[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EBNMA65B1SDCSDSS0X3WSS":3,"skill-same:01M7EBNMA65B1SDCSDSS0X3WSS":56},{"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},"01M7EBNMA65B1SDCSDSS0X3WSS","audit-augmentation",null,"Augments Trailmark code graphs with external audit findings from SARIF static analysis results, weAudit annotation files, and version-gated Trailmark 0.4.x binary-analysis graph exports. Maps findings to graph nodes by file and line overlap, creates severity-based subgraphs, and enables cross-referencing findings with pre-analysis data (blast radius, taint, etc.). Use when projecting SARIF results onto a code graph, overlaying weAudit annotations, importing binary graph findings, cross-referencing Semgrep, CodeQL, or binary-analysis findings with call graph data, or visualizing audit findings in the context of code structure.","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\u002F03-逆向工程\u002Faudit-augmentation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: audit-augmentation\ndescription: >\n  Augments Trailmark code graphs with external audit findings from SARIF static\n  analysis results, weAudit annotation files, and version-gated Trailmark 0.4.x\n  binary-analysis graph exports. Maps findings to graph nodes by\n  file and line overlap, creates severity-based subgraphs, and enables\n  cross-referencing findings with pre-analysis data (blast radius, taint, etc.).\n  Use when projecting SARIF results onto a code graph, overlaying weAudit\n  annotations, importing binary graph findings, cross-referencing Semgrep,\n  CodeQL, or binary-analysis findings with call graph data, or visualizing audit\n  findings in the context of code structure.\n---\n\n# Audit Augmentation\n\nProjects findings from external tools (SARIF) and human auditors (weAudit)\nonto Trailmark code graphs as annotations and subgraphs. Trailmark 0.4.0+ can\nalso import an external binary-analysis graph JSON export via\n`engine.augment_binary()`.\n\n## When to Use\n\n- Importing Semgrep, CodeQL, or other SARIF-producing tool results into a graph\n- Importing weAudit audit annotations into a graph\n- Importing binary-analysis graph data into a source graph (Trailmark 0.4.0+)\n- Cross-referencing static analysis findings with blast radius or taint data\n- Querying which functions have high-severity findings\n- Visualizing audit coverage alongside code structure\n- Preparing one SARIF or weAudit result for `trailmark-finding-triage`\n\n## When NOT to Use\n\n- Running static analysis tools (use semgrep\u002Fcodeql directly, then import)\n- Building the code graph itself (use the `trailmark` skill)\n- Generating diagrams (use the `diagramming-code` skill after augmenting)\n\n## Rationalizations to Reject\n\n| Rationalization | Why It's Wrong | Required Action |\n|-----------------|----------------|-----------------|\n| \"The user only asked about SARIF, skip pre-analysis\" | Without pre-analysis, you can't cross-reference findings with blast radius or taint | Always run `engine.preanalysis()` before augmenting |\n| \"Unmatched findings don't matter\" | Unmatched findings may indicate parsing gaps or out-of-scope files | Report unmatched count and investigate if high |\n| \"One severity subgraph is enough\" | Different severities need different triage workflows | Query all severity subgraphs, not just `error` |\n| \"SARIF results speak for themselves\" | Findings without graph context lack blast radius and taint reachability | Cross-reference with pre-analysis subgraphs |\n| \"weAudit and SARIF overlap, pick one\" | Human auditors and tools find different things | Import both when available |\n| \"Tool isn't installed, I'll do it manually\" | Manual analysis misses what tooling catches | Install trailmark first |\n\n---\n\n## Installation\n\n**MANDATORY:** If `uv run trailmark` fails, install trailmark first:\n\n```bash\nuv tool install trailmark\n# Python snippets: uv run --with trailmark python -   (a tool env is not importable)\n```\n\n## Version Gate\n\nSARIF and weAudit augmentation are v0.2-safe. Binary graph augmentation is\nTrailmark 0.4.0+ only. Before calling `engine.augment_binary()`, check:\n\n```python\nif not hasattr(engine, \"augment_binary\"):\n    raise RuntimeError(\"Binary augmentation requires Trailmark >= 0.4.0\")\n```\n\nOn Trailmark 0.5.0+, known links between source functions and imported binary\nor external endpoints can also be declared once in `.trailmark\u002Flinks.toml`\n(see the main `trailmark` skill's Repository Links section) instead of being\nre-derived per session. Declared external endpoints materialize as\n`proxy.external:\u003Csymbol>` nodes on every parse.