[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F5WQJ5KANAVDPHMVND0E9E":3,"skill-same:01M7F5WQJ5KANAVDPHMVND0E9E":74},{"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":42,"commitSha":43,"skillDirectory":44,"forksCount":14,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M7F5WQJ5KANAVDPHMVND0E9E","large-changeset-review",null,"Review large mixed-scope diffs before commit.","chaorenex1\u002Fhermes-home-content","chaorenex1","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F23194925?v=4","01M7F5NA1D1D02R2MEMYQN2NZT","chan chan","01M7F5NA20KTHMTY2015CYM1TZ",0,"MIT","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002F.archive\u002Flarge-changeset-review\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\r\nname: large-changeset-review\r\ndescription: \"Review large mixed-scope diffs before commit.\"\r\nversion: 1.1.0\r\nauthor: Hermes Agent\r\nlicense: MIT\r\nplatforms: [linux, macos, windows]\r\nmetadata:\r\n  hermes:\r\n    tags: [code-review, security, verification, pre-commit, large-diff, artifacts]\r\n    related_skills: [requesting-code-review, analyzing-codebases]\r\n---\r\n\r\n# Large Changeset Review\r\n\r\nPre-commit review for working trees that contain weeks of accumulated work:\r\nfeature branches, merge artifacts, generated files, platform-specific lock\r\nchurn, and mixed executable + test + documentation changes.\r\n\r\nThe standard `requesting-code-review` pipeline assumes a small, coherent diff.\r\nWhen `git status --porcelain` shows 50+ entries, that pipeline under-reports\r\nuntracked artifacts, lock-file drift, and security-boundary shifts hidden in\r\nlarge executable diffs.\r\n\r\n## When to Use\r\n\r\n- `git status --porcelain` shows 50+ modified\u002Funtracked entries\r\n- The diff exceeds ~4,000 lines or touches multiple architectural layers\r\n- The working tree has been accumulating changes for days\u002Fweeks\r\n- The user asks for a \"review before commit\" on a large mixed-scope changeset\r\n\r\n## The Core Problem\r\n\r\nLarge diffs fail review in three ways that small diffs do not:\r\n\r\n1. **Untracked artifacts** that should never be committed (`.orig` backups,\r\n   runtime caches, literal `~\u002F` directories created by tools that didn't\r\n   expand `~`).\r\n2. **Lock-file platform drift** — `package-lock.json` regenerated on Windows\r\n   drops optional platform-specific native deps (`@esbuild\u002Fwin32-*`, etc.)\r\n   and breaks installs on other platforms.\r\n3. **Security boundary shifts** hidden in large executable diffs — e.g. an\r\n   approval-bypass refactor that looks like a cleanup but changes which code\r\n   paths honor `approvals.mode: off`.\r\n\r\n## Grouped Inspection Protocol\r\n\r\nDo NOT read every file. Group by risk class and inspect per class:\r\n\r\n| Risk class | What to inspect | Example from real session |\r\n|---|---|---|\r\n| **Merge \u002F backup artifacts** | `*.orig`, `*.rej`, `*.bak`, `*.tmp`, `Python\u002F`, literal `~\u002F` dirs | `hermes_cli\u002Fweb_server.py.orig` (545KB), `Python\u002F` (34MB install cache), `~\u002F` (literal tilde dir with mem0 UUID) |\r\n| **Lock \u002F manifest files** | `package-lock.json`, `poetry.lock`, `Cargo.lock` — check for platform-dep removal | `package-lock.json` dropping `@esbuild\u002F*` optional deps |\r\n| **Security-sensitive runtime** | `tools\u002Fapproval.py`, `tools\u002Fregistry.py`, `agent\u002Fplugin_agent.py`, `agent\u002Ftool_executor.py` | Approval-gate refactor changing `approvals.mode: off` handling |\r\n| **New executable modules** | Untracked `.py` \u002F `.ts` >200 lines | `hermes_cli\u002Fultrawork_kanban.py` (5356 lines) |\r\n| **Test deletions** | Files