[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M699E30CWPD30MP45HZSJ24N":3,"skill-same:01M699E30CWPD30MP45HZSJ24N":78},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":49,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M699E30CWPD30MP45HZSJ24N","docs-impact-classifier",null,"Use this skill to classify the documentation impact of a pull request diff, returning one of three verdicts -- no-change, in-place edit, or structural change -- with bounded LLM cost. Activate as a sibling skill of docs-sync; the orchestrator calls this first, before any panel spawn, to keep cost floor at 1 LLM call when no docs work is needed. Reads .apm\u002Fdocs-index.yml as the corpus map; never reads the full corpus.","microsoft\u002Fapm","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M699CC41JR5QW38C9PDX6101",4369,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fapm\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdocs-impact-classifier\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"docs impact classifier","impact","docs","classifier","never","when","request","at","classify","structural","map","activate","orchestrator","spawn","edit","work","apm","documentation","sync","change","2026-11-10 10:12:30",false,"---\nname: docs-impact-classifier\ndescription: >-\n  Use this skill to classify the documentation impact of a pull\n  request diff, returning one of three verdicts -- no-change,\n  in-place edit, or structural change -- with bounded LLM cost.\n  Activate as a sibling skill of docs-sync; the orchestrator calls\n  this first, before any panel spawn, to keep cost floor at 1 LLM\n  call when no docs work is needed. Reads .apm\u002Fdocs-index.yml as\n  the corpus map; never reads the full corpus.\n---\n\n# docs-impact-classifier\n\nSingle responsibility: given a PR diff and the `.apm\u002Fdocs-index.yml`\ncorpus map, emit ONE classification verdict.\n\nThis skill is the cost gate for the entire docs-sync system. ~70% of\nPRs should exit at verdict `no_change` with zero panel spawn.\n\n## Architecture\n\nThis is a 3-layer funnel inside a single skill invocation:\n\n- **L0 deterministic path gate** -- pure file-path matching, no LLM.\n- **L1 symbol extraction + corpus grep** -- pure text processing, no LLM.\n- **L2 LLM classifier** -- bounded ~8 KB context envelope, 1 call.\n\nThe skill returns the verdict from the earliest layer that can decide.\n\n## Step 1: L0 deterministic path gate (no LLM)\n\nRead `.apm\u002Fdocs-index.yml` to load `no_impact_paths[]` and\n`user_surface_paths[]`. Get the changed file list from the PR diff\n(`gh pr diff --name-only`).\n\n```\nif every changed file matches no_impact_paths AND none match user_surface_paths:\n    return {verdict: \"no_change\", confidence: \"high\", source: \"L0\", scope_pages: []}\n```\n\nThis handles:\n- Test-only PRs (`tests\u002F**`)\n- CI workflow PRs (`.github\u002Fworkflows\u002F**`)\n- Doc-only PRs (`docs\u002F**`) -- out of scope, docs-sync doesn't review docs PRs\n- Primitive-only PRs (`.apm\u002F**`)\n- Script and meta PRs\n\nExpected hit rate: ~70% of PRs short-circuit here.\n\n## Step 2: L1 symbol extraction + corpus grep (no LLM)\n\nIf L0 did not exit, extract user-observable symbols from the diff:\n\n- **CLI command names** -- grep diff for `^@click.command`, `^@cli.command`, or any `apm \u003Cverb>` mention in added\u002Fremoved lines.\n- **Flag names** -- grep diff for `^@click.option`, `--[a-z-]+` patterns.\n- **Public API symbols** -- added\u002Fremoved `def \u003Cname>` in `src\u002Fapm_cli\u002F__init__.py` or `src\u002Fapm_cli\u002Fapi\u002F**`.\n- **Schema keys** -- added\u002Fremoved keys in `apm.yml`, `apm.lock.yaml`, `apm-policy.yml` parsers.\n- **Error strings** -- added\u002Fremoved string literals in user-facing error paths (look for `_rich_error`, `click.echo`, `raise ... Error(`).\n\nFor each extracted symbol, consult `.apm\u002Fdocs-index.yml#symbol_index`\nto find the documented pages. Collect all hits into `candidate_pages[]`.