[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69997KD41GX9F4Y70ASHVVH":3,"skill-same:01M69997KD41GX9F4Y70ASHVVH":68},{"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},"01M69997KD41GX9F4Y70ASHVVH","author-contributions",null,"Identify all files a specific author contributed to on a branch vs its upstream, tracing code through renames. Use when asked who edited what, what code an author contributed, or to audit authorship before a merge. This skill should be run as a subagent — it performs many git operations and returns a concise table.","microsoft\u002Fvscode","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M6998NK2WED5M549DX06VBCH",195271,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvscode\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fauthor-contributions\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"author","author contributions","use","when","authorship","concise","it","git operations","as","upstream","files","operations","branch","subagent","tracing","audit","git","code","run","merge","2026-11-10 10:12:30",false,"---\nname: author-contributions\ndescription: Identify all files a specific author contributed to on a branch vs its upstream, tracing code through renames. Use when asked who edited what, what code an author contributed, or to audit authorship before a merge. This skill should be run as a subagent — it performs many git operations and returns a concise table.\n---\n\nWhen asked to find all files a specific author contributed to on a branch (compared to main or another upstream), follow this procedure. The goal is to produce a simple table that both humans and LLMs can consume.\n\n## Run as a Subagent\n\nThis skill involves many sequential git commands. Delegate it to a subagent with a prompt like:\n\n> Find every file that author \"Full Name\" contributed to on branch `\u003Cbranch>` compared to `\u003Cupstream>`. Trace contributions through file renames. Return a markdown table with columns: Status (DIRECT or VIA_RENAME), File Path, and Lines (+\u002F-). Include a summary line at the end.\n\n## Procedure\n\n### 1. Identify the author's exact git identity\n\n```bash\ngit log --format=\"%an \u003C%ae>\" \u003Cupstream>..\u003Cbranch> | sort -u\n```\n\nMatch the requested person to their exact `--author=` string. Do not guess — short usernames won't match full display names (resolve via `git log` or the GitHub MCP `get_me` tool).\n\n### 2. Collect all files the author directly committed to\n\n```bash\ngit log --author=\"\u003CExact Name>\" --format=\"%H\" \u003Cupstream>..\u003Cbranch>\n```\n\nFor each commit hash, extract touched files:\n\n```bash\ngit diff-tree --no-commit-id --name-only -r \u003Chash>\n```\n\nUnion all results into a set (`author_files`).\n\n### 3. Build rename map across the entire branch\n\nFor **every** commit on the branch (not just the author's), extract renames:\n\n```bash\ngit diff-tree --no-commit-id -r -M \u003Chash>\n```\n\nParse lines with `R` status to build a map: `new_path → {old_paths}`.\n\n### 4. Get the merge diff file list\n\n```bash\ngit diff --name-only \u003Cupstream>..\u003Cbranch>\n```\n\nThese are the files that will actually land when the branch merges.\n\n### 5. Classify each file in the merge diff\n\nFor each file in step 4:\n- If it's in `author_files` → **DIRECT**\n- Else, walk the rename map transitively (follow chains: current → old → older) and check if any ancestor is in `author_files` → **VIA_RENAME**\n- Otherwise → not this author's contribution\n\n### 6. Get diff stats\n\n```bash\ngit diff --stat \u003Cupstream>..\u003Cbranch> -- \u003Cfile1> \u003Cfile2> ...\n```\n\n### 7. Return the table\n\nFormat the result as a markdown table:\n\n```\n| Status | File | +\u002F- |\n|--------|------|-----|\n| DIRECT | src\u002Fvs\u002Ffoo\u002Fbar.ts | +120\u002F-5 |\n| VIA_RENAME | src\u002Fvs\u002Fbaz\u002Fqux.ts | +300 |\n| ... | ... | ... |\n\n**Total: N files, +X\u002F-Y lines**\n```\n\n## Important Notes\n\n- **Use Python for the heavy lifting.