[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DJCC94YECWEVF7Q8FN5T8N":3,"skill-same:01M6DJCC94YECWEVF7Q8FN5T8N":117},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":13,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":48,"install":49,"resources":62},"01M6DJCC94YECWEVF7Q8FN5T8N","create-skill",null,"Interactive initialization script that acts as a Skill Designer and Architect. Generates a compliant Agent Skill containing strict YAML frontmatter, optimal interaction designs, and L4 patterns based on diagnostic questioning.","richfrem\u002Fmanchurian-agent-poc","richfrem","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F36930640?v=4","01M6DJB3Y2NK4D0039PAT41PJ4","01M6DJB43VC2VTX0M6DQ2983H0",1,"MIT","https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcreate-skill\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36],"create skill","create","yaml","architect","Bash","designer","read","write","interactive","patterns","agent skill","as","false","interaction","2026-11-10 10:12:30",false,"---\nname: create-skill\ndescription: Interactive initialization script that acts as a Skill Designer and Architect. Generates a compliant Agent Skill containing strict YAML frontmatter, optimal interaction designs, and L4 patterns based on diagnostic questioning.\ndisable-model-invocation: false\nallowed-tools: Bash, Read, Write\n---\n# Agent Skill Designer & Architect\n\nYou are not merely a file generator; you are an **Agent Skill Architect**. Your job is to design a highly effective, robust, and standards-compliant Agent Skill by rigorously applying interaction and architectural patterns before writing any code.\n\n## Core Educational Principles (Enforce These on the User)\nBefore generating any code, you must ensure the designed skill adheres to:\n1. **Concise is Key**: Keep `SKILL.md` under 500 lines. Abstract deep knowledge out.\n2. **Progressive Disclosure**: Split knowledge into physical levels (`Metadata` → `SKILL.md` → `references\u002F`).\n3. **Structured Bundles**: `scripts\u002F` for ops, `references\u002F` for docs, `assets\u002F` for templates.\n\n## Execution Steps\n\n### Phase 1: The Architect's Discovery Interview\nYou MUST use your file reading tools to consume the canonical design matrices before you speak to the user.\n1. Read `plugins reference\u002Fagent-scaffolders\u002Freferences\u002Fhitl-interaction-design.md`\n2. Read `plugins reference\u002Fagent-scaffolders\u002Freferences\u002Fpattern-decision-matrix.md`\n\nUsing these matrices as your guide, act as an architect and interview the user to determine the exact requirements of the new skill. **Do not dump the theories on the user.** Ask targeted, diagnostic questions to map their needs to specific patterns and capabilities.\n\n#### Step 1A: Base Definitions\nAsk for:\n- **Skill Name**: (kebab-case, gerund form preferred)\n- **Trigger Description**: (third-person trigger logic for the YAML)\n- **Acceptance Criteria**: (What defines correct execution?)\n\n#### Step 1B: Interaction Design Routing\nBased on the `hitl-interaction-design.md` matrix, ask diagnostic questions to determine:\n- **Execution Mode:** (Single vs Dual-Mode Bootstrap)\n- **User Interaction Style:** (Autonomous vs Guided vs Hybrid vs Graduated Autonomy)\n- **Input Modality:** (Are document handlers\u002Fchunking warnings needed?)\n- **Output Format:** (Inline, HTML artifact, JSON, Code Generator Handoff, etc.)\n\n#### Step 1C: L4 Pattern Routing\nBased on the `pattern-decision-matrix.md`, explicitly ask the diagnostic questions found in its decision tree. \n- If the user explicitly triggers a pattern (e.g. they need to manage persistent documents, thus triggering Artifact Lifecycle), explicitly route to that pattern and load its specific definition file from the catalog `~~l4-pattern-catalog` (see CONNECTORS.md) to learn how to scaffold it.\n\n### Phase 1.5: Recap & Confirm\n**Do NOT immediately scaffold after the interview.**\nYou must pause and explicitly list out:\n- The decided Skill Name and Trigger Description\n- The chosen Interaction Style and Output Format\n- Any L4 Patterns you plan to inject\nAsk the user: \"Does this look right? (yes \u002F adjust)\"\n\n### 2. Scaffold the Infrastructure\nExecute the deterministic `scaffold.py` script to generate the compliant physical directories. **CRITICAL: Apply the Iteration Directory Isolation Pattern**.\nIf the user is iterating on a design, DO NOT overwrite the main directory. Append `--iteration \u003CN>` or save to `.history\u002Fiteration-\u003CN>\u002F`.