[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DB1MZHK4VC1F2CP3TKDYF6":3,"skill-same:01M6DB1MZHK4VC1F2CP3TKDYF6":93},{"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":31,"publishedAt":52,"linkOnly":53,"markdownContent":54,"markdownBody":55,"frontMatter":56,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":14,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":62,"install":63,"resources":76},"01M6DB1MZHK4VC1F2CP3TKDYF6","autofix-bot-api",null,"Use when scanning a repository or code change for security vulnerabilities, leaked secrets, or dependency issues via the Autofix Bot API (api.autofix.bot) and auto-applying detected fixes; requires AUTOFIX_BOT_API_KEY ; do NOT use for general code review without an Autofix Bot account ; returns findings report and applied-fix summary.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fautofix-bot-api\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"bot","autofix bot api","api","fix","code review","summary","do","general","dependency","scanning","auto","use","vulnerabilities","secrets","review","repository","issues","report","code","change","2026-11-10 10:12:30",false,"---\nname: autofix-bot-api\ndescription: Use when scanning a repository or code change for security vulnerabilities, leaked secrets, or dependency issues via the Autofix Bot API (api.autofix.bot) and auto-applying detected fixes; requires AUTOFIX_BOT_API_KEY ; do NOT use for general code review without an Autofix Bot account ; returns findings report and applied-fix summary.\n---\n\n# Autofix Bot API\n\nScan code for security vulnerabilities, secrets, and dependency issues via the Autofix Bot REST API, and auto-fix detected issues.\n\n## Authentication\n\nAll API calls require a Bearer token. Read the key from the `AUTOFIX_BOT_API_KEY` environment variable:\n\n```bash\ncurl https:\u002F\u002Fapi.autofix.bot\u002Fworkspace \\\n  -H \"Authorization: Bearer $AUTOFIX_BOT_API_KEY\"\n```\n\nIf the key is not set, ask the user to provide it. Never hardcode API keys or pass them as command-line arguments. All bundled scripts read from this environment variable automatically.\n\n## Workflow\n\n### Step 1: Create a repository\n\n```bash\ncurl -X POST https:\u002F\u002Fapi.autofix.bot\u002Frepositories \\\n  -H \"Authorization: Bearer $AUTOFIX_BOT_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"name\": \"my-repo\",\n    \"external_id\": \"local:my-repo\",\n    \"detection\": [\"security\", \"secrets\"],\n    \"fix\": [\"security\", \"secrets\"]\n  }'\n```\n\nSave the returned `id` (e.g., `repo_...`). Use `external_id` to avoid duplicates — if a repo with the same `external_id` exists, retrieve it with `GET \u002Frepositories\u002Fexternal:local:my-repo` instead.\n\n### Step 2: Sync code\n\nUse the bundled `scripts\u002Fsync_repo.sh` script:\n\n```bash\n# Full sync (first time)\n.\u002Fscripts\u002Fsync_repo.sh \u002Fpath\u002Fto\u002Frepo \u003Crepo_id>\n\n# Incremental sync (subsequent updates)\n.\u002Fscripts\u002Fsync_repo.sh \u002Fpath\u002Fto\u002Frepo \u003Crepo_id> \u003Cbase_ref>\n```\n\nThe script creates a git bundle, obtains a signed upload URL, uploads the bundle, and polls until sync completes. It outputs the sync ID on success.\n\n**Manual sync steps** (if not using the script):\n\n1. Create a git bundle:\n   ```bash\n   # Full\n   git bundle create repo.bundle --all\n   # Incremental from a base ref\n   git bundle create repo.bundle \u003Cbase_ref>..HEAD\n   ```\n\n2. Create a sync: `POST \u002Frepositories\u002F{id}\u002Fsyncs` with `{\"type\": \"full\"}` or `{\"type\": \"incremental\", \"base_ref\": \"\u003Cref>\"}`\n\n3. Upload the bundle to the `upload_url` from the response:\n   ```bash\n   curl -X PUT \"\u003Cupload_url>\" -H \"Content-Type: application\u002Foctet-stream\" --data-binary @repo.bundle\n   ```\n\n4. Poll `GET \u002Frepositories\u002F{id}\u002Fsyncs\u002F{sync_id}` until `status` is `completed`.\n\n### Step 3: Run analysis\n\n```bash\ncurl -X POST https:\u002F\u002Fapi.autofix.bot\u002Fanalysis \\\n  -H \"Authorization: Bearer $AUTOFIX_BOT_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"type\": \"repository\",\n    \"repository_id\": \"\u003Crepo_id>\",\n    \"from_ref\": \"\u003Ccommit_sha>\"\n  }'\n```\n\n- `from_ref` (required): the git commit\u002Fref to analyze from. Use the full SHA of HEAD for a full scan.\n- `to_ref` (optional): end ref for analyzing a range of changes.\n- `patch` (optional): git patch to apply before analysis. Mutually exclusive with `to_ref`.\n\n### Step 4: Poll for results\n\nUse the bundled `scripts\u002Fpoll_analysis.sh` script:\n\n```bash\nRESULT=$(.\u002Fscripts\u002Fpoll_analysis.sh \u003Canalysis_id>)\n```\n\nOr poll manually: `GET \u002Fanalysis\u002F{id}` until `status` is `completed`.