with net-negative line changes in `tests\u002F` | Removed provider-review tests — verify they test removed code, not weakened coverage |\r\n| **Docs \u002F config** | `*.md`, `sidebars.ts`, `*.yaml` | Additive, usually safe |\r\n\r\n## Verification Shortcuts\r\n\r\n```bash\r\n# 1. Syntax-check all modified Python files in one pass\r\ngit diff --name-only -- '*.py' | xargs python -m py_compile\r\n\r\n# 2. Secret scan on added lines only\r\ngit diff | grep '^+' | grep -iE '(api[_-]?key|secret|password|token)\\s*=\\s*[\"\\'][^\"\\']{8,}[\"\\']'\r\n\r\n# 3. Find risky patterns in the diff\r\ngit diff | grep '^+' | grep -E 'shell\\s*=\\s*True|os\\.system|eval\\(|exec\\(|pickle\\.loads'\r\n\r\n# 4. Find test deletions (potential coverage loss)\r\ngit diff --stat -- 'tests\u002F*' | grep -E '\\|\\s+[0-9]+\\s+-+'\r\ngit diff -- 'tests\u002F*' | grep '^-.*def test_'\r\n```\r\n\r\n### Final Index Verification\r\n\r\nUnstaged checks are not sufficient when new files exist: `git diff` and\r\n`git diff --check` ignore untracked files. After grouped review and artifact\r\ncleanup, stage the intended tree and verify the exact commit candidate:\r\n\r\n```bash\r\ngit add -A\r\ngit diff --cached --check\r\ngit diff --cached --name-status\r\ngit diff --cached --stat\r\n```\r\n\r\nIf the cached whitespace check reports nearly every nonblank line in a newly\r\nadded file, inspect its byte-level line endings. Mixed CRLF\u002FLF files can appear\r\nas thousands of trailing-whitespace errors only after staging. Normalize only\r\nthe affected text files to the repository convention, re-stage them, and rerun\r\nthe cached check. Do not run blanket line-ending conversion across the tree.\r\n\r\nRun one final `git status --porcelain` after tests, builds, package installs,\r\nand reviewer tools. Verification itself can create caches, installer logs, or\r\nliteral path directories after the initial artifact sweep.\r\n\r\n## Pitfalls\r\n\r\n- **Do not skip untracked files.** `git diff` ignores them. Run\r\n  `git status --porcelain | grep '^??'` and inspect anything that is not\r\n  clearly source code.\r\n- **Do not call an unstaged whitespace check final.** `git diff --check` also\r\n  ignores untracked files. The commit candidate is clean only after\r\n  `git diff --cached --check` passes.\r\n- **Re-scan after verification.** Tests, package installs, and reviewer probes\r\n  can create new repo-root caches\u002Flogs after the first inventory.\r\n- **Preserve ambiguous backups before removal.** Move a pre-existing `.orig`\r\n  or similar backup outside the repository when its contents may be unique;\r\n  clean the commit without destroying the user's recovery copy.\r\n- **Use the project's canonical test runner.** If a broad run has known\r\n  baseline\u002Fplatform failures, isolate changed-file tests, rerun concrete\r\n  failing affected tests after each fix, and record unrelated baseline\r\n  failures separately. An ad hoc runner is not stronger evidence.\r\n- **Review the final state after fixes.** Give the independent reviewer the\r\n  final staged diff plus canonical test evidence. Constrain a focused retry to\r\n  code review when tests are already authoritative; do not let a noncanonical\r\n  rerun replace valid evidence.\r\n- **`.orig` files are never intentional commits.** They are editor merge\r\n  backups. Treat as blocking.\r\n- **Literal `~\u002F` or `Python\u002F` directories in repo root** indicate a tool failed\r\n  to expand a path. Treat as blocking and check whether the tool's config\r\n  leaked a user UUID or absolute home path.