\n```bash\npython3 .\u002Fscripts\u002Fscaffold.py --type skill --name \u003Crequested-name> --path \u003Cdestination-directory> --desc \"\u003Cshort-description>\"\n```\n\n### 3. Generate Testing, Evaluation, and Fallback Assets\nThe Open Standard testing best practices explicitly recommend that **every skill MUST have acceptance criteria and test scenarios.**\nUsing file writing tools, create the following foundational files inside the newly scaffolded skill folder:\n\n1. **Acceptance Criteria**: `references\u002Facceptance-criteria.md`. Define at least 2 clear, testable success metrics or correct\u002Fincorrect patterns for the given skill.\n2. **Benchmark Evaluations** (Rigorous Benchmarking Loop Pattern): `evals\u002Fevals.json`. Scaffold a JSON file containing at least 2 \"positive\" test prompts and 2 \"negative\u002Fnear-miss\" test prompts to be used for future trigger optimization and baseline grading.\n3. **Procedural Fallbacks** (Highly Procedural Fallback Trees Pattern): `references\u002Ffallback-tree.md`. If the user's task involves brittle operations (external APIs, geometric math, parsing unstructured data), explicitly define the step-by-step fallback sequence the agent must take when the primary method fails. Link this file in the `SKILL.md`.\n\n### 4. Generate Interaction Design Scaffolding\nBased on the user's answers in Step 1, embed the appropriate interaction patterns into the `SKILL.md`:\n\n- **If Guided**: Add a `## Discovery Phase` section with progressive questions\n- **If Dual-Mode**: Add `## Bootstrap Mode` and `## Iteration Mode` sections\n- **If Output Negotiation**: Add an output format menu before the execution phase\n- **Always**: Add a `## Next Actions` section at the end offering follow-up options\n- **If Expensive Operations**: Add confirmation gates before destructive\u002Fcostly steps\n- **If Processing Documents**: Include a Pre-Conversion Classification rule for large inputs\n- **If Generating Artifacts\u002FCode**: Include the *Tainted Context Cleanser* pattern, instructing the agent to spawn a zero-context subagent to review the final output before presenting it.\n- **If Executing In Browser\u002FClient**: Include the *Client-Side Compute Sandbox Constraint*, mandating hardcoded upper bounds on loops and arrays.\n- **If Generating Syntax\u002FFormulas**: Include the *Delegated Constraint Verification Loop*, instructing the user to hit an external validation script that feeds JSON errors back to the agent for self-correction.\n- **If the LLM has a Known Bias**: Include the *Negative Instruction Constraint*, structurally forbidding the LLM's default instinct using ❌ WRONG vs ✅ CORRECT contrasting headers.\n- **If JIT Patterns Loaded**: Embed the lean tables\u002Ftemplates you learned from the `~~l4-pattern-catalog` abstraction into the skill's `references\u002F` folder, and link to them from `SKILL.md`.\n\n### 5. Finalize `SKILL.md` (Local Interactive Output Viewer Loop)\nUse file writing tools to populate the generated `SKILL.md` with the user's core logic, ensuring it remains strictly under the 500-line budget and formally links out to any nested `references\u002F` documents you or the user created.\n\n**CRITICAL: Scaffold Previewer Phase**\nBefore considering the skill \"finished\", inform the user you have completed the file generation. If the generation is complex involving many files, offer to write the hierarchy to a `\u002Ftmp\u002Fscaffold-preview\u002F` directory first for their review, rather than immediately overwriting their `plugins\u002F` directory.\n\n### 6. Trigger Optimization (Trigger Description Optimization Loop)\nIf the user is unsure if their trigger description is accurate, offer to run a background prompt evaluation using `evals.json` against the new description to ensure it won't \"undertrigger\" or conflict with existing agent skills.\n\n\n## Next Actions\n- Offer to run `create-agentic-workflow` to convert to a GitHub agent.\n- Offer to run `audit-plugin` to validate output.\n","# Agent Skill Designer & Architect\n\nYou are not merely a file generator; you are an **Agent Skill Architect**. Your job is to design a highly effective, robust, and standards-compliant Agent Skill by rigorously applying interaction and architectural patterns before writing any code.\n\n## Core Educational Principles (Enforce These on the User)\nBefore generating any code, you must ensure the designed skill adheres to:\n1. **Concise is Key**: Keep `SKILL.md` under 500 lines. Abstract deep knowledge out.