\n\n### Step 5: Inspect results and apply fixes\n\nThe completed analysis contains:\n\n- `detection_result.issues` — list of detected issues with file, position, explanation, category\n- `fix_result.patch` — unified diff patch that fixes the detected issues\n- `fix_result.fixes` — individual fixes with explanations\n\n**Apply the fix patch:**\n\n```bash\necho \"$FIX_PATCH\" | git apply\n```\n\nIf only the first 50 issues\u002Ffixes are returned (`has_more: true`), paginate with:\n- `GET \u002Fanalysis\u002F{id}\u002Fissues?limit=100`\n- `GET \u002Fanalysis\u002F{id}\u002Ffixes?limit=100`\n\n## Detection Categories\n\n| Category | Description |\n|----------|-------------|\n| `security` | Code vulnerabilities (injection, XSS, unsafe deserialization, etc.) |\n| `secrets` | Leaked credentials, API keys, tokens in source code |\n| `dependencies` | Vulnerable dependencies |\n\nDefault detection: `[\"security\", \"secrets\"]`. Set per-repository or per-analysis.\n\n## Key Patterns\n\n**Reuse repositories**: Look up existing repos by external_id (`GET \u002Frepositories\u002Fexternal:\u003Cexternal_id>`) before creating new ones.\n\n**Incremental syncs**: After the first full sync, use incremental syncs with `base_ref` set to the last synced commit for faster uploads.\n\n**Idempotency**: Send `Idempotency-Key` header on create operations for safe retries.\n\n**Ref for full scan**: To scan the entire repo, set `from_ref` to the root commit or the HEAD commit SHA after syncing.\n\n## API Reference\n\nFor detailed endpoint documentation, request\u002Fresponse schemas, pagination, and error codes, see [references\u002Fapi-reference.md](references\u002Fapi-reference.md).\n","# Autofix Bot API\n\nScan code for security vulnerabilities, secrets, and dependency issues via the Autofix Bot REST API, and auto-fix detected issues.\n\n## Authentication\n\nAll API calls require a Bearer token. Read the key from the `AUTOFIX_BOT_API_KEY` environment variable:\n\n```bash\ncurl https:\u002F\u002Fapi.autofix.bot\u002Fworkspace \\\n  -H \"Authorization: Bearer $AUTOFIX_BOT_API_KEY\"\n```\n\nIf the key is not set, ask the user to provide it. Never hardcode API keys or pass them as command-line arguments. All bundled scripts read from this environment variable automatically.\n\n## Workflow\n\n### Step 1: Create a repository\n\n```bash\ncurl -X POST https:\u002F\u002Fapi.autofix.bot\u002Frepositories \\\n  -H \"Authorization: Bearer $AUTOFIX_BOT_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"name\": \"my-repo\",\n    \"external_id\": \"local:my-repo\",\n    \"detection\": [\"security\", \"secrets\"],\n    \"fix\": [\"security\", \"secrets\"]\n  }'\n```\n\nSave the returned `id` (e.g., `repo_...`). Use `external_id` to avoid duplicates — if a repo with the same `external_id` exists, retrieve it with `GET \u002Frepositories\u002Fexternal:local:my-repo` instead.\n\n### Step 2: Sync code\n\nUse the bundled `scripts\u002Fsync_repo.sh` script:\n\n```bash\n# Full sync (first time)\n.\u002Fscripts\u002Fsync_repo.sh \u002Fpath\u002Fto\u002Frepo \u003Crepo_id>\n\n# Incremental sync (subsequent updates)\n.\u002Fscripts\u002Fsync_repo.sh \u002Fpath\u002Fto\u002Frepo \u003Crepo_id> \u003Cbase_ref>\n```\n\nThe script creates a git bundle, obtains a signed upload URL, uploads the bundle, and polls until sync completes. It outputs the sync ID on success.\n\n**Manual sync steps** (if not using the script):\n\n1. Create a git bundle:\n   ```bash\n   # Full\n   git bundle create repo.bundle --all\n   # Incremental from a base ref\n   git bundle create repo.bundle \u003Cbase_ref>..HEAD\n   ```\n\n2. Create a sync: `POST \u002Frepositories\u002F{id}\u002Fsyncs` with `{\"type\": \"full\"}` or `{\"type\": \"incremental\", \"base_ref\": \"\u003Cref>\"}`\n\n3. Upload the bundle to the `upload_url` from the response:\n   ```bash\n   curl -X PUT \"\u003Cupload_url>\" -H \"Content-Type: application\u002Foctet-stream\" --data-binary @repo.bundle\n   ```\n\n4. Poll `GET \u002Frepositories\u002F{id}\u002Fsyncs\u002F{sync_id}` until `status` is `completed`.\n\n### Step 3: Run analysis\n\n```bash\ncurl -X POST https:\u002F\u002Fapi.autofix.bot\u002Fanalysis \\\n  -H \"Authorization: Bearer $AUTOFIX_BOT_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"type\": \"repository\",\n    \"repository_id\": \"\u003Crepo_id>\",\n    \"from_ref\": \"\u003Ccommit_sha>\"\n  }'\n```\n\n- `from_ref` (required): the git commit\u002Fref to analyze from. Use the full SHA of HEAD for a full scan.\n- `to_ref` (optional): end ref for analyzing a range of changes.\n- `patch` (optional): git patch to apply before analysis. Mutually exclusive with `to_ref`.