\n\n## Quick Start\n\n### CLI\n\n```bash\n# Augment with SARIF\nuv run trailmark augment {targetDir} --sarif results.sarif\n\n# Augment with weAudit\nuv run trailmark augment {targetDir} --weaudit .vscode\u002Falice.weaudit\n\n# Both at once, output JSON\nuv run trailmark augment {targetDir} \\\n    --sarif results.sarif \\\n    --weaudit .vscode\u002Falice.weaudit \\\n    --json\n```\n\nBinary graph augmentation is programmatic in Trailmark 0.4.0+; do not invent a\nCLI flag if `trailmark augment --help` does not show one.\n\n### Programmatic API\n\n```python\nfrom trailmark.query.api import QueryEngine\n\nengine = QueryEngine.from_directory(\"{targetDir}\", language=\"auto\")\n\n# Run pre-analysis first for cross-referencing\nengine.preanalysis()\n\n# Augment with SARIF\nresult = engine.augment_sarif(\"results.sarif\")\n# result: {matched_findings: 12, unmatched_findings: 3, subgraphs_created: [...]}\n\n# Augment with weAudit\nresult = engine.augment_weaudit(\".vscode\u002Falice.weaudit\")\n\n# Augment with an external binary graph export (v0.4+)\nif hasattr(engine, \"augment_binary\"):\n    result = engine.augment_binary(\"binary_graph.json\")\n\n# Query findings\nengine.findings()                                       # All findings\nengine.subgraph(\"sarif:error\")                          # High-severity SARIF\nengine.subgraph(\"weaudit:high\")                         # High-severity weAudit\nengine.subgraph(\"sarif:semgrep\")                        # By tool name\nengine.annotations_of(\"function_name\")                  # Per-node lookup\n```\n\nIf auto-detection is wrong for the target, rerun with an explicit language or\ncomma-separated list such as `python,rust`.\n\n## Workflow\n\n```\nAugmentation Progress:\n- [ ] Step 1: Build graph and run pre-analysis\n- [ ] Step 2: Locate SARIF\u002FweAudit\u002Fbinary graph files\n- [ ] Step 3: Run augmentation\n- [ ] Step 4: Inspect results and subgraphs\n- [ ] Step 5: Cross-reference with pre-analysis\n```\n\n**Step 1:** Build the graph and run pre-analysis for blast radius and taint\ncontext:\n\n```python\nengine = QueryEngine.from_directory(\"{targetDir}\", language=\"auto\")\nengine.preanalysis()\n```\n\nIf auto-detection is wrong for the target, rerun with an explicit language or\ncomma-separated list such as `python,rust`.\n\n**Step 2:** Locate input files:\n- **SARIF**: Usually output by tools like `semgrep --sarif -o results.sarif`\n  or `codeql database analyze --format=sarif-latest`\n- **weAudit**: Stored in `.vscode\u002F\u003Cusername>.weaudit` within the workspace\n- **Binary graph (v0.4+)**: External JSON with `artifact`, `functions`, and\n  `calls` fields. Trailmark imports this graph; it does not disassemble\n  binaries itself.\n\n**Step 3:** Run augmentation via `engine.augment_sarif()` or\n`engine.augment_weaudit()`. For binary graphs, run `engine.augment_binary()`\nonly after the Version Gate succeeds. Check `unmatched_findings` in SARIF and\nweAudit results — these are findings whose file\u002Fline locations didn't overlap\nany parsed code unit.\n\n**Step 4:** Query findings and subgraphs. Use `engine.findings()` to list all\nannotated nodes. Use `engine.subgraph_names()` to see available subgraphs.\n\n**Step 5:** Cross-reference with pre-analysis data to prioritize:\n- Findings on tainted nodes: overlap `sarif:error` with `tainted` subgraph\n- Findings on high blast radius nodes: overlap with `high_blast_radius`\n- Findings on privilege boundaries: overlap with `privilege_boundary`\n\nFor one candidate finding that needs a reachability verdict or PoC handoff,\ncontinue with `trailmark-finding-triage` and use the augmented node as the\nbound candidate.