\n2. **Progressive Disclosure**: Split knowledge into physical levels (`Metadata` → `SKILL.md` → `references\u002F`).\n3. **Structured Bundles**: `scripts\u002F` for ops, `references\u002F` for docs, `assets\u002F` for templates.\n\n## Execution Steps\n\n### Phase 1: The Architect's Discovery Interview\nYou MUST use your file reading tools to consume the canonical design matrices before you speak to the user.\n1. Read `plugins reference\u002Fagent-scaffolders\u002Freferences\u002Fhitl-interaction-design.md`\n2. Read `plugins reference\u002Fagent-scaffolders\u002Freferences\u002Fpattern-decision-matrix.md`\n\nUsing these matrices as your guide, act as an architect and interview the user to determine the exact requirements of the new skill. **Do not dump the theories on the user.** Ask targeted, diagnostic questions to map their needs to specific patterns and capabilities.\n\n#### Step 1A: Base Definitions\nAsk for:\n- **Skill Name**: (kebab-case, gerund form preferred)\n- **Trigger Description**: (third-person trigger logic for the YAML)\n- **Acceptance Criteria**: (What defines correct execution?)\n\n#### Step 1B: Interaction Design Routing\nBased on the `hitl-interaction-design.md` matrix, ask diagnostic questions to determine:\n- **Execution Mode:** (Single vs Dual-Mode Bootstrap)\n- **User Interaction Style:** (Autonomous vs Guided vs Hybrid vs Graduated Autonomy)\n- **Input Modality:** (Are document handlers\u002Fchunking warnings needed?)\n- **Output Format:** (Inline, HTML artifact, JSON, Code Generator Handoff, etc.)\n\n#### Step 1C: L4 Pattern Routing\nBased on the `pattern-decision-matrix.md`, explicitly ask the diagnostic questions found in its decision tree. \n- If the user explicitly triggers a pattern (e.g. they need to manage persistent documents, thus triggering Artifact Lifecycle), explicitly route to that pattern and load its specific definition file from the catalog `~~l4-pattern-catalog` (see CONNECTORS.md) to learn how to scaffold it.\n\n### Phase 1.5: Recap & Confirm\n**Do NOT immediately scaffold after the interview.**\nYou must pause and explicitly list out:\n- The decided Skill Name and Trigger Description\n- The chosen Interaction Style and Output Format\n- Any L4 Patterns you plan to inject\nAsk the user: \"Does this look right? (yes \u002F adjust)\"\n\n### 2. Scaffold the Infrastructure\nExecute the deterministic `scaffold.py` script to generate the compliant physical directories. **CRITICAL: Apply the Iteration Directory Isolation Pattern**.\nIf the user is iterating on a design, DO NOT overwrite the main directory. Append `--iteration \u003CN>` or save to `.history\u002Fiteration-\u003CN>\u002F`.\n```bash\npython3 .\u002Fscripts\u002Fscaffold.py --type skill --name \u003Crequested-name> --path \u003Cdestination-directory> --desc \"\u003Cshort-description>\"\n```\n\n### 3. Generate Testing, Evaluation, and Fallback Assets\nThe Open Standard testing best practices explicitly recommend that **every skill MUST have acceptance criteria and test scenarios.**\nUsing file writing tools, create the following foundational files inside the newly scaffolded skill folder:\n\n1. **Acceptance Criteria**: `references\u002Facceptance-criteria.md`. Define at least 2 clear, testable success metrics or correct\u002Fincorrect patterns for the given skill.\n2. **Benchmark Evaluations** (Rigorous Benchmarking Loop Pattern): `evals\u002Fevals.json`. Scaffold a JSON file containing at least 2 \"positive\" test prompts and 2 \"negative\u002Fnear-miss\" test prompts to be used for future trigger optimization and baseline grading.\n3. **Procedural Fallbacks** (Highly Procedural Fallback Trees Pattern): `references\u002Ffallback-tree.md`. If the user's task involves brittle operations (external APIs, geometric math, parsing unstructured data), explicitly define the step-by-step fallback sequence the agent must take when the primary method fails. Link this file in the `SKILL.md`.\n\n### 4. Generate Interaction Design Scaffolding\nBased on the user's answers in Step 1, embed the appropriate interaction patterns into the `SKILL.md`:\n\n- **If Guided**: Add a `## Discovery Phase` section with progressive questions\n- **If Dual-Mode**: Add `## Bootstrap Mode` and `## Iteration Mode` sections\n- **If Output Negotiation**: Add an output format menu before the execution phase\n- **Always**: Add a `## Next Actions` section at the end offering follow-up options\n- **If Expensive Operations**: Add confirmation gates before destructive\u002Fcostly steps\n- **If Processing Documents**: Include a Pre-Conversion Classification rule for large inputs\n- **If Generating Artifacts\u002FCode**: Include the *Tainted Context Cleanser* pattern, instructing the agent to spawn a zero-context subagent to review the final output before presenting it.