** Shell loops with inline comments break in zsh. Write a temp `.py` script, run it, then delete it.\n- **Author matching is exact.** Always run step 1 first. `--author` does substring matching but you must verify the right person is matched (e.g., don't match \"Joshua Smith\" when looking for \"Josh S.\"). Use the GitHub MCP `get_me` tool or `git log` output to resolve the correct full name.\n- **Renames can be multi-hop.** A file may have moved `contrib\u002Fchat\u002F` → `agentSessions\u002F` → `sessions\u002F`. The rename map must be walked transitively.\n- **Only report files in the merge diff** (step 4). Files the author touched that were later deleted entirely should not appear — they won't land in the upstream.\n- **The rename map must include all authors' commits**, not just the target author's. Other people often do the rename commits (e.g., bulk refactors\u002Fmoves).\n\n## Example Python Script\n\n```python\nimport subprocess, os\n\nos.chdir('\u003Crepo_root>')\nUPSTREAM = 'main'\nAUTHOR = '\u003CAuthor Name>'  # Resolve via `git log` or GitHub MCP `get_me`\n\n# Step 2: author's files\ncommits = subprocess.check_output(\n    ['git', 'log', f'--author={AUTHOR}', '--format=%H', f'{UPSTREAM}..HEAD'],\n    text=True).strip().split('\\n')\nauthor_files = set()\nfor h in (c for c in commits if c):\n    files = subprocess.check_output(\n        ['git', 'diff-tree', '--no-commit-id', '--name-only', '-r', h],\n        text=True).strip().split('\\n')\n    author_files.update(f for f in files if f)\n\n# Step 3: rename map from ALL commits\nall_commits = subprocess.check_output(\n    ['git', 'log', '--format=%H', f'{UPSTREAM}..HEAD'],\n    text=True).strip().split('\\n')\nrename_map = {}  # new_name -> set(old_names)\nfor h in (c for c in all_commits if c):\n    out = subprocess.check_output(\n        ['git', 'diff-tree', '--no-commit-id', '-r', '-M', h],\n        text=True, timeout=5).strip()\n    for line in out.split('\\n'):\n        if not line:\n            continue\n        parts = line.split('\\t')\n        if len(parts) >= 3 and 'R' in parts[0]:\n            rename_map.setdefault(parts[2], set()).add(parts[1])\n\n# Step 4: merge diff\ndiff_files = subprocess.check_output(\n    ['git', 'diff', '--name-only', f'{UPSTREAM}..HEAD'],\n    text=True).strip().split('\\n')\n\n# Step 5: classify\nresults = []\nfor f in (x for x in diff_files if x):\n    if f in author_files:\n        results.append(('DIRECT', f))\n    else:\n        # walk rename chain\n        chain, to_check = set(), [f]\n        while to_check:\n            cur = to_check.pop()\n            if cur in chain:\n                continue\n            chain.add(cur)\n            to_check.extend(rename_map.get(cur, []))\n        chain.discard(f)\n        if chain & author_files:\n            results.append(('VIA_RENAME', f))\n\n# Step 6: stats\nif results:\n    stat = subprocess.check_output(\n        ['git', 'diff', '--stat', f'{UPSTREAM}..HEAD', '--'] +\n        [f for _, f in results], text=True)\n    print(stat)\n\n# Step 7: table\nfor kind, f in sorted(results, key=lambda x: x[1]):\n    print(f'| {kind:12s} | {f} |')\nprint(f'\\nTotal: {len(results)} files')\n```\n\n### Alternative Script\n\nAfter following the process above, run this script to cross-check files touched by an author against the branch diff.   You can do this both with an without src\u002Fvs\u002Fsessions.\n\n```\nAUTHOR=\"\"\n\n# 1. Find commits by author on this branch (not on main)\ngit log main...HEAD --author=\"$AUTHOR\" --format=\"%H\"\n\n# 2. Get unique files touched across all those commits, excluding src\u002Fvs\u002Fsessions\u002F\ngit log main...HEAD --author=\"$AUTHOR\" --format=\"%H\" \\\n  | xargs -I{} git diff-tree --no-commit-id -r --name-only {} \\\n  | sort -u \\\n  | grep -v '^src\u002Fvs\u002Fsessions\u002F'\n\n# 3. Cross-reference with branch diff to keep only files still changed vs main\ngit log main...HEAD --author=\"$AUTHOR\" --format=\"%H\" \\\n  | xargs -I{} git diff-tree --no-commit-id -r --name-only {} \\\n  | sort -u \\\n  | grep -v '^src\u002Fvs\u002Fsessions\u002F' \\\n  | while read f; do git diff main...HEAD --name-only -- \"$f\" 2>\u002Fdev\u002Fnull; done \\\n  | sort -u\n```\n","When asked to find all files a specific author contributed to on a branch (compared to main or another upstream), follow this procedure. The goal is to produce a simple table that both humans and LLMs can consume.