds, frontier, warnings, and reconciled counts; copy only emitted\ncanonical URL or SCM facts and never reconstruct an omitted URL identity.\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl jira issue fields KEY-123 --metadata-only\natl jira issue field get KEY-123 --field 'Delivery Notes' --max-bytes 16384\natl jira issue refs KEY-123 --fields 'Delivery Notes'\natl jira issue history KEY-123 --field 'Delivery Notes' --since 2026-07-01 --summary-only\n```\n\nRequire top-level and named-source completeness before claiming a link\u002Fchange\nis absent. For refs, use top-level `summary` and per-issue\n`reference_summary` for total\u002Fper-kind references and source-value counts; do\nnot manually add the nested arrays. The reconciliation booleans make count and\ncompleteness disagreements explicit. A repeated URL is deduplicated within one\nissue but counted once per issue across a multi-issue selection. Use\ntyped `jira_issue_refs` when only those reconciled aggregate facts are needed;\nit deliberately omits every raw URL and narrative field. Keep the CLI route\nabove when the selected URL itself must be followed into Confluence. Use\n`jira epic digest` instead when an epic question spans children, status\nnarrative, comments, history, and refs.\n\n### 5. Escalate only when bounded reads are insufficient\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl conf page view '\u003Cid-or-url>' -o text\natl jira issue get KEY-123 \\\n  --fields summary,status,issuetype,description,labels,updated,resolution\natl jira issue comment list KEY-123 -o text\n```\n\nFor repeated deep reading, mirror once and search locally:\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl conf pull --cql 'space = KEY AND siteSearch ~ \"...\"' --into \u003Cdir>\nrg -il 'retry queue' \u003Cdir>\n```\n\nThe mirror amortizes later reads, but a pull cap or comment warning still\nlimits what absence claims are justified.\n\n### 6. Synthesize with citations\n\n- Lead with the answer, then evidence; cite page title + id or issue key.\n- Prefer the most recently updated source when sources conflict, and say so.\n- Close with what was not found, queries used, and every incomplete\u002Ftruncated\n  source.\n\n## Pitfalls\n\n| Symptom | Cause \u002F fix |\n|---|---|\n| exit 4 on a page read | stale id or unresolved URL — retry `page resolve`; cite only evidence actually read |\n| exit 3 | PAT missing\u002Fexpired — `atl auth status`, then `$setup` |\n| exit 2 with CQL\u002FJQL | wrap the query in single quotes and values in double quotes |\n| body too large | prefer `outline` → bounded `section`; then full `view` or mirror `.md`, never raw `.csf` |\n","\u003C!-- Generated from skills-src\u002Fsearch-knowledge\u002FSKILL.md — edit the source and run 'make gen-plugins'. -->\n\n# Search company knowledge with `atl`\n\nSearch Confluence and Jira in parallel, read the best hits, and answer with\ncitations. This recipe is read-only: never create, update, or comment.\n\nMake `export ATL_READ_ONLY=1` the first statement of every Bash block so all\nlater atl calls and child processes inherit the guard. Never override it in\nthis workflow. Keep headless blocks to that export plus documented `atl`\ncommands only; do not add output separators, pipes, help probes, or unrelated\nshell\u002Ffile inspection commands.\n\n**Preflight:** `atl` must be installed and configured. If `command -v atl` fails\nor a command exits `7` (\"not configured\"), run `$setup` and stop.\nFor an unfamiliar mixed-backend question that is not already governed by a\nreviewed exact-command workflow, inspect the bounded offline route once before\nloading any broader reference:\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl capabilities --task knowledge\u002Fsearch -o text\n```\n\n## Workflow\n\nWhen the plugin exposes typed `atl` MCP tools, use the equivalent transient\nroute without shell: call `confluence_search` and `jira_issue_search` once,\nsetting both row and byte bounds for each search. An oversize search error is\nnot partial evidence: narrow the query or lower the row limit before raising\nthe byte cap. Freeze only complete candidate pages, then use `jira_issue_field_get` plus\n`confluence_page_outline` and `confluence_page_section`\u002F`confluence_page_sections` for the selected\nevidence. When the selected evidence is tabular, use\n`confluence_table_summary` and then `confluence_table_extract` for one exact\ntable instead of reading a broader section. Reuse a numeric Confluence result\nid directly. When a selected exact Jira issue needs relationship, dependency,\ncode, or