\n\nAlso `grep -rn \u003Csymbol> docs\u002Fsrc\u002Fcontent\u002Fdocs\u002F` for symbols NOT in\nthe index (catches drift between index and corpus).\n\n## Step 3: L2 LLM verdict (1 call, bounded context)\n\nIf L1 found zero candidate pages AND zero schema\u002FCLI\u002Fflag changes:\nreturn `{verdict: \"no_change\", confidence: \"medium\", source: \"L1\", scope_pages: []}`.\n\nOtherwise, invoke the doc-analyser persona with EXACTLY this context\nenvelope (must fit in ~8 KB tokens):\n\n- PR title + body (first 500 chars)\n- Diff stats (`gh pr diff --stat` output)\n- `.apm\u002Fdocs-index.yml` (the whole file; it's ~8 KB seeded, may grow)\n- L1 candidate pages with +\u002F-5 lines of context per hit\n- Path-classification summary from L0\n- **`pr_doc_diff_paths[]`**: the list of paths under `docs\u002Fsrc\u002Fcontent\u002Fdocs\u002F**`\n  that the PR itself already modifies (drives the `in_place_resolved`\n  downgrade rule in \"In-place-resolved detection\" below).\n\nAsk doc-analyser to return JSON matching this schema:\n\n```json\n{\n  \"verdict\": \"no_change\" | \"in_place_resolved\" | \"in_place\" | \"structural\",\n  \"confidence\": \"low\" | \"medium\" | \"high\",\n  \"scope_pages\": [\"docs\u002Fsrc\u002Fcontent\u002Fdocs\u002F...\"],\n  \"structural_proposal\": {\n    \"new_pages\": [{\"slug\": \"...\", \"rationale\": \"...\"}],\n    \"moved_pages\": [{\"from\": \"...\", \"to\": \"...\"}],\n    \"toc_changes\": \"\u003Cone-paragraph>\"\n  },\n  \"reasoning\": \"\u003Cone-paragraph: what surface changed, what docs are affected, why this verdict>\"\n}\n```\n\n`structural_proposal` is populated only when verdict is `structural`.\n`scope_pages` is populated for `in_place` and `structural` verdicts.\n\n## Verdict semantics\n\n| Verdict | Meaning | Panel size | Cost |\n|---|---|---|---|\n| `no_change` | No user-observable surface changed | 0 panel spawns | ~0-1 LLM call |\n| `in_place_resolved` | Doc impact existed, but the PR's OWN diff already patches every page in `scope_pages` -- author already did the work | 0 panel spawns; skill emits NO advisory | ~1 LLM call |\n| `in_place` | One to a few pages need a paragraph or section update; no new pages, no TOC change | N candidate pages x (doc-writer + python-architect) + editorial-owner + growth-hacker + CDO | ~6-12 LLM calls |\n| `structural` | A new page is needed, OR an existing page should be split\u002Fmerged, OR the TOC needs to change to fit a new concept | architect first (TOC delta), then in-place panel for affected pages | ~10-15 LLM calls |\n\n## In-place-resolved detection (false-alarm killer)\n\nBEFORE returning `in_place`, intersect your `scope_pages[]` with the\nlist of files the PR itself touches under `docs\u002F**` (provided to you\nby the orchestrator under `pr_doc_diff_paths[]`). If EVERY scope page\nalready appears in `pr_doc_diff_paths`, downgrade to `in_place_resolved`\nand emit `reasoning` of the form \"Author already patched \u003Cpage list>\".\nThis is the well-behaved-author path; the skill stays silent.\n\nIf only SOME scope pages are pre-patched, keep `in_place` and list the\nREMAINING (unpatched) pages in `scope_pages[]`. Note the pre-patched\nones in `reasoning` for transparency.\n\n## Rename \u002F breaking-change heuristic (PR 1244 class)\n\nWhen the L1 layer reports an ADDED public symbol that matches an\nEXISTING public symbol's name in the corpus (e.g. PR adds `apm update`\nbut `apm update` already appears in 9 docs pages with different\nsemantics), this is a RENAME or BREAKING SEMANTIC CHANGE. Bias toward\n`structural` (not `in_place`):\n- the existing page describing the OLD semantics may need to SPLIT\n  into two pages (old verb under new name + new verb keeping old name)\n- the TOC may need a NEW reference page for the renamed verb\n- every passing mention in the corpus needs verification\n\nDo NOT collapse a rename into `in_place` just because the affected\npages already exist. The shape of the work is structural even when no\nnew page is strictly required.