\n\n## Run as a Subagent\n\nThis skill involves many sequential git commands. Delegate it to a subagent with a prompt like:\n\n> Find every file that author \"Full Name\" contributed to on branch `\u003Cbranch>` compared to `\u003Cupstream>`. Trace contributions through file renames. Return a markdown table with columns: Status (DIRECT or VIA_RENAME), File Path, and Lines (+\u002F-). Include a summary line at the end.\n\n## Procedure\n\n### 1. Identify the author's exact git identity\n\n```bash\ngit log --format=\"%an \u003C%ae>\" \u003Cupstream>..\u003Cbranch> | sort -u\n```\n\nMatch the requested person to their exact `--author=` string. Do not guess — short usernames won't match full display names (resolve via `git log` or the GitHub MCP `get_me` tool).\n\n### 2. Collect all files the author directly committed to\n\n```bash\ngit log --author=\"\u003CExact Name>\" --format=\"%H\" \u003Cupstream>..\u003Cbranch>\n```\n\nFor each commit hash, extract touched files:\n\n```bash\ngit diff-tree --no-commit-id --name-only -r \u003Chash>\n```\n\nUnion all results into a set (`author_files`).\n\n### 3. Build rename map across the entire branch\n\nFor **every** commit on the branch (not just the author's), extract renames:\n\n```bash\ngit diff-tree --no-commit-id -r -M \u003Chash>\n```\n\nParse lines with `R` status to build a map: `new_path → {old_paths}`.\n\n### 4. Get the merge diff file list\n\n```bash\ngit diff --name-only \u003Cupstream>..\u003Cbranch>\n```\n\nThese are the files that will actually land when the branch merges.\n\n### 5. Classify each file in the merge diff\n\nFor each file in step 4:\n- If it's in `author_files` → **DIRECT**\n- Else, walk the rename map transitively (follow chains: current → old → older) and check if any ancestor is in `author_files` → **VIA_RENAME**\n- Otherwise → not this author's contribution\n\n### 6. Get diff stats\n\n```bash\ngit diff --stat \u003Cupstream>..\u003Cbranch> -- \u003Cfile1> \u003Cfile2> ...\n```\n\n### 7. Return the table\n\nFormat the result as a markdown table:\n\n```\n| Status | File | +\u002F- |\n|--------|------|-----|\n| DIRECT | src\u002Fvs\u002Ffoo\u002Fbar.ts | +120\u002F-5 |\n| VIA_RENAME | src\u002Fvs\u002Fbaz\u002Fqux.ts | +300 |\n| ... | ... | ... |\n\n**Total: N files, +X\u002F-Y lines**\n```\n\n## Important Notes\n\n- **Use Python for the heavy lifting.** Shell loops with inline comments break in zsh. Write a temp `.py` script, run it, then delete it.\n- **Author matching is exact.** Always run step 1 first. `--author` does substring matching but you must verify the right person is matched (e.g., don't match \"Joshua Smith\" when looking for \"Josh S.\"). Use the GitHub MCP `get_me` tool or `git log` output to resolve the correct full name.\n- **Renames can be multi-hop.** A file may have moved `contrib\u002Fchat\u002F` → `agentSessions\u002F` → `sessions\u002F`. The rename map must be walked transitively.\n- **Only report files in the merge diff** (step 4). Files the author touched that were later deleted entirely should not appear — they won't land in the upstream.\n- **The rename map must include all authors' commits**, not just the target author's. Other people often do the rename commits (e.g., bulk refactors\u002Fmoves).