[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F5P0FDJC22NTFFB0PFPDNR":3,"skill-same:01M7F5P0FDJC22NTFFB0PFPDNR":76},{"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":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M7F5P0FDJC22NTFFB0PFPDNR","survey-generator",null,"Generate source-backed AI\u002FML survey paper artifacts with curated bibliographies and Fireworks\u002FKimi HTML rendering.","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\u002Fsurvey-generator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: survey-generator\ndescription: \"Generate source-backed AI\u002FML survey paper artifacts with curated bibliographies and Fireworks\u002FKimi HTML rendering.\"\nallowed-tools: Read, Write, Bash, WebFetch, AskUserQuestion\ncategory: \"research\"\nrisk: \"safe\"\nsource: \"official\"\nsource_repo: \"dair-ai\u002Fdair-academy-plugins\"\nsource_type: \"official\"\ndate_added: \"2026-06-19\"\nauthor: \"DAIR.AI\"\nlicense: \"MIT\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002Fdair-ai\u002Fdair-academy-plugins\u002Fblob\u002Fmain\u002FREADME.md#license\"\ntags:\n  - dair-academy\n  - ai\n  - workflow\ntools:\n  - claude-code\n  - codex-cli\n  - cursor\n---\n\n# Survey Generator Skill\n\n## When to Use\n\nUse when this workflow matches the user request: Use this skill for its documented workflow.\n\n\n_Source: [dair-ai\u002Fdair-academy-plugins](https:\u002F\u002Fgithub.com\u002Fdair-ai\u002Fdair-academy-plugins) (MIT)._\n\nGenerate an academic-style survey paper as a single self-contained HTML file.\n\n## What this skill does\n\nGiven a topic and a public anchor resource, this skill:\n1. Reads the anchor resource and extracts the landscape of relevant work.\n2. Builds a structured `research_bundle.json` (title, taxonomy, sections, bibliography of real papers).\n3. Calls Kimi K2.6 via the Fireworks chat completions API with the research bundle and a fixed `style_spec.json`.\n4. Writes a single-file HTML artifact with inline SVG figures, an academic layout, numbered sections, and a References list.\n\nThe agent using this skill is responsible only for research curation. All prose, figures, and HTML are generated by Kimi K2.6 in one API call.\n\n## Inputs from the user\n\nThe user invokes this skill with at minimum:\n\n- `topic`: a concise survey topic, for example \"Agentic Engineering\" or \"Reasoning Models\".\n- `source_url`: a public anchor resource. Any curated list, canonical blog post, arXiv survey, GitHub awesome-list, or index page works. Suggested starting points: [DAIR.AI AI Papers of the Week](https:\u002F\u002Fgithub.com\u002Fdair-ai\u002FAI-Papers-of-the-Week) (a continuously updated open-source index of notable AI\u002FML papers, well suited for broad topics), a GitHub awesome-* repo, an arXiv survey PDF, or a well-maintained papers page.\n\nOptional:\n\n- `bibliography_size`: target bibliography size. Default 20 for a quick survey. Use 40 to 50 for a comprehensive survey, 80 to 100 for an exhaustive one. Section length and token budget scale with this.\n- `section_count`: number of sections, default 6 to 10.\n\nIf the user has not provided these, use AskUserQuestion to collect them before proceeding.\n\n## Requirements\n\n- `FIREWORKS_API_KEY` exported in the environment. The build script reads it from `os.environ`.\n- Python 3 with stdlib only (urllib). No external dependencies.\n\n## Workflow for the agent\n\nFollow these steps in order. Do not skip steps.\n\n### Step 1. Read the anchor resource\n\nFetch and read `source_url`. If it is a GitHub repo, fetch the README and any relevant `README-*.md` or `papers.md` indices. If it is an arXiv survey, use the abstract, figures, and section headings. If it is a blog post, read it in full. Extract the key subtopics and the papers or systems it references by name.\n\nFor broad AI\u002FML topics, [DAIR.AI AI Papers of the Week](https:\u002F\u002Fgithub.com\u002Fdair-ai\u002FAI-Papers-of-the-Week) is a particularly rich anchor: it has weekly issues going back years, each with short summaries of 6 to 10 notable papers, so it is easy to scan across time and filter to the subset that matches your topic.\n\nIf a paper-search tool is available to your agent (a Papers-of-the-Week MCP, arXiv search, Semantic Scholar, Google Scholar, an organization's internal index, etc.), use it to expand the candidate pool beyond what the anchor resource cites directly.