\n\n## Anti-patterns (verdict shape errors)\n\n- Returning `in_place` with empty `scope_pages` -- invalid; orchestrator will reject.\n- Returning `structural` without `structural_proposal` -- invalid.\n- Returning `in_place` when EVERY scope page is in `pr_doc_diff_paths` -- should be `in_place_resolved`.\n- Inflating `structural` to seem thorough -- the CDO will catch this. Return the minimal true verdict.\n- Missing the rename heuristic above and emitting `in_place` for a verb-swap PR.\n- Reading the corpus (the .md files themselves) at L2 -- context budget breach. You read the index, not the corpus.\n\n## Output contract\n\nReturn a SINGLE JSON document matching the schema in Step 3 as the\nfinal message of your task. No prose around the JSON. The\norchestrator parses your last message.\n","# docs-impact-classifier\n\nSingle responsibility: given a PR diff and the `.apm\u002Fdocs-index.yml`\ncorpus map, emit ONE classification verdict.\n\nThis skill is the cost gate for the entire docs-sync system. ~70% of\nPRs should exit at verdict `no_change` with zero panel spawn.\n\n## Architecture\n\nThis is a 3-layer funnel inside a single skill invocation:\n\n- **L0 deterministic path gate** -- pure file-path matching, no LLM.\n- **L1 symbol extraction + corpus grep** -- pure text processing, no LLM.\n- **L2 LLM classifier** -- bounded ~8 KB context envelope, 1 call.\n\nThe skill returns the verdict from the earliest layer that can decide.\n\n## Step 1: L0 deterministic path gate (no LLM)\n\nRead `.apm\u002Fdocs-index.yml` to load `no_impact_paths[]` and\n`user_surface_paths[]`. Get the changed file list from the PR diff\n(`gh pr diff --name-only`).\n\n```\nif every changed file matches no_impact_paths AND none match user_surface_paths:\n    return {verdict: \"no_change\", confidence: \"high\", source: \"L0\", scope_pages: []}\n```\n\nThis handles:\n- Test-only PRs (`tests\u002F**`)\n- CI workflow PRs (`.github\u002Fworkflows\u002F**`)\n- Doc-only PRs (`docs\u002F**`) -- out of scope, docs-sync doesn't review docs PRs\n- Primitive-only PRs (`.apm\u002F**`)\n- Script and meta PRs\n\nExpected hit rate: ~70% of PRs short-circuit here.\n\n## Step 2: L1 symbol extraction + corpus grep (no LLM)\n\nIf L0 did not exit, extract user-observable symbols from the diff:\n\n- **CLI command names** -- grep diff for `^@click.command`, `^@cli.command`, or any `apm \u003Cverb>` mention in added\u002Fremoved lines.\n- **Flag names** -- grep diff for `^@click.option`, `--[a-z-]+` patterns.\n- **Public API symbols** -- added\u002Fremoved `def \u003Cname>` in `src\u002Fapm_cli\u002F__init__.py` or `src\u002Fapm_cli\u002Fapi\u002F**`.\n- **Schema keys** -- added\u002Fremoved keys in `apm.yml`, `apm.lock.yaml`, `apm-policy.yml` parsers.\n- **Error strings** -- added\u002Fremoved string literals in user-facing error paths (look for `_rich_error`, `click.echo`, `raise ... Error(`).\n\nFor each extracted symbol, consult `.apm\u002Fdocs-index.yml#symbol_index`\nto find the documented pages. Collect all hits into `candidate_pages[]`.\n\nAlso `grep -rn \u003Csymbol> docs\u002Fsrc\u002Fcontent\u002Fdocs\u002F` for symbols NOT in\nthe index (catches drift between index and corpus).\n\n## Step 3: L2 LLM verdict (1 call, bounded context)\n\nIf L1 found zero candidate pages AND zero schema\u002FCLI\u002Fflag changes:\nreturn `{verdict: \"no_change\", confidence: \"medium\", source: \"L1\", scope_pages: []}`.\n\nOtherwise, invoke the doc-analyser persona with EXACTLY this context\nenvelope (must fit in ~8 KB tokens):\n\n- PR title + body (first 500 chars)\n- Diff stats (`gh pr diff --stat` output)\n- `.apm\u002Fdocs-index.yml` (the whole file; it's ~8 KB seeded, may grow)\n- L1 candidate pages with +\u002F-5 lines of context per hit\n- Path-classification summary from L0\n- **`pr_doc_diff_paths[]`**: the list of paths under `docs\u002Fsrc\u002Fcontent\u002Fdocs\u002F**`\n  that the PR itself already modifies (drives the `in_place_resolved`\n  downgrade rule in \"In-place-resolved detection\" below).