[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F4FFPT2AAQCF2XDGRCHKGT":3,"skill-same:01M7F4FFPT2AAQCF2XDGRCHKGT":86},{"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":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":6,"ownerHtmlUrl":40,"ownerBlogUrl":6,"ownerDescription":41,"updatedAt":42,"install":43,"resources":55},"01M7F4FFPT2AAQCF2XDGRCHKGT","second-opinion",null,"Load for a cross-model review, challenge, audit, or quick consult.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsecond-opinion\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: second-opinion\ndescription: \"Load for a cross-model review, challenge, audit, or quick consult.\"\nsummary: \"Cross-model second opinion: review, challenge, audit, and consult through an external AI CLI (Claude and Codex).\"\nlicense: MIT\nuser-invocable: true\nargument-hint: \"review [scope] | challenge [description] | audit [path] | quick [question]\"\nmetadata:\n  author: vanillagreen\n  source: kendex\n  repository: \"https:\u002F\u002Fgithub.com\u002Fvanillagreencom\u002Fkendex\"\n  bugs: \"https:\u002F\u002Fgithub.com\u002Fvanillagreencom\u002Fkendex\u002Fissues\"\n  version: \"1.0.0\"\ntags: [review]\n---\n\n# Second Opinion\n\nCross-model second opinion via external AI CLI. Every mode walks the `SECOND_OPINION_MODELS` roster in priority order and takes the first target that is available and runs a different model: Codex from a Claude Code session, Claude from a Codex session; when nothing eligible remains the run refuses and says why. Full contract: `second-opinion --help`.\n\n```bash\n.agents\u002Fskills\u002Fsecond-opinion\u002Fscripts\u002Fsecond-opinion \u003Cmode> [options]\n```\n\n## Workflows\n\n| Command | Workflow | Output |\n|---------|----------|--------|\n| `review [scope]` | [workflows\u002Freview.md](workflows\u002Freview.md) | Review finding JSON |\n| `challenge [description]` | [workflows\u002Fchallenge.md](workflows\u002Fchallenge.md) | Structured critique (text) |\n| `audit [path]` | [workflows\u002Faudit.md](workflows\u002Faudit.md) | Review finding JSON |\n| `quick [question]` | [workflows\u002Fquick.md](workflows\u002Fquick.md) | Text response |\n| `detect` | (built-in) | Target name(s) a review would run |\n\n## Execution Rules\n\n- Execute all workflow sections in order. The workflow decides what to skip via \"**Skip if**\" conditions. Never skip based on your own scope assessment.\n- `\u003Coutput_format>` tags are literal templates: fill `[PLACEHOLDERS]`, omit empty lines, add nothing else, do not paraphrase.\n- **Pass `--target`** when the user explicitly requests a specific model\u002FCLI (e.g., \"use Claude\", \"ask Codex\"). Otherwise omit it. The script selects from the roster and the current session's model. A forced target that runs this session's model is refused; report the refusal, do not work around it.\n- **Do not pass `--timeout`** unless the user explicitly asks for a different value for this specific call. The script reads the default from project config.\n- **Always pass `--cwd`** with the absolute project root path. Never use `--cwd .`.\n- Pass `--foreground` when the call can outlast the harness foreground cap. This detaches the run and prints its artifact, deadline, and wait command.\n- Execute the exact printed wait command and follow its exit handling in `second-opinion --help` until terminal.\n- For `quick` mode, you can pass the question inline: `.agents\u002Fskills\u002Fsecond-opinion\u002Fscripts\u002Fsecond-opinion quick \"your question here\" --cwd \u002Fpath --foreground`.\n\n## Session identity\n\nCross-model is enforced in every mode: a run with no eligible target exits 1 naming every candidate and its reason, writing nothing and invoking nothing. In a multi-model front end (Pi, OpenCode, Cursor) or an undetected harness, export `SECOND_OPINION_CURRENT_MODEL` in that session's own environment (`none` when there is no session model), never in a project settings file. Identity resolution, normalization, and the refusal rules: `second-opinion --help`.\n\n## Multi-lane review\n\n`SECOND_OPINION_COUNT` of 2 or more makes `review` run up to that many distinct eligible models in parallel on one pinned scope and write a single union artifact. Lane resolution, merge rules, artifact placement and permissions, scratch durability, and the failure taxonomy: [references\u002Fmulti-lane.md](references\u002Fmulti-lane.md).