\n\n### Step 2. Define the taxonomy and sections\n\nDraft a taxonomy rooted at the topic with 4 to 8 branches, each with 2 to 4 children. Branches should cover distinct subareas of the topic, not overlap. Draft 6 to 10 numbered sections that match the taxonomy progression: introduction, foundations, methods, evaluation, open problems. Figure 1's viewport height scales automatically with the total leaf count via the geometry contract in `style_spec.json`, so deeper taxonomies render cleanly.\n\n### Step 3. Curate the bibliography\n\nPick real papers sized to `bibliography_size`. For a comprehensive survey, 40 to 50 entries is the sweet spot; the skill has been tested up to 100 entries with `max_tokens=81920` in `build_artifact.py`. Every entry must have: `key`, `authors`, `year`, `title`, `venue`, and a 1 to 2 sentence `summary`. Do not invent papers. Every section's `papers` array must reference keys that exist in the bibliography.\n\n### Step 4. Write `research_bundle.json`\n\nWrite `research_bundle.json` in the skill directory (next to `build_artifact.py`). Use `templates\u002Fresearch_bundle_template.json` as the structural scaffold. Required top-level fields: `title`, `authors_placeholder`, `anchor_source`, `abstract_hints`, `taxonomy`, `paradigms`, `stack`, `sections`, `table`, `bibliography`. See `examples\u002Fagentic-engineering\u002Fresearch_bundle.json` for a complete worked example.\n\n### Step 5. Run the generator\n\n```bash\npython3 build_artifact.py\n```\n\nRun this from the skill directory. The script reads `research_bundle.json` and `style_spec.json`, calls Kimi K2.6 on Fireworks, and writes `output\u002Fsurvey_kimi-k2p6_v{N}.html`. Each run produces a new versioned file.\n\nTo use a different Fireworks model (for example Kimi K2.5 for side-by-side comparison):\n\n```bash\nFIREWORKS_MODEL=accounts\u002Ffireworks\u002Fmodels\u002Fkimi-k2p5 python3 build_artifact.py\n```\n\nOutput filenames are slugged by model so you can compare versions across models.\n\n### Step 6. Preview and iterate\n\nOpen the HTML file locally. It is a fully self-contained HTML document, so you can also serve it from any static host, embed it in a dashboard, or hand it to any artifact-preview mechanism your agent exposes.\n\nIf figures look weak, sharpen `style_spec.json` (the `required_figures` and `figure_quality_note` keys) and rerun. If prose is thin or sections are missing, tighten the section `guidance` fields in `research_bundle.json`. Do not edit the Kimi output directly; iterate on inputs.\n\nCommon figure failure modes and the style_spec patterns that fix them:\n- Nodes from different panels collapsing into one panel: require `\u003Cg transform=\"translate(OFFSET,0)\">` groups with panel-local coordinates (enforced for Figure 2).\n- Leaf rects overlapping vertically so labels get clipped: enforce rect_pitch greater than rect_height with an explicit formula and a sanity check (enforced for Figure 1).\n- Root label overflowing its pill: pin minimum rect width in the spec (enforced for Figure 1, width=200).\n- Sibling nodes in a row overlapping horizontally (e.g. Worker A, Worker B, Worker C in an orchestrator-workers panel): enforce a deterministic rect_width and center_x formula for N nodes in a fixed-width panel, with a minimum horizontal gap between adjacent rects (enforced for Figure 2 multi-node rows).\n- Panel contents drifting to the left or right edge instead of sitting in the middle of the panel background: pin each group's translate offset to match the panel background's x position (10, 270, 530) and center all content on panel-local x=120 (enforced for Figure 2).\n- Figures emitted in the wrong numeric order because the model preferred a different narrative flow: require the captions to use the exact IDs from required_figures in sequence (Figure 1 before Figure 2 before Figure 3), even if it means placing two figures in the same section (enforced via hard_rules_for_generation).\n- Right-side labels on the stack diagram getting clipped at the viewport edge: widen the stack SVG viewport to 720 and require role-text tspans to fit within x=710 (enforced for Figure 3).