\n\nAsk doc-analyser to return JSON matching this schema:\n\n```json\n{\n  \"verdict\": \"no_change\" | \"in_place_resolved\" | \"in_place\" | \"structural\",\n  \"confidence\": \"low\" | \"medium\" | \"high\",\n  \"scope_pages\": [\"docs\u002Fsrc\u002Fcontent\u002Fdocs\u002F...\"],\n  \"structural_proposal\": {\n    \"new_pages\": [{\"slug\": \"...\", \"rationale\": \"...\"}],\n    \"moved_pages\": [{\"from\": \"...\", \"to\": \"...\"}],\n    \"toc_changes\": \"\u003Cone-paragraph>\"\n  },\n  \"reasoning\": \"\u003Cone-paragraph: what surface changed, what docs are affected, why this verdict>\"\n}\n```\n\n`structural_proposal` is populated only when verdict is `structural`.\n`scope_pages` is populated for `in_place` and `structural` verdicts.\n\n## Verdict semantics\n\n| Verdict | Meaning | Panel size | Cost |\n|---|---|---|---|\n| `no_change` | No user-observable surface changed | 0 panel spawns | ~0-1 LLM call |\n| `in_place_resolved` | Doc impact existed, but the PR's OWN diff already patches every page in `scope_pages` -- author already did the work | 0 panel spawns; skill emits NO advisory | ~1 LLM call |\n| `in_place` | One to a few pages need a paragraph or section update; no new pages, no TOC change | N candidate pages x (doc-writer + python-architect) + editorial-owner + growth-hacker + CDO | ~6-12 LLM calls |\n| `structural` | A new page is needed, OR an existing page should be split\u002Fmerged, OR the TOC needs to change to fit a new concept | architect first (TOC delta), then in-place panel for affected pages | ~10-15 LLM calls |\n\n## In-place-resolved detection (false-alarm killer)\n\nBEFORE returning `in_place`, intersect your `scope_pages[]` with the\nlist of files the PR itself touches under `docs\u002F**` (provided to you\nby the orchestrator under `pr_doc_diff_paths[]`). If EVERY scope page\nalready appears in `pr_doc_diff_paths`, downgrade to `in_place_resolved`\nand emit `reasoning` of the form \"Author already patched \u003Cpage list>\".\nThis is the well-behaved-author path; the skill stays silent.\n\nIf only SOME scope pages are pre-patched, keep `in_place` and list the\nREMAINING (unpatched) pages in `scope_pages[]`. Note the pre-patched\nones in `reasoning` for transparency.\n\n## Rename \u002F breaking-change heuristic (PR 1244 class)\n\nWhen the L1 layer reports an ADDED public symbol that matches an\nEXISTING public symbol's name in the corpus (e.g. PR adds `apm update`\nbut `apm update` already appears in 9 docs pages with different\nsemantics), this is a RENAME or BREAKING SEMANTIC CHANGE. Bias toward\n`structural` (not `in_place`):\n- the existing page describing the OLD semantics may need to SPLIT\n  into two pages (old verb under new name + new verb keeping old name)\n- the TOC may need a NEW reference page for the renamed verb\n- every passing mention in the corpus needs verification\n\nDo NOT collapse a rename into `in_place` just because the affected\npages already exist. The shape of the work is structural even when no\nnew page is strictly required.\n\n## Anti-patterns (verdict shape errors)\n\n- Returning `in_place` with empty `scope_pages` -- invalid; orchestrator will reject.\n- Returning `structural` without `structural_proposal` -- invalid.\n- Returning `in_place` when EVERY scope page is in `pr_doc_diff_paths` -- should be `in_place_resolved`.\n- Inflating `structural` to seem thorough -- the CDO will catch this. Return the minimal true verdict.\n- Missing the rename heuristic above and emitting `in_place` for a verb-swap PR.\n- Reading the corpus (the .md files themselves) at L2 -- context budget breach. You read the index, not the corpus.\n\n## Output contract\n\nReturn a SINGLE JSON document matching the schema in Step 3 as the\nfinal message of your task. No prose around the JSON. The\norchestrator parses your last message.