\n\n## Configuration\n\nSet non-sensitive defaults in `kendex.settings.toml` under `[env]`; `.env.local` wins over it, and a `.env` file is never read. `SECOND_OPINION_FOREGROUND_CAP` is session-only; a project-file foreground-cap declaration is refused, and shipped workflows pass `--foreground` directly. This skill marks no key `# required`, so an install writes nothing into `kendex.settings.toml`; assign a key there only to change a default the scripts already read (`SECOND_OPINION_TARGET` has none). Keys, defaults, and the built-in `claude`\u002F`codex` commands: `second-opinion --help`.\n\n## Error Handling\n\nOn script failure, stderr carries a JSON error object (`{\"error\": \"description\", \"target\": \"codex\"}`) or a plain `Error:` line for pre-flight configuration errors; exit codes, preserved-response paths, and the output-clearing\u002Fownership rules are in `second-opinion --help`. Report the stated reason. An ineligible-target refusal is fixed by installing the CLI or adjusting `SECOND_OPINION_\u003CNAME>_CMD`, `SECOND_OPINION_MODELS`, or `SECOND_OPINION_CURRENT_MODEL`, never by forcing the same model. For a timeout, suggest a larger `--timeout` or a narrower `--range`.\n\nIf the script fails during the orch `review-pr` or `submit-pr` (local pre-PR review) workflows, **continue**. External review is advisory.\n","# Second Opinion\n\nCross-model second opinion via external AI CLI. Every mode walks the `SECOND_OPINION_MODELS` roster in priority order and takes the first target that is available and runs a different model: Codex from a Claude Code session, Claude from a Codex session; when nothing eligible remains the run refuses and says why. Full contract: `second-opinion --help`.\n\n```bash\n.agents\u002Fskills\u002Fsecond-opinion\u002Fscripts\u002Fsecond-opinion \u003Cmode> [options]\n```\n\n## Workflows\n\n| Command | Workflow | Output |\n|---------|----------|--------|\n| `review [scope]` | [workflows\u002Freview.md](workflows\u002Freview.md) | Review finding JSON |\n| `challenge [description]` | [workflows\u002Fchallenge.md](workflows\u002Fchallenge.md) | Structured critique (text) |\n| `audit [path]` | [workflows\u002Faudit.md](workflows\u002Faudit.md) | Review finding JSON |\n| `quick [question]` | [workflows\u002Fquick.md](workflows\u002Fquick.md) | Text response |\n| `detect` | (built-in) | Target name(s) a review would run |\n\n## Execution Rules\n\n- Execute all workflow sections in order. The workflow decides what to skip via \"**Skip if**\" conditions. Never skip based on your own scope assessment.\n- `\u003Coutput_format>` tags are literal templates: fill `[PLACEHOLDERS]`, omit empty lines, add nothing else, do not paraphrase.\n- **Pass `--target`** when the user explicitly requests a specific model\u002FCLI (e.g., \"use Claude\", \"ask Codex\"). Otherwise omit it. The script selects from the roster and the current session's model. A forced target that runs this session's model is refused; report the refusal, do not work around it.\n- **Do not pass `--timeout`** unless the user explicitly asks for a different value for this specific call. The script reads the default from project config.\n- **Always pass `--cwd`** with the absolute project root path. Never use `--cwd .`.\n- Pass `--foreground` when the call can outlast the harness foreground cap. This detaches the run and prints its artifact, deadline, and wait command.\n- Execute the exact printed wait command and follow its exit handling in `second-opinion --help` until terminal.\n- For `quick` mode, you can pass the question inline: `.agents\u002Fskills\u002Fsecond-opinion\u002Fscripts\u002Fsecond-opinion quick \"your question here\" --cwd \u002Fpath --foreground`.\n\n## Session identity\n\nCross-model is enforced in every mode: a run with no eligible target exits 1 naming every candidate and its reason, writing nothing and invoking nothing. In a multi-model front end (Pi, OpenCode, Cursor) or an undetected harness, export `SECOND_OPINION_CURRENT_MODEL` in that session's own environment (`none` when there is no session model), never in a project settings file. Identity resolution, normalization, and the refusal rules: `second-opinion --help`.