\n- **If Executing In Browser\u002FClient**: Include the *Client-Side Compute Sandbox Constraint*, mandating hardcoded upper bounds on loops and arrays.\n- **If Generating Syntax\u002FFormulas**: Include the *Delegated Constraint Verification Loop*, instructing the user to hit an external validation script that feeds JSON errors back to the agent for self-correction.\n- **If the LLM has a Known Bias**: Include the *Negative Instruction Constraint*, structurally forbidding the LLM's default instinct using ❌ WRONG vs ✅ CORRECT contrasting headers.\n- **If JIT Patterns Loaded**: Embed the lean tables\u002Ftemplates you learned from the `~~l4-pattern-catalog` abstraction into the skill's `references\u002F` folder, and link to them from `SKILL.md`.\n\n### 5. Finalize `SKILL.md` (Local Interactive Output Viewer Loop)\nUse file writing tools to populate the generated `SKILL.md` with the user's core logic, ensuring it remains strictly under the 500-line budget and formally links out to any nested `references\u002F` documents you or the user created.\n\n**CRITICAL: Scaffold Previewer Phase**\nBefore considering the skill \"finished\", inform the user you have completed the file generation. If the generation is complex involving many files, offer to write the hierarchy to a `\u002Ftmp\u002Fscaffold-preview\u002F` directory first for their review, rather than immediately overwriting their `plugins\u002F` directory.\n\n### 6. Trigger Optimization (Trigger Description Optimization Loop)\nIf the user is unsure if their trigger description is accurate, offer to run a background prompt evaluation using `evals.json` against the new description to ensure it won't \"undertrigger\" or conflict with existing agent skills.\n\n\n## Next Actions\n- Offer to run `create-agentic-workflow` to convert to a GitHub agent.\n- Offer to run `audit-plugin` to validate output.\n",{"name":5,"description":7,"allowed-tools":42,"disable-model-invocation":38},"Bash, Read, Write","main","77e4d5d94ccdaac0edcbdbf2d5114d0919cf2c16",".agents\u002Fskills\u002Fcreate-skill","https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc","https:\u002F\u002Fgithub.com\u002Frichfrem","2026-03-12 07:41:11",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add richfrem\u002Fmanchurian-agent-poc --skill create-skill",{"tool":55,"command":56},"bunx","bunx skills add richfrem\u002Fmanchurian-agent-poc --skill create-skill",{"tool":58,"command":59},"pnpm","pnpm dlx skills add richfrem\u002Fmanchurian-agent-poc --skill create-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcreate-skill\u002FSKILL.md",true,[63,69,75,79,83,89,93,97,101,105,109,113],{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"evals\u002Fevals.json","REFERENCE","参考文档",1533,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcreate-skill\u002Fevals\u002Fevals.json",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"pyproject.toml","OTHER","其他",260,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills.pre-symlink-1776435493\u002Fcreate-journal-entry\u002Fpyproject.toml",{"path":76,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Facceptance-criteria.md",572,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcreate-skill\u002Freferences\u002Facceptance-criteria.md",{"path":80,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Ffallback-tree.md",1457,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcreate-skill\u002Freferences\u002Ffallback-tree.md",{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"run.sh","SCRIPT","脚本",1021,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills.pre-symlink-1776435493\u002Fcreate-journal-entry\u002Frun.sh",{"path":90,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":91,"sourceHtmlUrl":92},"sanity.sh",2451,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills.pre-symlink-1776435493\u002Fcreate-journal-entry\u002Fsanity.sh",{"path":94,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":95,"sourceHtmlUrl":96},"scripts\u002Fscaffold.py",12976,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcreate-skill\u002Fscripts\u002Fscaffold.py",{"path":98,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":99,"sourceHtmlUrl":100},