\n\n## Example Python Script\n\n```python\nimport subprocess, os\n\nos.chdir('\u003Crepo_root>')\nUPSTREAM = 'main'\nAUTHOR = '\u003CAuthor Name>'  # Resolve via `git log` or GitHub MCP `get_me`\n\n# Step 2: author's files\ncommits = subprocess.check_output(\n    ['git', 'log', f'--author={AUTHOR}', '--format=%H', f'{UPSTREAM}..HEAD'],\n    text=True).strip().split('\\n')\nauthor_files = set()\nfor h in (c for c in commits if c):\n    files = subprocess.check_output(\n        ['git', 'diff-tree', '--no-commit-id', '--name-only', '-r', h],\n        text=True).strip().split('\\n')\n    author_files.update(f for f in files if f)\n\n# Step 3: rename map from ALL commits\nall_commits = subprocess.check_output(\n    ['git', 'log', '--format=%H', f'{UPSTREAM}..HEAD'],\n    text=True).strip().split('\\n')\nrename_map = {}  # new_name -> set(old_names)\nfor h in (c for c in all_commits if c):\n    out = subprocess.check_output(\n        ['git', 'diff-tree', '--no-commit-id', '-r', '-M', h],\n        text=True, timeout=5).strip()\n    for line in out.split('\\n'):\n        if not line:\n            continue\n        parts = line.split('\\t')\n        if len(parts) >= 3 and 'R' in parts[0]:\n            rename_map.setdefault(parts[2], set()).add(parts[1])\n\n# Step 4: merge diff\ndiff_files = subprocess.check_output(\n    ['git', 'diff', '--name-only', f'{UPSTREAM}..HEAD'],\n    text=True).strip().split('\\n')\n\n# Step 5: classify\nresults = []\nfor f in (x for x in diff_files if x):\n    if f in author_files:\n        results.append(('DIRECT', f))\n    else:\n        # walk rename chain\n        chain, to_check = set(), [f]\n        while to_check:\n            cur = to_check.pop()\n            if cur in chain:\n                continue\n            chain.add(cur)\n            to_check.extend(rename_map.get(cur, []))\n        chain.discard(f)\n        if chain & author_files:\n            results.append(('VIA_RENAME', f))\n\n# Step 6: stats\nif results:\n    stat = subprocess.check_output(\n        ['git', 'diff', '--stat', f'{UPSTREAM}..HEAD', '--'] +\n        [f for _, f in results], text=True)\n    print(stat)\n\n# Step 7: table\nfor kind, f in sorted(results, key=lambda x: x[1]):\n    print(f'| {kind:12s} | {f} |')\nprint(f'\\nTotal: {len(results)} files')\n```\n\n### Alternative Script\n\nAfter following the process above, run this script to cross-check files touched by an author against the branch diff.   You can do this both with an without src\u002Fvs\u002Fsessions.\n\n```\nAUTHOR=\"\"\n\n# 1. Find commits by author on this branch (not on main)\ngit log main...HEAD --author=\"$AUTHOR\" --format=\"%H\"\n\n# 2. Get unique files touched across all those commits, excluding src\u002Fvs\u002Fsessions\u002F\ngit log main...HEAD --author=\"$AUTHOR\" --format=\"%H\" \\\n  | xargs -I{} git diff-tree --no-commit-id -r --name-only {} \\\n  | sort -u \\\n  | grep -v '^src\u002Fvs\u002Fsessions\u002F'\n\n# 3. Cross-reference with branch diff to keep only files still changed vs main\ngit log main...HEAD --author=\"$AUTHOR\" --format=\"%H\" \\\n  | xargs -I{} git diff-tree --no-commit-id -r --name-only {} \\\n  | sort -u \\\n  | grep -v '^src\u002Fvs\u002Fsessions\u002F' \\\n  | while read f; do git diff main...HEAD --name-only -- \"$f\" 2>\u002Fdev\u002Fnull; done \\\n  | sort -u\n```\n",{"name":5,"description":7},"main","11ba54a90a0ff8720cf47c086f5a9948eef9cf2c",".github\u002Fskills\u002Fauthor-contributions",43773,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvscode","https:\u002F\u002Fcode.visualstudio.com","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-11 08:47:49",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add microsoft\u002Fvscode --skill author-contributions",{"tool":60,"command":61},"bunx","bunx skills add microsoft\u002Fvscode --skill author-contributions",{"tool":63,"command":64},"pnpm","pnpm dlx skills add microsoft\u002Fvscode --skill author-contributions","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvscode\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fauthor-contributions\u002FSKILL.md",true,[],[69,94,116,130,143,159],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":39},"01M70H0ANBKZAVEP1NVV4K28M3","sweeper-query","Answer natural-language questions about the VS Code Sweeper's published issue index (index-\u003Cname>.json for microsoft\u002Fvscode and the enrolled family repos) — which