\n\nWhen adding a new figure or changing an existing one, follow the same pattern: declare an absolute viewport, per-element coordinates or a deterministic formula, and a hard-invariant check clause at the end of the description.\n\n## Files in this skill\n\n- `SKILL.md` - this file.\n- `build_artifact.py` - Python script that calls Fireworks.\n- `style_spec.json` - visual and structural spec (topic-agnostic).\n- `templates\u002Fresearch_bundle_template.json` - empty template for new topics.\n- `examples\u002Fagentic-engineering\u002F` - reference 100-paper run (research_bundle.json + survey.html).\n\n## Hard rules the agent must follow\n\n1. Never invent bibliography entries. Every cited paper must be a real work with a real venue.\n2. Every section's `papers` array must reference keys in the bibliography.\n3. Never edit the generated HTML. Iterate on `research_bundle.json` or `style_spec.json` and rerun.\n4. Do not modify the hard rules in `style_spec.json.hard_rules_for_generation`.\n5. Keep the style_spec topic-agnostic. Topic-specific content lives only in `research_bundle.json`.\n6. Do not use em dashes or arrow symbols in the research bundle prose fields.\n\n\n## Limitations\n\n- Requires the upstream tool, account, API key, or local setup when the workflow names one.\n- Does not authorize destructive, production, paid, or external-message actions without explicit user approval.\n- Validate generated artifacts or recommendations against the user's real sources before treating them as final.\n","# Survey Generator Skill\n\n## When to Use\n\nUse when this workflow matches the user request: Use this skill for its documented workflow.\n\n\n_Source: [dair-ai\u002Fdair-academy-plugins](https:\u002F\u002Fgithub.com\u002Fdair-ai\u002Fdair-academy-plugins) (MIT)._\n\nGenerate an academic-style survey paper as a single self-contained HTML file.\n\n## What this skill does\n\nGiven a topic and a public anchor resource, this skill:\n1. Reads the anchor resource and extracts the landscape of relevant work.\n2. Builds a structured `research_bundle.json` (title, taxonomy, sections, bibliography of real papers).\n3. Calls Kimi K2.6 via the Fireworks chat completions API with the research bundle and a fixed `style_spec.json`.\n4. Writes a single-file HTML artifact with inline SVG figures, an academic layout, numbered sections, and a References list.\n\nThe agent using this skill is responsible only for research curation. All prose, figures, and HTML are generated by Kimi K2.6 in one API call.\n\n## Inputs from the user\n\nThe user invokes this skill with at minimum:\n\n- `topic`: a concise survey topic, for example \"Agentic Engineering\" or \"Reasoning Models\".\n- `source_url`: a public anchor resource. Any curated list, canonical blog post, arXiv survey, GitHub awesome-list, or index page works. Suggested starting points: [DAIR.AI AI Papers of the Week](https:\u002F\u002Fgithub.com\u002Fdair-ai\u002FAI-Papers-of-the-Week) (a continuously updated open-source index of notable AI\u002FML papers, well suited for broad topics), a GitHub awesome-* repo, an arXiv survey PDF, or a well-maintained papers page.\n\nOptional:\n\n- `bibliography_size`: target bibliography size. Default 20 for a quick survey. Use 40 to 50 for a comprehensive survey, 80 to 100 for an exhaustive one. Section length and token budget scale with this.\n- `section_count`: number of sections, default 6 to 10.\n\nIf the user has not provided these, use AskUserQuestion to collect them before proceeding.\n\n## Requirements\n\n- `FIREWORKS_API_KEY` exported in the environment. The build script reads it from `os.environ`.\n- Python 3 with stdlib only (urllib). No external dependencies.\n\n## Workflow for the agent\n\nFollow these steps in order. Do not skip steps.\n\n### Step 1. Read the anchor resource\n\nFetch and read `source_url`. If it is a GitHub repo, fetch the README and any relevant `README-*.md` or `papers.md` indices. If it is an arXiv survey, use the abstract, figures, and section headings. If it is a blog post, read it in full. Extract the key subtopics and the papers or systems it references by name.\n\nFor broad AI\u002FML topics, [DAIR.AI AI Papers of the Week](https:\u002F\u002Fgithub.com\u002Fdair-ai\u002FAI-Papers-of-the-Week) is a particularly rich anchor: it has weekly issues going back years, each with short summaries of 6 to 10 notable papers, so it is easy to scan across time and filter to the subset that matches your topic.