[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73HMHYTN35W3XP0HC93GSXD":3,"skill-same:01M73HMHYTN35W3XP0HC93GSXD":61},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":38,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M73HMHYTN35W3XP0HC93GSXD","pacsomatic",null,"Prepares and launches nf-core\u002Fpacsomatic matched tumor-normal PacBio HiFi genomics workflows from unaligned BAM inputs. Supports samplesheet generation, pinned Nextflow launch artifacts, local checks, LSF\u002FSlurm\u002FPBS Pro\u002FSGE launcher submission, and startup troubleshooting. Use for pacsomatic run preparation and execution, not general short-read somatic analysis or medical imaging PACS.","bg-szy\u002FTOP-SKILLS","bg-szy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F106576190?v=4","01M73A4E8KPV67SFXRY8XZGNBX","ShuZhiyong","01M73A4E96MQ294MHM74TZBVQD",6,"MIT","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fawesome-skills\u002Fpacsomatic\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fawesome-skills\u002Fpacsomatic\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: pacsomatic\ndescription: Prepares and launches nf-core\u002Fpacsomatic matched tumor-normal PacBio HiFi genomics workflows from unaligned BAM inputs. Supports samplesheet generation, pinned Nextflow launch artifacts, local checks, LSF\u002FSlurm\u002FPBS Pro\u002FSGE launcher submission, and startup troubleshooting. Use for pacsomatic run preparation and execution, not general short-read somatic analysis or medical imaging PACS.\nlicense: MIT\ncompatibility: Requires Python 3.10+ for the standard-library helper. Execution requires Bash, Nextflow >=24.04.2, a compatible Java runtime (current Nextflow supports Java 17-26), the selected container runtime and optionally a scheduler. Network access is needed for uncached pipeline code, plugins, references and containers.\nmetadata:\n  version: \"1.4\"\n  skill-author: Beifang Niu\n  contributors: Haidong, Wenchao\n  upstream-pipeline: https:\u002F\u002Fgithub.com\u002Fnf-core\u002Fpacsomatic\n  upstream-revision: \"24c84cb371b0339c1d65a4de9451671945e19772\"\n  last-reviewed: \"2026-10-01\"\n---\n\n# pacsomatic\n\n## When to use\n\nUse [scripts\u002Frun_pacsomatic.py](scripts\u002Frun_pacsomatic.py) to prepare one matched\nPacBio HiFi tumor\u002Fnormal pair, generate a samplesheet and reproducible launch\nartifacts, and launch locally or submit the **Nextflow driver** to a scheduler.\nThe pipeline realigns input BAMs; this helper targets unaligned HiFi BAMs and\noptional PacBio `.pbi` indexes. Do not substitute short reads or treat a BAM\nfilename as evidence of platform, matched identity, or methylation information.\n\nThe reviewed upstream `dev` commit is\n`24c84cb371b0339c1d65a4de9451671945e19772`. GitHub had no releases or tags on\n2026-10-01, despite the internal manifest saying `1.0.0`. The helper pins that\ncommit by default for `nf-core\u002Fpacsomatic`; it does not invent a release tag.\nThis is a source-reviewed development workflow, not a clinically validated assay.\nSee [references\u002Fpacsomatic_guide.md](references\u002Fpacsomatic_guide.md) for sources\nand scientific checks.\n\n## Workflow\n\n1. Obtain distinct tumor and normal BAM paths, patient ID, distinct sample IDs,\n   output directory, and exactly one reference mode: `--fasta` or `--genome`.\n   IDs and BAM\u002FPBI\u002FFASTA paths must have no whitespace. Local inputs must be\n   nonempty regular files. Remote BAM\u002FPBI\u002FFASTA URIs are passed through without\n   downloading or authenticating; use managed filesystem\u002Fcloud credentials,\n   never embed secrets or signed URLs in generated files.\n2. Confirm PacBio HiFi read groups and sample identity from acquisition metadata;\n   confirm that MM\u002FML modification tags needed for methylation have been retained.\n   Verify reference sequence\u002Fcontig compatibility for every annotation resource.