\n\n## Annotation Format\n\nFindings are stored as standard Trailmark annotations:\n\n- **Kind**: `finding` (tool-generated) or `audit_note` (human notes)\n- **Source**: `sarif:\u003Ctool_name>` or `weaudit:\u003Cauthor>`\n- **Description**: Compact single-line:\n  `[SEVERITY] rule-id: message (tool)`\n\n## Subgraphs Created\n\n| Subgraph | Contents |\n|----------|----------|\n| `sarif:error` | Nodes with SARIF error-level findings |\n| `sarif:warning` | Nodes with SARIF warning-level findings |\n| `sarif:note` | Nodes with SARIF note-level findings |\n| `sarif:\u003Ctool>` | Nodes flagged by a specific tool |\n| `weaudit:high` | Nodes with high-severity weAudit findings |\n| `weaudit:medium` | Nodes with medium-severity weAudit findings |\n| `weaudit:low` | Nodes with low-severity weAudit findings |\n| `weaudit:findings` | All weAudit findings (entryType=0) |\n| `weaudit:notes` | All weAudit notes (entryType=1) |\n| `binary:\u003Cartifact>` | Binary function nodes imported from a v0.4+ binary graph |\n\n## How Matching Works\n\nFindings are matched to graph nodes by file path and line range overlap:\n\n1. Finding file path is normalized relative to the graph's `root_path`\n2. Nodes whose `location.file_path` matches AND whose line range overlaps are\n   selected\n3. The tightest match (smallest span) is preferred\n4. If a finding's location doesn't overlap any node, it counts as unmatched\n\nSARIF paths may be relative, absolute, or `file:\u002F\u002F` URIs — all are handled.\nweAudit uses 0-indexed lines which are converted to 1-indexed automatically.\n\nBinary graph imports create `origin=binary` function nodes, `origin=proxy`\nexternal proxy nodes for unresolved binary calls, and inferred\n`corresponds_to` edges when a binary function maps back to a source node. The\nexpected JSON shape is intentionally small:\n\n```json\n{\n  \"artifact\": {\"name\": \"libexample\", \"architecture\": \"x86_64\", \"sha256\": \"...\"},\n  \"functions\": [\n    {\"symbol\": \"parse_packet\", \"address\": \"0x401000\",\n     \"source\": {\"file\": \"src\u002Fparser.c\", \"line\": 42}}\n  ],\n  \"calls\": [\n    {\"source\": \"parse_packet\", \"target\": \"malloc\", \"confidence\": \"inferred\"}\n  ]\n}\n```\n\n## Supporting Documentation\n\n- **[references\u002Fformats.md](references\u002Fformats.md)** — SARIF 2.1.0 and\n  weAudit file format field reference\n","# Audit Augmentation\n\nProjects findings from external tools (SARIF) and human auditors (weAudit)\nonto Trailmark code graphs as annotations and subgraphs. Trailmark 0.4.0+ can\nalso import an external binary-analysis graph JSON export via\n`engine.augment_binary()`.\n\n## When to Use\n\n- Importing Semgrep, CodeQL, or other SARIF-producing tool results into a graph\n- Importing weAudit audit annotations into a graph\n- Importing binary-analysis graph data into a source graph (Trailmark 0.4.0+)\n- Cross-referencing static analysis findings with blast radius or taint data\n- Querying which functions have high-severity findings\n- Visualizing audit coverage alongside code structure\n- Preparing one SARIF or weAudit result for `trailmark-finding-triage`\n\n## When NOT to Use\n\n- Running static analysis tools (use semgrep\u002Fcodeql directly, then import)\n- Building the code graph itself (use the `trailmark` skill)\n- Generating diagrams (use the `diagramming-code` skill after augmenting)\n\n## Rationalizations to Reject\n\n| Rationalization | Why It's Wrong | Required Action |\n|-----------------|----------------|-----------------|\n| \"The user only asked about SARIF, skip pre-analysis\" | Without pre-analysis, you can't cross-reference findings with blast radius or taint | Always run `engine.preanalysis()` before augmenting |\n| \"Unmatched findings don't matter\" | Unmatched findings may indicate parsing gaps or out-of-scope files | Report unmatched count and investigate if high |\n| \"One severity subgraph is enough\" | Different severities need different triage workflows | Query all severity subgraphs, not just `error` |\n| \"SARIF results speak for themselves\" | Findings without graph context lack blast radius and taint reachability | Cross-reference with pre-analysis subgraphs |\n| \"weAudit and SARIF overlap, pick one\" | Human auditors and tools find different things | Import both when available |\n| \"Tool isn't