\n\n### Step 4: Poll for results\n\nUse the bundled `scripts\u002Fpoll_analysis.sh` script:\n\n```bash\nRESULT=$(.\u002Fscripts\u002Fpoll_analysis.sh \u003Canalysis_id>)\n```\n\nOr poll manually: `GET \u002Fanalysis\u002F{id}` until `status` is `completed`.\n\n### Step 5: Inspect results and apply fixes\n\nThe completed analysis contains:\n\n- `detection_result.issues` — list of detected issues with file, position, explanation, category\n- `fix_result.patch` — unified diff patch that fixes the detected issues\n- `fix_result.fixes` — individual fixes with explanations\n\n**Apply the fix patch:**\n\n```bash\necho \"$FIX_PATCH\" | git apply\n```\n\nIf only the first 50 issues\u002Ffixes are returned (`has_more: true`), paginate with:\n- `GET \u002Fanalysis\u002F{id}\u002Fissues?limit=100`\n- `GET \u002Fanalysis\u002F{id}\u002Ffixes?limit=100`\n\n## Detection Categories\n\n| Category | Description |\n|----------|-------------|\n| `security` | Code vulnerabilities (injection, XSS, unsafe deserialization, etc.) |\n| `secrets` | Leaked credentials, API keys, tokens in source code |\n| `dependencies` | Vulnerable dependencies |\n\nDefault detection: `[\"security\", \"secrets\"]`. Set per-repository or per-analysis.\n\n## Key Patterns\n\n**Reuse repositories**: Look up existing repos by external_id (`GET \u002Frepositories\u002Fexternal:\u003Cexternal_id>`) before creating new ones.\n\n**Incremental syncs**: After the first full sync, use incremental syncs with `base_ref` set to the last synced commit for faster uploads.\n\n**Idempotency**: Send `Idempotency-Key` header on create operations for safe retries.\n\n**Ref for full scan**: To scan the entire repo, set `from_ref` to the root commit or the HEAD commit SHA after syncing.\n\n## API Reference\n\nFor detailed endpoint documentation, request\u002Fresponse schemas, pagination, and error codes, see [references\u002Fapi-reference.md](references\u002Fapi-reference.md).\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fautofix-bot-api","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill autofix-bot-api",{"tool":69,"command":70},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill autofix-bot-api",{"tool":72,"command":73},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill autofix-bot-api","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fautofix-bot-api\u002FSKILL.md",true,[77,83,89],{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fapi-reference.md","REFERENCE","参考文档",7871,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fautofix-bot-api\u002Freferences\u002Fapi-reference.md",{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"scripts\u002Fpoll_analysis.sh","SCRIPT","脚本",1429,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fautofix-bot-api\u002Fscripts\u002Fpoll_analysis.sh",{"path":90,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":91,"sourceHtmlUrl":92},"scripts\u002Fsync_repo.sh",3529,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fautofix-bot-api\u002Fscripts\u002Fsync_repo.sh",[94,114,142,168,180,196],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":52},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[101,102,103,104,105,106,107,108,41,43,109,110,111,112,113],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","context","repo","injection","execution","file",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":123,"publishedAt":52},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[120],{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[124,125,126,127,128,129,130,131,132,133,134,135,136,137,43,138,139,140,38,141],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","MCP",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":154,"publishedAt":52},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[148,151],{"categoryNo":149,"categoryName":150,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":152,"categoryName":153,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[46,155,156,157,158,159,160,161,162,163,125,164,165,166,167],"visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":174,"publishedAt":52},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[170,175,49,176,177,178,48,179],"setup","project","installation","project setup","state",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":187,"publishedAt":52},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[186],{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},[182,188,106,189,190,191,43,192,193,194,195],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":197,"name":175,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":201,"publishedAt":52},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[175,176,140,202,178,203],"files","interactive"]