\r\n- **package-lock.json shrinking on Windows** is almost always npm dropping\r\n  optional platform deps. Compare against `git show HEAD:package-lock.json |\r\n  grep -c '@esbuild'` to confirm.\r\n- **Test deletions are acceptable only when they test removed functionality.**\r\n  Cross-check the removed test names against the feature diff.\r\n- **Approval \u002F auth \u002F gate refactors** deserve line-by-line reading of the\r\n  boolean expressions. A change from `A or B or C` to `helper()` is only safe\r\n  when `helper()` is proven to cover `C`.\r\n\r\n## Final Commit Gate\r\n\r\nCommit only when all four conditions hold:\r\n\r\n1. The exact staged tree has passed artifact, secret, and whitespace checks.\r\n2. Changed behavior has canonical test evidence; unrelated baseline failures\r\n   are explicitly separated from regressions.\r\n3. An independent reviewer has reviewed the final staged state, not an older\r\n   pre-fix diff.\r\n4. After commit, `git show -1 --shortstat`, `git diff HEAD^ HEAD --check`, and\r\n   `git status --short --branch` verify the recorded artifact and clean\r\n   worktree. Do not push unless the user asked for a remote write.\r\n\r\n## Verdict Template\r\n\r\nFor large changesets, return a structured verdict:\r\n\r\n```json\r\n{\r\n  \"passed\": false,\r\n  \"blocking_findings\": [\r\n    {\"path\": \"hermes_cli\u002Fweb_server.py.orig\", \"line\": 1, \"rationale\": \"545KB merge backup; should not be committed\"},\r\n    {\"path\": \"package-lock.json\", \"line\": null, \"rationale\": \"416 lines removed; drops platform-specific esbuild deps, breaks non-Windows installs\"}\r\n  ],\r\n  \"nonblocking_findings\": [\r\n    {\"path\": \"agent\u002Fplugin_agent.py\", \"line\": 36, \"rationale\": \"Empty toolsets=[] now allowed; verify AIAgent handles None as 'all default toolsets'\"}\r\n  ],\r\n  \"recommended_targeted_tests\": [\r\n    \"python -m pytest tests\u002Fagent\u002Ftest_plugin_agent.py -v\",\r\n    \"python -m pytest tests\u002Fhermes_cli\u002Ftest_kanban_db.py -v\"\r\n  ]\r\n}\r\n```\r\n\r\n## Reference\r\n\r\n- `references\u002Fsession-example.md` — worked example from a real 65-file\r\n  Hermes Agent pre-commit review, including exact commands and findings.\r\n- `references\u002Fjson-only-post-fix-review.md` — pattern for when the user asks\r\n  for a focused post-fix review with strict JSON-only output (e.g. \"Return\r\n  ONLY valid JSON\"). Covers staged-diff scoping, `git show :\u003Cfile>` reads to\r\n  verify removals and remaining plumbing, and the verdict template.\r\n","# Large Changeset Review\r\n\r\nPre-commit review for working trees that contain weeks of accumulated work:\r\nfeature branches, merge artifacts, generated files, platform-specific lock\r\nchurn, and mixed executable + test + documentation changes.\r\n\r\nThe standard `requesting-code-review` pipeline assumes a small, coherent diff.\r\nWhen `git status --porcelain` shows 50+ entries, that pipeline under-reports\r\nuntracked artifacts, lock-file drift, and security-boundary shifts hidden in\r\nlarge executable diffs.\r\n\r\n## When to Use\r\n\r\n- `git status --porcelain` shows 50+ modified\u002Funtracked entries\r\n- The diff exceeds ~4,000 lines or touches multiple architectural layers\r\n- The working tree has been accumulating changes for days\u002Fweeks\r\n- The user asks for a \"review before commit\" on a large mixed-scope changeset\r\n\r\n## The Core Problem\r\n\r\nLarge diffs fail review in three ways that small diffs do not:\r\n\r\n1. **Untracked artifacts** that should never be committed (`.orig` backups,\r\n   runtime caches, literal `~\u002F` directories created by tools that didn't\r\n   expand `~`).