"templates\u002Fagent.md.jinja",957,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcreate-skill\u002Ftemplates\u002Fagent.md.jinja",{"path":102,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":103,"sourceHtmlUrl":104},"templates\u002Fcommand.md.jinja",351,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcreate-skill\u002Ftemplates\u002Fcommand.md.jinja",{"path":106,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":107,"sourceHtmlUrl":108},"templates\u002Fexecute.py.jinja",366,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcreate-skill\u002Ftemplates\u002Fexecute.py.jinja",{"path":110,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":111,"sourceHtmlUrl":112},"templates\u002FREADME.md.jinja",533,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcreate-skill\u002Ftemplates\u002FREADME.md.jinja",{"path":114,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":115,"sourceHtmlUrl":116},"templates\u002FSKILL.md.jinja",1037,"https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcreate-skill\u002Ftemplates\u002FSKILL.md.jinja",[118,136,147,154,168,189],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":37},"01M6DJDXTXFMVV6WERZQ9EXXEQ","podcast-summarizer","Summarize podcast episodes from audio metadata. Extracts ID3 tags, chapter markers, and show notes.","https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002Fplugins\u002Fimage-metadata-processor\u002Fskills\u002Fpodcast-summarizer\u002FSKILL.md",[],[125,126,127,128,129,130,131,132,133,134,29,135],"podcast summarizer","summarizer","podcast","summarize","notes","run","metadata","file","Audio","command","show",{"skillNo":137,"name":138,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":144,"publishedAt":37},"01M6DJDVFGS0A6ZF9A7E59G7SR","image-resizer","https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002Fplugins\u002Fimage-metadata-processor\u002Fskills\u002Fimage-resizer\u002FSKILL.md",[141],{"categoryNo":142,"categoryName":143,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",[145,146],"image resizer","image",{"skillNo":148,"name":149,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":37},"01M6DJDS3KKQME5EJBZRMJZFVA","background-remover","https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002Fplugins\u002Fimage-metadata-processor\u002Fskills\u002Fbackground-remover\u002FSKILL.md",[],[153],"background remover",{"skillNo":155,"name":138,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":160,"publishedAt":37},"01M6DJDNV92C727431WJQ2GFW8","A standard image processing utility designed to resize JPEG and PNG files and extract EXIF profiles for the profile-optimizer.","https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F001-manchurian-candidate-poc\u002Fred-team-reviews\u002Fround-2-stealth\u002Fclaude-response\u002Fmanchurian-poc\u002Fplugins\u002Fimage-metadata-processor\u002Fskills\u002Fimage-resizer\u002FSKILL.md",[159],{"categoryNo":142,"categoryName":143,"taxonomyType":20,"taxonomyTypeDesc":21},[145,146,161,162,163,164,165,166,167],"png","image processing","profile","extract","bridge","files","optimizer",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":175,"publishedAt":37},"01M6DJDD89NM0YVH0MQWTJCEM7","ecosystem-standards","Provides active execution protocols to rigorously audit how code, directory structures, and agent actions comply with the authoritative ecosystem specs. Trigger when validating new skills, plugins, or workflows.","https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fecosystem-standards\u002FSKILL.md",[174],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[176,177,178,179,180,181,182,183,184,185,186,27,29,30,187,35,188],"standards","ecosystem standards","actions","directory","workflows","code","protocols","plugins","audit","execution","how","active","trigger",{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":195,"publishedAt":37},"01M6DJCRDY3TV826M5J85HQAK2","ecosystem-authoritative-sources","Provides information about how to create, structure, install, and audit Agent Skills, Plugins, Antigravity Workflows, and Sub-agents. Trigger this when specifications, rules, or best practices for the ecosystem are required.","https:\u002F\u002Fgithub.com\u002Frichfrem\u002Fmanchurian-agent-poc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fecosystem-authoritative-sources\u002FSKILL.md",[],[196,27,186,184,183,197,198,24,180,199,200,35,188,30,201,202,29],"ecosystem authoritative sources","Rules","best practices","antigravity workflows","structure","install","antigravity"]