issues are agent-ready to implement or plan, what the sweeper proposed for an assignee or area, whether the sweeper knows a report as a duplicate, the highest-value open bugs in a lane — and, for one issue, the review's full record (evidence with file citations, fix brief, proposed comment). Use ONLY when the request explicitly names the sweeper — \"sweeper\", \"vscodesweeper\", \"sweeper-query\", a sweeper verdict, record, brief or index, an agent-ready issue — or asks what \"the sweeper\" found, proposed or knows. Do NOT use for general questions about issues, duplicates, priorities or ranking that do not mention the sweeper. Read-only; discovery only.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvscode\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fsweeper-query\u002FSKILL.md",[],[76,77,78,79,80,22,81,82,83,84,85,86,87,88,89,90,91,92,93,36],"sweeper query","query","sweeper","review","fix","request","which","natural-language","ranking","duplicates","ready","only","read","plan","open","Citations","brief","issues",{"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":100,"publishedAt":39},"01M699DRJS4YJCV600Q72SVVWE","update-skills","Create or update repository skills and instructions when major learnings are discovered during a session. Use when the user says \"learn!\", when a significant pattern or pitfall is identified, or when reusable domain knowledge should be captured for future sessions.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvscode\u002Fblob\u002Fmain\u002Fsrc\u002Fvs\u002Fsessions\u002Fskills\u002Fupdate-skills\u002FSKILL.md",[],[101,102,103,104,105,106,107,21,108,109,110,111,112,113,114,115,22],"update","update skills","for","pattern","domain","learnings","reusable","session","user","instructions","knowledge","repository","learn","create","sessions",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":39},"01M699DPWHZ72B66P82EW31RNE","update-pr","Update the pull request for the current session. Use when the user wants to push new changes to an existing PR.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvscode\u002Fblob\u002Fmain\u002Fsrc\u002Fvs\u002Fsessions\u002Fskills\u002Fupdate-pr\u002FSKILL.md",[],[101,123,124,22,81,125,103,21,108,109,126,127,128,129],"pr","update pr","Existing","push","pull","pull request","changes",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":39},"01M699DJMR6CE1MH5XCJZ0GFQ0","sync","Sync the current session branch with its upstream branch, or publish the current session branch to a remote. Use when the user asks to sync a branch, pull latest changes, rebase onto upstream, push current branch, publish branch, or set upstream.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvscode\u002Fblob\u002Fmain\u002Fsrc\u002Fvs\u002Fsessions\u002Fskills\u002Fsync\u002FSKILL.md",[],[132,137,138,126,127,139,22,129,140,141,142,28,21,108,109,31],"SET","publish","rebase","latest","with","remote",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":39},"01M699DGXHX6A2A72X57R6GGHJ","sync-upstream","Update a stale session branch by rebasing onto the latest origin. Use when the upstream has moved significantly and the session needs to catch up, resolving conflicts by preserving upstream changes and adapting session work to fit.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvscode\u002Fblob\u002Fmain\u002Fsrc\u002Fvs\u002Fsessions\u002Fskills\u002Fsync-upstream\u002FSKILL.md",[],[28,132,150,151,22,152,153,129,140,154,155,156,157,21,108,31,158,101],"sync upstream","fit","catch","catch up","origin","conflicts","stale","up","work",{"skillNo":160,"name":38,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":39},"01M699DEXYFWDGW0BAXJ5QQ377","Merge changes from the topic branch to the merge base branch. Use when the user wants to merge their session's work back to the base branch.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvscode\u002Fblob\u002Fmain\u002Fsrc\u002Fvs\u002Fsessions\u002Fskills\u002Fmerge\u002FSKILL.md",[],[38,108,21,158,31,109,22,165,166,129],"back","base"]