\n\nIf a paper-search tool is available to your agent (a Papers-of-the-Week MCP, arXiv search, Semantic Scholar, Google Scholar, an organization's internal index, etc.), use it to expand the candidate pool beyond what the anchor resource cites directly.\n\n### Step 2. Define the taxonomy and sections\n\nDraft a taxonomy rooted at the topic with 4 to 8 branches, each with 2 to 4 children. Branches should cover distinct subareas of the topic, not overlap. Draft 6 to 10 numbered sections that match the taxonomy progression: introduction, foundations, methods, evaluation, open problems. Figure 1's viewport height scales automatically with the total leaf count via the geometry contract in `style_spec.json`, so deeper taxonomies render cleanly.\n\n### Step 3. Curate the bibliography\n\nPick real papers sized to `bibliography_size`. For a comprehensive survey, 40 to 50 entries is the sweet spot; the skill has been tested up to 100 entries with `max_tokens=81920` in `build_artifact.py`. Every entry must have: `key`, `authors`, `year`, `title`, `venue`, and a 1 to 2 sentence `summary`. Do not invent papers. Every section's `papers` array must reference keys that exist in the bibliography.\n\n### Step 4. Write `research_bundle.json`\n\nWrite `research_bundle.json` in the skill directory (next to `build_artifact.py`). Use `templates\u002Fresearch_bundle_template.json` as the structural scaffold. Required top-level fields: `title`, `authors_placeholder`, `anchor_source`, `abstract_hints`, `taxonomy`, `paradigms`, `stack`, `sections`, `table`, `bibliography`. See `examples\u002Fagentic-engineering\u002Fresearch_bundle.json` for a complete worked example.\n\n### Step 5. Run the generator\n\n```bash\npython3 build_artifact.py\n```\n\nRun this from the skill directory. The script reads `research_bundle.json` and `style_spec.json`, calls Kimi K2.6 on Fireworks, and writes `output\u002Fsurvey_kimi-k2p6_v{N}.html`. Each run produces a new versioned file.\n\nTo use a different Fireworks model (for example Kimi K2.5 for side-by-side comparison):\n\n```bash\nFIREWORKS_MODEL=accounts\u002Ffireworks\u002Fmodels\u002Fkimi-k2p5 python3 build_artifact.py\n```\n\nOutput filenames are slugged by model so you can compare versions across models.\n\n### Step 6. Preview and iterate\n\nOpen the HTML file locally. It is a fully self-contained HTML document, so you can also serve it from any static host, embed it in a dashboard, or hand it to any artifact-preview mechanism your agent exposes.\n\nIf figures look weak, sharpen `style_spec.json` (the `required_figures` and `figure_quality_note` keys) and rerun. If prose is thin or sections are missing, tighten the section `guidance` fields in `research_bundle.json`. Do not edit the Kimi output directly; iterate on inputs.\n\nCommon figure failure modes and the style_spec patterns that fix them:\n- Nodes from different panels collapsing into one panel: require `\u003Cg transform=\"translate(OFFSET,0)\">` groups with panel-local coordinates (enforced for Figure 2).\n- Leaf rects overlapping vertically so labels get clipped: enforce rect_pitch greater than rect_height with an explicit formula and a sanity check (enforced for Figure 1).\n- Root label overflowing its pill: pin minimum rect width in the spec (enforced for Figure 1, width=200).\n- Sibling nodes in a row overlapping horizontally (e.g. Worker A, Worker B, Worker C in an orchestrator-workers panel): enforce a deterministic rect_width and center_x formula for N nodes in a fixed-width panel, with a minimum horizontal gap between adjacent rects (enforced for Figure 2 multi-node rows).\n- Panel contents drifting to the left or right edge instead of sitting in the middle of the panel background: pin each group's translate offset to match the panel background's x position (10, 270, 530) and center all content on panel-local x=120 (enforced for Figure 2).\n- Figures emitted in the wrong numeric order because the model preferred a different narrative flow: require the captions to use the exact IDs from required_figures in sequence (Figure 1 before Figure 2 before Figure 3), even if it means placing two figures in the same section (enforced via hard_rules_for_generation).