\r\n2. **Lock-file platform drift** — `package-lock.json` regenerated on Windows\r\n   drops optional platform-specific native deps (`@esbuild\u002Fwin32-*`, etc.)\r\n   and breaks installs on other platforms.\r\n3. **Security boundary shifts** hidden in large executable diffs — e.g. an\r\n   approval-bypass refactor that looks like a cleanup but changes which code\r\n   paths honor `approvals.mode: off`.\r\n\r\n## Grouped Inspection Protocol\r\n\r\nDo NOT read every file. Group by risk class and inspect per class:\r\n\r\n| Risk class | What to inspect | Example from real session |\r\n|---|---|---|\r\n| **Merge \u002F backup artifacts** | `*.orig`, `*.rej`, `*.bak`, `*.tmp`, `Python\u002F`, literal `~\u002F` dirs | `hermes_cli\u002Fweb_server.py.orig` (545KB), `Python\u002F` (34MB install cache), `~\u002F` (literal tilde dir with mem0 UUID) |\r\n| **Lock \u002F manifest files** | `package-lock.json`, `poetry.lock`, `Cargo.lock` — check for platform-dep removal | `package-lock.json` dropping `@esbuild\u002F*` optional deps |\r\n| **Security-sensitive runtime** | `tools\u002Fapproval.py`, `tools\u002Fregistry.py`, `agent\u002Fplugin_agent.py`, `agent\u002Ftool_executor.py` | Approval-gate refactor changing `approvals.mode: off` handling |\r\n| **New executable modules** | Untracked `.py` \u002F `.ts` >200 lines | `hermes_cli\u002Fultrawork_kanban.py` (5356 lines) |\r\n| **Test deletions** | Files with net-negative line changes in `tests\u002F` | Removed provider-review tests — verify they test removed code, not weakened coverage |\r\n| **Docs \u002F config** | `*.md`, `sidebars.ts`, `*.yaml` | Additive, usually safe |\r\n\r\n## Verification Shortcuts\r\n\r\n```bash\r\n# 1. Syntax-check all modified Python files in one pass\r\ngit diff --name-only -- '*.py' | xargs python -m py_compile\r\n\r\n# 2. Secret scan on added lines only\r\ngit diff | grep '^+' | grep -iE '(api[_-]?key|secret|password|token)\\s*=\\s*[\"\\'][^\"\\']{8,}[\"\\']'\r\n\r\n# 3. Find risky patterns in the diff\r\ngit diff | grep '^+' | grep -E 'shell\\s*=\\s*True|os\\.system|eval\\(|exec\\(|pickle\\.loads'\r\n\r\n# 4. Find test deletions (potential coverage loss)\r\ngit diff --stat -- 'tests\u002F*' | grep -E '\\|\\s+[0-9]+\\s+-+'\r\ngit diff -- 'tests\u002F*' | grep '^-.*def test_'\r\n```\r\n\r\n### Final Index Verification\r\n\r\nUnstaged checks are not sufficient when new files exist: `git diff` and\r\n`git diff --check` ignore untracked files. After grouped review and artifact\r\ncleanup, stage the intended tree and verify the exact commit candidate:\r\n\r\n```bash\r\ngit add -A\r\ngit diff --cached --check\r\ngit diff --cached --name-status\r\ngit diff --cached --stat\r\n```\r\n\r\nIf the cached whitespace check reports nearly every nonblank line in a newly\r\nadded file, inspect its byte-level line endings. Mixed CRLF\u002FLF files can appear\r\nas thousands of trailing-whitespace errors only after staging. Normalize only\r\nthe affected text files to the repository convention, re-stage them, and rerun\r\nthe cached check. Do not run blanket line-ending conversion across the tree.\r\n\r\nRun one final `git status --porcelain` after tests, builds, package installs,\r\nand reviewer tools. Verification itself can create caches, installer logs, or\r\nliteral path directories after the initial artifact sweep.\r\n\r\n## Pitfalls\r\n\r\n- **Do not skip untracked files.** `git diff` ignores them. Run\r\n  `git status --porcelain | grep '^??'` and inspect anything that is not\r\n  clearly source code.\r\n- **Do not call an unstaged whitespace check final.** `git diff --check` also\r\n  ignores untracked files. The commit candidate is clean only after\r\n  `git diff --cached --check` passes.