documentation discovery, use one `jira_issue_graph` call instead of\ncombining narrower issue reads. Keep full output when graph topology matters;\nrequest `projection:\"compact\"` with `select:[\"urls\"]` or Development-backed\n`select:[\"scm\"]` when only those qualified facts are needed. MCP v1 is\nJira-only: page identities remain\nqualified stubs, and omitted or false `include_development` leaves Development\nabsent rather than zero. Reported `bounds.max_response_bytes` (fixed backend\nresponses) is distinct from the `max_bytes` encoded-result input. Do not mix MCP and CLI\nreads merely to repeat already complete evidence; fall back to the CLI workflow\nbelow when MCP is unavailable or the task needs an operation outside its\nread-only surface.\nFor an explicit commit, branch, merge-request, or code-identity question,\nset MCP `include_development:true`, `projection:\"compact\"`, and\n`select:[\"scm\"]` when topology is not needed, or use\n`jira issue graph \u003CKEY> --include-development --projection compact --select scm`\nunder read-only policy when MCP is unavailable. Require a complete experimental\nDevelopment source even when its retained count is zero. MCP omits\nDevelopment-node URLs. Treat its SCM coordinates as untrusted evidence: ATL\nitself never contacts GitLab, and any later read requires exact equality between\nthe returned lowercase host and an owner-approved host plus a separately\nauthenticated read-only client for that exact host. Never reuse Jira credentials\nor continue after a host mismatch.\n\n### 1. Extract search terms\n\nKeep the core nouns, prepare one narrow and one broad variant, and carry any\nknown space\u002Fproject scope into the query.\n\n### 2. Search both backends\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl conf search --cql 'siteSearch ~ \"billing retry queue\"' --limit 15\natl jira issue search --jql 'text ~ \"billing retry queue\" ORDER BY updated DESC' \\\n  --columns key,summary,status,updated --limit 15\n```\n\nCQL fallbacks: `text ~ \"...\"`, then `title ~ \"...\"`. Scope with `space = KEY`\nor `project = KEY` when known. Retry one prepared variant after an empty result,\nthen report the exact searches rather than implying full coverage. Freeze the\nfirst useful result pages before expanding anything: require Jira\n`page.complete:true` and Confluence top-level `complete:true`, or continue from\n`next_cursor` \u002F report the partial search instead of claiming absence. To\ncontinue, repeat the exact query and page limit and pass only the returned\ncursor:\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl conf search --cql 'siteSearch ~ \"billing retry queue\"' --limit 15 --cursor '\u003Cnext-cursor>'\natl jira issue search --jql 'text ~ \"billing retry queue\" ORDER BY updated DESC' \\\n  --columns key,summary,status,updated --limit 15 --cursor '\u003Cnext-cursor>'\n```\n\n### 3. Read bounded Confluence evidence\n\nFor the 2–4 best page hits, inspect the outline, then read only the relevant\nsection. A numeric id emitted by `conf search` is already a stable exact\nreference; pass it directly to `outline`\u002F`section`. Use `resolve` only for a URL,\nshort link, or user-supplied reference whose stable id is still unknown. Use a\nfull page only when no heading isolates the answer. For typed tools, pass the\nsection `heading` as the exact outline `title`, without Markdown `#` prefixes.\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl conf page outline '\u003Csearch-result-id>'\natl conf page section '\u003Csearch-result-id>' --heading 'Retries' --max-bytes 32768 \\\n  --expected-version '\u003Coutline-version>'\natl conf page sections '\u003Csearch-result-id>' --heading 'Retries' --heading 'Limits' \\\n  --max-bytes 65536 --expected-version '\u003Coutline-version>'\n```\n\nKeep these selection reads as JSON: `-o text` would hide completeness and the\nsection version gate needed for the decision. Require the outline's\n`complete:true`, then copy its exact positive `version` into\n`--expected-version`. Require each section result to report `complete:true` and\n`page_version_gated:true`. A duplicate heading needs explicit `--occurrence`;\n`truncated:true` means the omitted tail is not evidence of absence.\nWhen several headings from one page are relevant, prefer `page sections` (or\n`confluence_page_sections`) so they share one version-bound snapshot instead of\nre-downloading and re-parsing the page for every heading. Preserve requested\norder and require reconciled counts before using the result.