installed, I'll do it manually\" | Manual analysis misses what tooling catches | Install trailmark first |\n\n---\n\n## Installation\n\n**MANDATORY:** If `uv run trailmark` fails, install trailmark first:\n\n```bash\nuv tool install trailmark\n# Python snippets: uv run --with trailmark python -   (a tool env is not importable)\n```\n\n## Version Gate\n\nSARIF and weAudit augmentation are v0.2-safe. Binary graph augmentation is\nTrailmark 0.4.0+ only. Before calling `engine.augment_binary()`, check:\n\n```python\nif not hasattr(engine, \"augment_binary\"):\n    raise RuntimeError(\"Binary augmentation requires Trailmark >= 0.4.0\")\n```\n\nOn Trailmark 0.5.0+, known links between source functions and imported binary\nor external endpoints can also be declared once in `.trailmark\u002Flinks.toml`\n(see the main `trailmark` skill's Repository Links section) instead of being\nre-derived per session. Declared external endpoints materialize as\n`proxy.external:\u003Csymbol>` nodes on every parse.\n\n## Quick Start\n\n### CLI\n\n```bash\n# Augment with SARIF\nuv run trailmark augment {targetDir} --sarif results.sarif\n\n# Augment with weAudit\nuv run trailmark augment {targetDir} --weaudit .vscode\u002Falice.weaudit\n\n# Both at once, output JSON\nuv run trailmark augment {targetDir} \\\n    --sarif results.sarif \\\n    --weaudit .vscode\u002Falice.weaudit \\\n    --json\n```\n\nBinary graph augmentation is programmatic in Trailmark 0.4.0+; do not invent a\nCLI flag if `trailmark augment --help` does not show one.\n\n### Programmatic API\n\n```python\nfrom trailmark.query.api import QueryEngine\n\nengine = QueryEngine.from_directory(\"{targetDir}\", language=\"auto\")\n\n# Run pre-analysis first for cross-referencing\nengine.preanalysis()\n\n# Augment with SARIF\nresult = engine.augment_sarif(\"results.sarif\")\n# result: {matched_findings: 12, unmatched_findings: 3, subgraphs_created: [...]}\n\n# Augment with weAudit\nresult = engine.augment_weaudit(\".vscode\u002Falice.weaudit\")\n\n# Augment with an external binary graph export (v0.4+)\nif hasattr(engine, \"augment_binary\"):\n    result = engine.augment_binary(\"binary_graph.json\")\n\n# Query findings\nengine.findings()                                       # All findings\nengine.subgraph(\"sarif:error\")                          # High-severity SARIF\nengine.subgraph(\"weaudit:high\")                         # High-severity weAudit\nengine.subgraph(\"sarif:semgrep\")                        # By tool name\nengine.annotations_of(\"function_name\")                  # Per-node lookup\n```\n\nIf auto-detection is wrong for the target, rerun with an explicit language or\ncomma-separated list such as `python,rust`.\n\n## Workflow\n\n```\nAugmentation Progress:\n- [ ] Step 1: Build graph and run pre-analysis\n- [ ] Step 2: Locate SARIF\u002FweAudit\u002Fbinary graph files\n- [ ] Step 3: Run augmentation\n- [ ] Step 4: Inspect results and subgraphs\n- [ ] Step 5: Cross-reference with pre-analysis\n```\n\n**Step 1:** Build the graph and run pre-analysis for blast radius and taint\ncontext:\n\n```python\nengine = QueryEngine.from_directory(\"{targetDir}\", language=\"auto\")\nengine.preanalysis()\n```\n\nIf auto-detection is wrong for the target, rerun with an explicit language or\ncomma-separated list such as `python,rust`.\n\n**Step 2:** Locate input files:\n- **SARIF**: Usually output by tools like `semgrep --sarif -o results.sarif`\n  or `codeql database analyze --format=sarif-latest`\n- **weAudit**: Stored in `.vscode\u002F\u003Cusername>.weaudit` within the workspace\n- **Binary graph (v0.4+)**: External JSON with `artifact`, `functions`, and\n  `calls` fields. Trailmark imports this graph; it does not disassemble\n  binaries itself.\n\n**Step 3:** Run augmentation via `engine.augment_sarif()` or\n`engine.augment_weaudit()`. For binary graphs, run `engine.augment_binary()`\nonly after the Version Gate succeeds. Check `unmatched_findings` in SARIF and\nweAudit results — these are findings whose file\u002Fline locations didn't overlap\nany parsed code unit.\n\n**Step 4:** Query findings and subgraphs. Use `engine.findings()` to list all\nannotated nodes. Use `engine.subgraph_names()` to see available subgraphs.