\n\n## Multi-lane review\n\n`SECOND_OPINION_COUNT` of 2 or more makes `review` run up to that many distinct eligible models in parallel on one pinned scope and write a single union artifact. Lane resolution, merge rules, artifact placement and permissions, scratch durability, and the failure taxonomy: [references\u002Fmulti-lane.md](references\u002Fmulti-lane.md).\n\n## Configuration\n\nSet non-sensitive defaults in `kendex.settings.toml` under `[env]`; `.env.local` wins over it, and a `.env` file is never read. `SECOND_OPINION_FOREGROUND_CAP` is session-only; a project-file foreground-cap declaration is refused, and shipped workflows pass `--foreground` directly. This skill marks no key `# required`, so an install writes nothing into `kendex.settings.toml`; assign a key there only to change a default the scripts already read (`SECOND_OPINION_TARGET` has none). Keys, defaults, and the built-in `claude`\u002F`codex` commands: `second-opinion --help`.\n\n## Error Handling\n\nOn script failure, stderr carries a JSON error object (`{\"error\": \"description\", \"target\": \"codex\"}`) or a plain `Error:` line for pre-flight configuration errors; exit codes, preserved-response paths, and the output-clearing\u002Fownership rules are in `second-opinion --help`. Report the stated reason. An ineligible-target refusal is fixed by installing the CLI or adjusting `SECOND_OPINION_\u003CNAME>_CMD`, `SECOND_OPINION_MODELS`, or `SECOND_OPINION_CURRENT_MODEL`, never by forcing the same model. For a timeout, suggest a larger `--timeout` or a narrower `--range`.\n\nIf the script fails during the orch `review-pr` or `submit-pr` (local pre-PR review) workflows, **continue**. External review is advisory.\n",{"name":5,"tags":24,"license":15,"summary":26,"metadata":27,"description":7,"argument-hint":33,"user-invocable":34},[25],"review","Cross-model second opinion: review, challenge, audit, and consult through an external AI CLI (Claude and Codex).",{"bugs":28,"author":29,"source":30,"version":31,"repository":32},"https:\u002F\u002Fgithub.com\u002Fvanillagreencom\u002Fkendex\u002Fissues","vanillagreen","kendex","1.0.0","https:\u002F\u002Fgithub.com\u002Fvanillagreencom\u002Fkendex","review [scope] | challenge [description] | audit [path] | quick [question]",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fsecond-opinion",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":34},[45,48,51],{"tool":46,"command":47},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill second-opinion",{"tool":49,"command":50},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill second-opinion",{"tool":52,"command":53},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill second-opinion","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsecond-opinion\u002FSKILL.md",[56,62,66,70,74,78,82],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"README.md","REFERENCE","参考文档",1661,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsecond-opinion\u002FREADME.md",{"path":63,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fmulti-lane.md",7514,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsecond-opinion\u002Freferences\u002Fmulti-lane.md",{"path":67,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":68,"sourceHtmlUrl":69},"schemas\u002Freview-finding-prompt.md",2559,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsecond-opinion\u002Fschemas\u002Freview-finding-prompt.md",{"path":71,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":72,"sourceHtmlUrl":73},"workflows\u002Faudit.md",2013,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsecond-opinion\u002Fworkflows\u002Faudit.md",{"path":75,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":76,"sourceHtmlUrl":77},"workflows\u002Fchallenge.md",2399,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsecond-opinion\u002Fworkflows\u002Fchallenge.md",{"path":79,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":80,"sourceHtmlUrl":81},"workflows\u002Fquick.md",1319,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsecond-opinion\u002Fworkflows\u002Fquick.md",{"path":83,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":84,"sourceHtmlUrl":85},"workflows\u002Freview.md",3606,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsecond-opinion\u002Fworkflows\u002Freview.md",[87,94,99,106,113,120],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":95,"name":89,"nameZh":6,"description":90,"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":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]