\r\n- **Re-scan after verification.** Tests, package installs, and reviewer probes\r\n  can create new repo-root caches\u002Flogs after the first inventory.\r\n- **Preserve ambiguous backups before removal.** Move a pre-existing `.orig`\r\n  or similar backup outside the repository when its contents may be unique;\r\n  clean the commit without destroying the user's recovery copy.\r\n- **Use the project's canonical test runner.** If a broad run has known\r\n  baseline\u002Fplatform failures, isolate changed-file tests, rerun concrete\r\n  failing affected tests after each fix, and record unrelated baseline\r\n  failures separately. An ad hoc runner is not stronger evidence.\r\n- **Review the final state after fixes.** Give the independent reviewer the\r\n  final staged diff plus canonical test evidence. Constrain a focused retry to\r\n  code review when tests are already authoritative; do not let a noncanonical\r\n  rerun replace valid evidence.\r\n- **`.orig` files are never intentional commits.** They are editor merge\r\n  backups. Treat as blocking.\r\n- **Literal `~\u002F` or `Python\u002F` directories in repo root** indicate a tool failed\r\n  to expand a path. Treat as blocking and check whether the tool's config\r\n  leaked a user UUID or absolute home path.\r\n- **package-lock.json shrinking on Windows** is almost always npm dropping\r\n  optional platform deps. Compare against `git show HEAD:package-lock.json |\r\n  grep -c '@esbuild'` to confirm.\r\n- **Test deletions are acceptable only when they test removed functionality.**\r\n  Cross-check the removed test names against the feature diff.\r\n- **Approval \u002F auth \u002F gate refactors** deserve line-by-line reading of the\r\n  boolean expressions. A change from `A or B or C` to `helper()` is only safe\r\n  when `helper()` is proven to cover `C`.\r\n\r\n## Final Commit Gate\r\n\r\nCommit only when all four conditions hold:\r\n\r\n1. The exact staged tree has passed artifact, secret, and whitespace checks.\r\n2. Changed behavior has canonical test evidence; unrelated baseline failures\r\n   are explicitly separated from regressions.\r\n3. An independent reviewer has reviewed the final staged state, not an older\r\n   pre-fix diff.\r\n4. After commit, `git show -1 --shortstat`, `git diff HEAD^ HEAD --check`, and\r\n   `git status --short --branch` verify the recorded artifact and clean\r\n   worktree. Do not push unless the user asked for a remote write.\r\n\r\n## Verdict Template\r\n\r\nFor large changesets, return a structured verdict:\r\n\r\n```json\r\n{\r\n  \"passed\": false,\r\n  \"blocking_findings\": [\r\n    {\"path\": \"hermes_cli\u002Fweb_server.py.orig\", \"line\": 1, \"rationale\": \"545KB merge backup; should not be committed\"},\r\n    {\"path\": \"package-lock.json\", \"line\": null, \"rationale\": \"416 lines removed; drops platform-specific esbuild deps, breaks non-Windows installs\"}\r\n  ],\r\n  \"nonblocking_findings\": [\r\n    {\"path\": \"agent\u002Fplugin_agent.py\", \"line\": 36, \"rationale\": \"Empty toolsets=[] now allowed; verify AIAgent handles None as 'all default toolsets'\"}\r\n  ],\r\n  \"recommended_targeted_tests\": [\r\n    \"python -m pytest tests\u002Fagent\u002Ftest_plugin_agent.py -v\",\r\n    \"python -m pytest tests\u002Fhermes_cli\u002Ftest_kanban_db.py -v\"\r\n  ]\r\n}\r\n```\r\n\r\n## Reference\r\n\r\n- `references\u002Fsession-example.md` — worked example from a real 65-file\r\n  Hermes Agent pre-commit review, including exact commands and findings.\r\n- `references\u002Fjson-only-post-fix-review.md` — pattern for when the user asks\r\n  for a focused post-fix review with strict JSON-only output (e.g. \"Return\r\n  ONLY valid JSON\"). Covers staged-diff scoping, `git show :\u003Cfile>` reads to\r\n  verify removals and remaining plumbing, and the verdict template.