\n\n**Step 5:** Cross-reference with pre-analysis data to prioritize:\n- Findings on tainted nodes: overlap `sarif:error` with `tainted` subgraph\n- Findings on high blast radius nodes: overlap with `high_blast_radius`\n- Findings on privilege boundaries: overlap with `privilege_boundary`\n\nFor one candidate finding that needs a reachability verdict or PoC handoff,\ncontinue with `trailmark-finding-triage` and use the augmented node as the\nbound candidate.\n\n## Annotation Format\n\nFindings are stored as standard Trailmark annotations:\n\n- **Kind**: `finding` (tool-generated) or `audit_note` (human notes)\n- **Source**: `sarif:\u003Ctool_name>` or `weaudit:\u003Cauthor>`\n- **Description**: Compact single-line:\n  `[SEVERITY] rule-id: message (tool)`\n\n## Subgraphs Created\n\n| Subgraph | Contents |\n|----------|----------|\n| `sarif:error` | Nodes with SARIF error-level findings |\n| `sarif:warning` | Nodes with SARIF warning-level findings |\n| `sarif:note` | Nodes with SARIF note-level findings |\n| `sarif:\u003Ctool>` | Nodes flagged by a specific tool |\n| `weaudit:high` | Nodes with high-severity weAudit findings |\n| `weaudit:medium` | Nodes with medium-severity weAudit findings |\n| `weaudit:low` | Nodes with low-severity weAudit findings |\n| `weaudit:findings` | All weAudit findings (entryType=0) |\n| `weaudit:notes` | All weAudit notes (entryType=1) |\n| `binary:\u003Cartifact>` | Binary function nodes imported from a v0.4+ binary graph |\n\n## How Matching Works\n\nFindings are matched to graph nodes by file path and line range overlap:\n\n1. Finding file path is normalized relative to the graph's `root_path`\n2. Nodes whose `location.file_path` matches AND whose line range overlaps are\n   selected\n3. The tightest match (smallest span) is preferred\n4. If a finding's location doesn't overlap any node, it counts as unmatched\n\nSARIF paths may be relative, absolute, or `file:\u002F\u002F` URIs — all are handled.\nweAudit uses 0-indexed lines which are converted to 1-indexed automatically.\n\nBinary graph imports create `origin=binary` function nodes, `origin=proxy`\nexternal proxy nodes for unresolved binary calls, and inferred\n`corresponds_to` edges when a binary function maps back to a source node. The\nexpected JSON shape is intentionally small:\n\n```json\n{\n  \"artifact\": {\"name\": \"libexample\", \"architecture\": \"x86_64\", \"sha256\": \"...\"},\n  \"functions\": [\n    {\"symbol\": \"parse_packet\", \"address\": \"0x401000\",\n     \"source\": {\"file\": \"src\u002Fparser.c\", \"line\": 42}}\n  ],\n  \"calls\": [\n    {\"source\": \"parse_packet\", \"target\": \"malloc\", \"confidence\": \"inferred\"}\n  ]\n}\n```\n\n## Supporting Documentation\n\n- **[references\u002Fformats.md](references\u002Fformats.md)** — SARIF 2.1.0 and\n  weAudit file format field reference\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","03-逆向工程\u002Faudit-augmentation",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 audit-augmentation",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill audit-augmentation",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill audit-augmentation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Faudit-augmentation\u002FSKILL.md",true,[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",245,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Faudit-augmentation\u002Fagents\u002Fopenai.yaml",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fformats.md",3609,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Faudit-augmentation\u002Freferences\u002Fformats.md",[57,65,70,77,84,91],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":64},"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":66,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":64},"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":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":64},"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":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":64},"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":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":64},"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":64},"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",[],[]]