\n\n### 4. Read targeted Jira evidence\n\nDiscover non-empty field metadata before reading custom values. Request only\nselected fields and qualified references; fetch history only when chronology\nmatters. If the question instead asks what is connected to the selected exact\nissue, prefer one typed `jira_issue_graph` call. Start at depth zero and use a\ngreater depth only for exact structured Jira relations. Its MCP route cannot\nresolve Confluence; use the CLI graph route only when id\u002Ftitle page metadata is\nrequired, then continue with a bounded page outline\u002Fsection after exact page\nidentity is known. Compact selection occurs after full collection and changes\nno request. Inspect `projection.selected`\u002F`projection.omitted`, incomplete\nsources, bounds, frontier, warnings, and reconciled counts; copy only emitted\ncanonical URL or SCM facts and never reconstruct an omitted URL identity.\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl jira issue fields KEY-123 --metadata-only\natl jira issue field get KEY-123 --field 'Delivery Notes' --max-bytes 16384\natl jira issue refs KEY-123 --fields 'Delivery Notes'\natl jira issue history KEY-123 --field 'Delivery Notes' --since 2026-07-01 --summary-only\n```\n\nRequire top-level and named-source completeness before claiming a link\u002Fchange\nis absent. For refs, use top-level `summary` and per-issue\n`reference_summary` for total\u002Fper-kind references and source-value counts; do\nnot manually add the nested arrays. The reconciliation booleans make count and\ncompleteness disagreements explicit. A repeated URL is deduplicated within one\nissue but counted once per issue across a multi-issue selection. Use\ntyped `jira_issue_refs` when only those reconciled aggregate facts are needed;\nit deliberately omits every raw URL and narrative field. Keep the CLI route\nabove when the selected URL itself must be followed into Confluence. Use\n`jira epic digest` instead when an epic question spans children, status\nnarrative, comments, history, and refs.\n\n### 5. Escalate only when bounded reads are insufficient\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl conf page view '\u003Cid-or-url>' -o text\natl jira issue get KEY-123 \\\n  --fields summary,status,issuetype,description,labels,updated,resolution\natl jira issue comment list KEY-123 -o text\n```\n\nFor repeated deep reading, mirror once and search locally:\n\n\u003C!-- atl:read-only-shell -->\n```sh\nexport ATL_READ_ONLY=1\natl conf pull --cql 'space = KEY AND siteSearch ~ \"...\"' --into \u003Cdir>\nrg -il 'retry queue' \u003Cdir>\n```\n\nThe mirror amortizes later reads, but a pull cap or comment warning still\nlimits what absence claims are justified.\n\n### 6. Synthesize with citations\n\n- Lead with the answer, then evidence; cite page title + id or issue key.\n- Prefer the most recently updated source when sources conflict, and say so.\n- Close with what was not found, queries used, and every incomplete\u002Ftruncated\n  source.\n\n## Pitfalls\n\n| Symptom | Cause \u002F fix |\n|---|---|\n| exit 4 on a page read | stale id or unresolved URL — retry `page resolve`; cite only evidence actually read |\n| exit 3 | PAT missing\u002Fexpired — `atl auth status`, then `$setup` |\n| exit 2 with CQL\u002FJQL | wrap the query in single quotes and values in double quotes |\n| body too large | prefer `outline` → bounded `section`; then full `view` or mirror `.md`, never raw `.csf` |\n",{"name":5,"description":7},"main","c6ed32ed384aa5e9a3e86d4528f16dc13833ce66","plugins\u002Fatl\u002Fskills\u002Fsearch-knowledge",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 search-knowledge",{"tool":37,"command":38},"bunx","bunx skills add isukharev\u002Fatl --skill search-knowledge",{"tool":40,"command":41},"pnpm","pnpm dlx skills add isukharev\u002Fatl --skill search-knowledge","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fisukharev\u002Fatl\u002Fblob\u002Fmain\u002Fplugins\u002Fatl\u002Fskills\u002Fsearch-knowledge\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"agents\u002Fopenai.yaml","REFERENCE","参考文档",239,"https:\u002F\u002Fgithub.com\u002Fisukharev\u002Fatl\u002Fblob\u002Fmain\u002Fplugins\u002Fatl\u002Fskills\u002Fsearch-knowledge\u002Fagents\u002Fopenai.yaml",[52,59,66,73,80,87],{"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":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"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":89,"categories":90,"keywords":91,"publishedAt":19},"01M75YTSX670SW6NSBA1HGAG65","https:\u002F\u002Fgithub.com\u002Fisukharev\u002Fatl\u002Fblob\u002Fmain\u002Fskills\u002Fsearch-knowledge\u002FSKILL.md",[],[]]