\n",{"name":5,"description":7},"main","2920043258932f0f67e6f01df7b9047eb42f358c",".agents\u002Fskills\u002Fdocs-impact-classifier",426,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fapm","https:\u002F\u002Fmicrosoft.github.io\u002Fapm\u002F","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-14 10:21:38",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add microsoft\u002Fapm --skill docs-impact-classifier",{"tool":60,"command":61},"bunx","bunx skills add microsoft\u002Fapm --skill docs-impact-classifier",{"tool":63,"command":64},"pnpm","pnpm dlx skills add microsoft\u002Fapm --skill docs-impact-classifier","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fapm\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdocs-impact-classifier\u002FSKILL.md",true,[68,74],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"agents\u002Fopenai.yaml","REFERENCE","参考文档",166,"https:\u002F\u002Fgithub.com\u002Fnichee\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude\u002Fskills\u002Fimprove-codebase-architecture\u002Fagents\u002Fopenai.yaml",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"HTML-REPORT.md",6685,"https:\u002F\u002Fgithub.com\u002Fnichee\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude\u002Fskills\u002Fimprove-codebase-architecture\u002FHTML-REPORT.md",[79,88,93,99,105,110],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":87},"01M78JKQKRC85N30WT8HPN3EHM","autopilot-issue-accept","Use this skill to accept ONE microsoft\u002Fapm issue with a declared scope. The canvas Accept button, or a maintainer asking to accept an issue, starts it. Draft only from the latest triage proposed scope, get exact-text approval in this chat from a GOVERNANCE roster human, post that comment as that human, then add status\u002Faccepted. Do not invent scope, do not accept pull requests, and do not implement the issue.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fapm\u002Fblob\u002Fmain\u002Fpackages\u002Fautopilot\u002Fautopilot-issue-accept\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":89,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":87},"01M78JK63ZWG0XX043NVHZHNH9","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fapm\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fautopilot-issue-accept\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"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":96,"categories":97,"keywords":98,"publishedAt":39},"01M699JMZBYWPBT7JYWBSB95Z6","hello","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fapm\u002Fblob\u002Fmain\u002Ftests\u002Fintegration\u002Ffixtures\u002Ftarget_resolution\u002Fshared\u002Fminimal_skill\u002F.apm\u002Fskills\u002Fhello\u002FSKILL.md",[],[95],{"skillNo":100,"name":101,"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":102,"categories":103,"keywords":104,"publishedAt":39},"01M699JKAMZ4DH1PYJMXHE4FG4","placeholder","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fapm\u002Fblob\u002Fmain\u002Ftests\u002Fintegration\u002Ffixtures\u002Ftarget_resolution\u002Fs25_copilot_alias\u002F.apm\u002Fskills\u002Fplaceholder\u002FSKILL.md",[],[101],{"skillNo":106,"name":101,"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":107,"categories":108,"keywords":109,"publishedAt":39},"01M699JHR9DKJ7BZHAPF6DZX2Z","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fapm\u002Fblob\u002Fmain\u002Ftests\u002Fintegration\u002Ffixtures\u002Ftarget_resolution\u002Fs24_priority_override\u002F.apm\u002Fskills\u002Fplaceholder\u002FSKILL.md",[],[101],{"skillNo":111,"name":101,"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":112,"categories":113,"keywords":114,"publishedAt":39},"01M699JG5BJBZSWM25F1VMJ2H6","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fapm\u002Fblob\u002Fmain\u002Ftests\u002Fintegration\u002Ffixtures\u002Ftarget_resolution\u002Fs23_error_renderer\u002F.apm\u002Fskills\u002Fplaceholder\u002FSKILL.md",[],[101]]