[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EV26THRFJP1Y5SR9B787PH":3,"skill-same:01M7EV26THRFJP1Y5SR9B787PH":92},{"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":30,"updatedAt":31,"install":32,"resources":45},"01M7EV26THRFJP1Y5SR9B787PH","variant-analysis",null,"Hunts for the other instances of a bug already found — the variants of one root cause across a codebase. Use immediately after a vulnerability, logic bug, or bad pattern turns up in a specific file and the question becomes where else it occurs, including the bare conversational form (\"are there others like this?\", \"is this the same bug?\"). Also for generalizing one known instance into a CodeQL or Semgrep query for its whole pattern family, and for triaging a set of look-alike candidates against a known root cause. Not for initial discovery with no bug in hand.","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\u002F04-安全渗透\u002Fvariant-analysis-trailofbits__skills\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: variant-analysis\ndescription: Hunts for the other instances of a bug already found — the variants of one root cause across a codebase. Use immediately after a vulnerability, logic bug, or bad pattern turns up in a specific file and the question becomes where else it occurs, including the bare conversational form (\"are there others like this?\", \"is this the same bug?\"). Also for generalizing one known instance into a CodeQL or Semgrep query for its whole pattern family, and for triaging a set of look-alike candidates against a known root cause. Not for initial discovery with no bug in hand.\n---\n\n# Variant Analysis\n\nFind the other instances of a bug you have already found. One root cause usually has several\nmanifestations, and they are rarely in the module where you found the first one.\n\n## When to Use\n\n- A vulnerability has been found and you need to search for similar instances\n- Building or refining CodeQL\u002FSemgrep queries for security patterns\n- Performing systematic code audits after an initial issue discovery\n- Analyzing how a single root cause manifests in different code paths\n\n## When NOT to Use\n\n- Initial vulnerability discovery — use audit-context-building or a domain-specific audit\n- General code review with no known pattern to search for\n- Writing fix recommendations — use issue-writer\n- Understanding unfamiliar code — use audit-context-building first\n\n## The Five Steps\n\nRead the reference for a step when you reach it.\n\n**1. Understand the original issue.** Extract the root cause — why the code is wrong, not\nwhat it does — and enumerate the directions a variant could hide in: related identifiers,\nother manifestations of the same mistake, data-type edge cases.\n→ [references\u002Froot-cause.md](references\u002Froot-cause.md)\n\n**2. Create an exact match.** Write a pattern matching ONLY the known instance and confirm\nit hits. A pattern that matches nothing means you have misunderstood the bug, and every\nsearch built on it is calibrated against the wrong code.\n\n**3–4. Generalize one element at a time.** Climb from the exact match toward the pattern\nfamily, running and reading all matches after each single change. Stop when more than half\nthe matches are noise.\n→ [references\u002Fsearching.md](references\u002Fsearching.md) — abstraction ladder, tool selection,\nfalse-positive filters\n\n**5. Triage.** Decide which candidates are real, and say so with a severity attached.\n→ [references\u002Ftriage.md](references\u002Ftriage.md)\n\n**Then write it up**, including the patterns that failed and a CI rule to prevent regression.\n→ [references\u002Freporting.md](references\u002Freporting.md)\n\n## Running it as a Workflow\n\nThis plugin ships `\u002Fvariant-analysis:variants`, which runs the five steps across parallel\nsubagents — one per expansion axis, looping until the sweep stops finding anything new.\nEach stage reads the reference above that matches its job.\n\nUse the workflow when the codebase is large or the root cause has many manifestations. Work\nthe steps directly when the search is narrow or you want a say in each generalization.\n\n## What Makes Hunts Fail\n\n1. **Narrow scope** — searching only the module the original bug was in\n2. **Pattern too specific** — searching one attribute and missing the family around it\n3. **One vulnerability class** — chasing a single manifestation of the root cause\n4. **Happy-path testing** — never trying the null, empty, and boundary cases\n5. **Generalizing too fast** — abstracting several elements at once, so noise cannot be\n   attributed to any one of them\n\nThe first three are covered in root-cause.md and searching.md, the fourth in triage.md.\n\n## Resources\n\n**CodeQL** (`resources\u002Fcodeql\u002F`): `python.ql`, `javascript.ql`, `java.ql`, `go.ql`, `cpp.ql`\n\n**Semgrep** (`resources\u002Fsemgrep\u002F`): `python.yaml`, `javascript.yaml`, `java.yaml`, `go.yaml`, `cpp.yaml`\n\n**Report**: `resources\u002Fvariant-report-template.md`\n","# Variant Analysis\n\nFind the other instances of a bug you have already found. One root cause usually has several\nmanifestations, and they are rarely in the module where you found the first one.\n\n## When to Use\n\n- A vulnerability has been found and you need to search for similar instances\n- Building or refining CodeQL\u002FSemgrep queries for security patterns\n- Performing systematic code audits after an initial issue discovery\n- Analyzing how a single root cause manifests in different code paths\n\n## When NOT to Use\n\n- Initial vulnerability discovery — use audit-context-building or a domain-specific audit\n- General code review with no known pattern to search for\n- Writing fix recommendations — use issue-writer\n- Understanding unfamiliar code — use audit-context-building first\n\n## The Five Steps\n\nRead the reference for a step when you reach it.\n\n**1. Understand the original issue.** Extract the root cause — why the code is wrong, not\nwhat it does — and enumerate the directions a variant could hide in: related identifiers,\nother manifestations of the same mistake, data-type edge cases.