\n- Right-side labels on the stack diagram getting clipped at the viewport edge: widen the stack SVG viewport to 720 and require role-text tspans to fit within x=710 (enforced for Figure 3).\n\nWhen adding a new figure or changing an existing one, follow the same pattern: declare an absolute viewport, per-element coordinates or a deterministic formula, and a hard-invariant check clause at the end of the description.\n\n## Files in this skill\n\n- `SKILL.md` - this file.\n- `build_artifact.py` - Python script that calls Fireworks.\n- `style_spec.json` - visual and structural spec (topic-agnostic).\n- `templates\u002Fresearch_bundle_template.json` - empty template for new topics.\n- `examples\u002Fagentic-engineering\u002F` - reference 100-paper run (research_bundle.json + survey.html).\n\n## Hard rules the agent must follow\n\n1. Never invent bibliography entries. Every cited paper must be a real work with a real venue.\n2. Every section's `papers` array must reference keys in the bibliography.\n3. Never edit the generated HTML. Iterate on `research_bundle.json` or `style_spec.json` and rerun.\n4. Do not modify the hard rules in `style_spec.json.hard_rules_for_generation`.\n5. Keep the style_spec topic-agnostic. Topic-specific content lives only in `research_bundle.json`.\n6. Do not use em dashes or arrow symbols in the research bundle prose fields.\n\n\n## Limitations\n\n- Requires the upstream tool, account, API key, or local setup when the workflow names one.\n- Does not authorize destructive, production, paid, or external-message actions without explicit user approval.\n- Validate generated artifacts or recommendations against the user's real sources before treating them as final.\n",{"name":5,"risk":24,"tags":25,"tools":29,"author":33,"source":34,"license":15,"category":35,"date_added":36,"description":7,"source_repo":37,"source_type":34,"allowed-tools":38,"license_source":39},"safe",[26,27,28],"dair-academy","ai","workflow",[30,31,32],"claude-code","codex-cli","cursor","DAIR.AI","official","research","2026-06-19","dair-ai\u002Fdair-academy-plugins","Read, Write, Bash, WebFetch, AskUserQuestion","https:\u002F\u002Fgithub.com\u002Fdair-ai\u002Fdair-academy-plugins\u002Fblob\u002Fmain\u002FREADME.md#license","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fsurvey-generator",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":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill survey-generator",{"tool":54,"command":55},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill survey-generator",{"tool":57,"command":58},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill survey-generator","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\u002Fsurvey-generator\u002FSKILL.md",true,[62,68,72],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"examples\u002Fagentic-engineering\u002Fresearch_bundle.json","REFERENCE","参考文档",54751,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsurvey-generator\u002Fexamples\u002Fagentic-engineering\u002Fresearch_bundle.json",{"path":69,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":70,"sourceHtmlUrl":71},"style_spec.json",13284,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsurvey-generator\u002Fstyle_spec.json",{"path":73,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":74,"sourceHtmlUrl":75},"templates\u002Fresearch_bundle_template.json",3105,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsurvey-generator\u002Ftemplates\u002Fresearch_bundle_template.json",[77,84,89,96,103,110],{"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":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":85,"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":86,"categories":87,"keywords":88,"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":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},"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":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},"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":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},"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":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},"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",[],[]]