\r\n",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"platforms":38,"description":7},"Hermes Agent","1.1.0",{"hermes":27},{"tags":28,"related_skills":35},[29,30,31,32,33,34],"code-review","security","verification","pre-commit","large-diff","artifacts",[36,37],"requesting-code-review","analyzing-codebases",[39,40,41],"linux","macos","windows","main","a3f3199bb87ec3c91248f68a39d88527e1847ae9","skills\u002F.archive\u002Flarge-changeset-review","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content","https:\u002F\u002Fgithub.com\u002Fchaorenex1","https:\u002F\u002Fblog.aduib.com","A programmer whose only hobby in life is coding","2026-10-20 00:34:32",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add chaorenex1\u002Fhermes-home-content --skill large-changeset-review",{"tool":56,"command":57},"bunx","bunx skills add chaorenex1\u002Fhermes-home-content --skill large-changeset-review",{"tool":59,"command":60},"pnpm","pnpm dlx skills add chaorenex1\u002Fhermes-home-content --skill large-changeset-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002F.archive\u002Flarge-changeset-review\u002FSKILL.md",true,[64,70],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fjson-only-post-fix-review.md","REFERENCE","参考文档",3107,"https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002F.archive\u002Flarge-changeset-review\u002Freferences\u002Fjson-only-post-fix-review.md",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fsession-example.md",5572,"https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002F.archive\u002Flarge-changeset-review\u002Freferences\u002Fsession-example.md",[75,82,89,96,103,110],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7F8GF32YD5MBQW2TGSRH1YP","web-retrieval-resilience","Web tools fail or search rules break: repair or fall back.","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fweb\u002Fweb-retrieval-resilience\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7F8FP46QESQMCZ1KBT3TW3R","blocked-page-recovery","Use when a fetch fails: 403\u002F429, paywall, WAF, bot wall.","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fweb\u002Fblocked-page-recovery\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7F8ER6VXHBNVRQBZS7X08SE","verification-loop","Run a six-phase verification of a Claude Code session's work — build, type check, lint, tests with coverage, security grep, and diff review — then produce a PASS\u002FFAIL verification report. Use when verifying work after completing a feature or refactor, before creating a PR, or when quality gates must pass.","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M7F8E4BQJ38KVQVM3MT20PYV","unreal-world-builder","开放世界与环境专家——精通 UE5 World Partition、Landscape、程序化植被、HLOD 和大规模关卡流式加载，打造无缝开放世界体验","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Funreal-engine\u002Funreal-world-builder\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"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":19},"01M7F8D747SQW2FTP7GBSX38BR","unreal-technical-artist","Unreal Engine 视觉管线专家——精通材质编辑器、Niagara 特效、程序化内容生成和 UE5 项目的美术到引擎管线","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Funreal-engine\u002Funreal-technical-artist\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":19},"01M7F8CKHYJVZVBTN0321J88T2","unreal-systems-engineer","性能与混合架构专家——精通 C++\u002FBlueprint 边界、Nanite 几何体、Lumen GI 和 Gameplay Ability System，面向 AAA 级 Unreal Engine 项目","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Funreal-engine\u002Funreal-systems-engineer\u002FSKILL.md",[],[]]