\n→ [references\u002Froot-cause.md](references\u002Froot-cause.md)\n\n**2. Create an exact match.** Write a pattern matching ONLY the known instance and confirm\nit hits. A pattern that matches nothing means you have misunderstood the bug, and every\nsearch built on it is calibrated against the wrong code.\n\n**3–4. Generalize one element at a time.** Climb from the exact match toward the pattern\nfamily, running and reading all matches after each single change. Stop when more than half\nthe matches are noise.\n→ [references\u002Fsearching.md](references\u002Fsearching.md) — abstraction ladder, tool selection,\nfalse-positive filters\n\n**5. Triage.** Decide which candidates are real, and say so with a severity attached.\n→ [references\u002Ftriage.md](references\u002Ftriage.md)\n\n**Then write it up**, including the patterns that failed and a CI rule to prevent regression.\n→ [references\u002Freporting.md](references\u002Freporting.md)\n\n## Running it as a Workflow\n\nThis plugin ships `\u002Fvariant-analysis:variants`, which runs the five steps across parallel\nsubagents — one per expansion axis, looping until the sweep stops finding anything new.\nEach stage reads the reference above that matches its job.\n\nUse the workflow when the codebase is large or the root cause has many manifestations. Work\nthe steps directly when the search is narrow or you want a say in each generalization.\n\n## What Makes Hunts Fail\n\n1. **Narrow scope** — searching only the module the original bug was in\n2. **Pattern too specific** — searching one attribute and missing the family around it\n3. **One vulnerability class** — chasing a single manifestation of the root cause\n4. **Happy-path testing** — never trying the null, empty, and boundary cases\n5. **Generalizing too fast** — abstracting several elements at once, so noise cannot be\n   attributed to any one of them\n\nThe first three are covered in root-cause.md and searching.md, the fourth in triage.md.\n\n## Resources\n\n**CodeQL** (`resources\u002Fcodeql\u002F`): `python.ql`, `javascript.ql`, `java.ql`, `go.ql`, `cpp.ql`\n\n**Semgrep** (`resources\u002Fsemgrep\u002F`): `python.yaml`, `javascript.yaml`, `java.yaml`, `go.yaml`, `cpp.yaml`\n\n**Report**: `resources\u002Fvariant-report-template.md`\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Fvariant-analysis-trailofbits__skills",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":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill variant-analysis",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill variant-analysis",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill variant-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvariant-analysis-trailofbits__skills\u002FSKILL.md",true,[46,52,56,60,64,68,72,76,80,84,88],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",247,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvariant-analysis-trailofbits__skills\u002Fagents\u002Fopenai.yaml",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Freporting.md",1547,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvariant-analysis-trailofbits__skills\u002Freferences\u002Freporting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Froot-cause.md",4209,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvariant-analysis-trailofbits__skills\u002Freferences\u002Froot-cause.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fsearching.md",4585,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvariant-analysis-trailofbits__skills\u002Freferences\u002Fsearching.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Ftriage.md",3587,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvariant-analysis-trailofbits__skills\u002Freferences\u002Ftriage.md",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"resources\u002Fsemgrep\u002Fcpp.yaml",2795,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvariant-analysis-trailofbits__skills\u002Fresources\u002Fsemgrep\u002Fcpp.yaml",{"path":73,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":74,"sourceHtmlUrl":75},"resources\u002Fsemgrep\u002Fgo.yaml",1797,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvariant-analysis-trailofbits__skills\u002Fresources\u002Fsemgrep\u002Fgo.yaml",{"path":77,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":78,"sourceHtmlUrl":79},"resources\u002Fsemgrep\u002Fjava.yaml",2011,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvariant-analysis-trailofbits__skills\u002Fresources\u002Fsemgrep\u002Fjava.yaml",{"path":81,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":82,"sourceHtmlUrl":83},"resources\u002Fsemgrep\u002Fjavascript.yaml",1715,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvariant-analysis-trailofbits__skills\u002Fresources\u002Fsemgrep\u002Fjavascript.yaml",{"path":85,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":86,"sourceHtmlUrl":87},"resources\u002Fsemgrep\u002Fpython.yaml",2002,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvariant-analysis-trailofbits__skills\u002Fresources\u002Fsemgrep\u002Fpython.yaml",{"path":89,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":90,"sourceHtmlUrl":91},"resources\u002Fvariant-report-template.md",1356,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvariant-analysis-trailofbits__skills\u002Fresources\u002Fvariant-report-template.md",[93,101,106,113,120,127],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":100},"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",[],[],"2026-11-16 10:05:34",{"skillNo":102,"name":95,"nameZh":6,"description":96,"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":100},"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":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":100},"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":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":100},"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":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":100},"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":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":100},"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",[],[]]