\n3. Generate artifacts with `--dry-run`. This performs helper checks and writes\n   files, but does **not** invoke the pipeline, validate BAM contents, check remote\n   availability, resolve every pipeline parameter, or verify biological suitability.\n   Missing runtime tools are warnings here. `--dry-run` cannot be combined with\n   `--run`\u002F`--submit`, cloning, or environment creation.\n4. Review samplesheet, generated params YAML, script, pipeline revision, profiles,\n   and branch-specific resources\u002Fskips. Existing artifacts require explicit\n   `--overwrite`; input files can never be artifact targets. `config.yaml` is an\n   operator reference, not an automatically loaded configuration file.\n5. For execution, select the actual runtime with `--use-current-path` or an\n   existing `--conda-env`. Load cluster modules **before** invoking the helper;\n   `--module-load` only repeats those commands in the generated script. No Conda\n   YAML is bundled; creating an environment needs `--conda-env-file` explicitly.\n6. Use `--run` only for requested execution. For HPC, distinguish the outer\n   launcher scheduler (`--executor`) from Nextflow's per-task `process.executor`,\n   configured by a site profile or `--nextflow-config`. Driver CPU\u002Fmemory requests\n   do not constrain task resources. Read [references\u002Fconfig-and-output.md](references\u002Fconfig-and-output.md).\n7. Report artifact paths, revision, checks\u002Fwarnings, run type, submission ID if\n   present, and a concrete next QC or failure-triage step. Scheduler acceptance\n   is not pipeline completion. Keep the output directory and work\u002Fcache state\n   stable for `--resume`; scripts run with the output directory as their cwd.\n\n## Examples\n\nRun these from the repository root. Paths and site settings are **illustrative**;\nlocal tests use synthetic placeholders only, not human genomic data.\n\n```bash\npython skills\u002Fpacsomatic\u002Fscripts\u002Frun_pacsomatic.py \\\n  --tumor-bam \u002Fdata\u002FP001_T.bam --normal-bam \u002Fdata\u002FP001_N.bam \\\n  --patient-id P001 --tumor-sample-id P001_T --normal-sample-id P001_N \\\n  --outdir \u002Fresults\u002FP001 --fasta \u002Frefs\u002FGRCh38.fa \\\n  --profile apptainer --use-current-path --dry-run\n```\n\nAfter reviewing artifacts, a Slurm launch can use the same inputs plus the\nfollowing options (replace `--dry-run` with `--run`):\n\n```text\n--executor slurm --queue compute --project my_account\n--cpus 2 --memory-gb 8 --walltime 48:00\n--nextflow-config \u002Fconfigs\u002Fslurm.config --overwrite --run\n```\n\nThose resources are for the driver, assuming the reviewed infrastructure config\nsets `process.executor = 'slurm'` and suitable task queue\u002Fresources. The helper\nnormalizes `48:00` to Slurm `48:00:00` (48 hours). Do not add a `sanger` profile\nunless actually using that institution's LSF infrastructure.\n\nCustom pipeline parameters go in `--params-file`; infrastructure goes in\n`--nextflow-config` (`-c`). The helper's explicit input\u002Foutdir\u002Freference options\nwin over params-file values. `--extra-args` is tokenized and shell-quoted, but\ncannot override these managed inputs\u002Fconfiguration options. Keep paths inside\nexternal params\u002Fconfig files absolute because the launcher cwd is the outdir.\n\n## Verification and references\n\n```bash\nuv run skills-ref validate skills\u002Fpacsomatic\npython tests\u002Frun_all.py --isolated pacsomatic\n```\n\nThe standard-library suite checks local artifact behavior, path protections,\nCLI modes, runtime failures and mocked scheduler submissions. Native Nextflow\nchecks use a tiny local workflow; they do not establish that pacsomatic's full\ncontainerized scientific pipeline succeeds on a given dataset or cluster.\n\n- [Operator playbook](references\u002Fagent-playbook.md)\n- [Configuration, scheduler and output contracts](references\u002Fconfig-and-output.md)\n- [Upstream sources and scientific checks](references\u002Fpacsomatic_guide.md)\n","# pacsomatic\n\n## When to use\n\nUse [scripts\u002Frun_pacsomatic.py](scripts\u002Frun_pacsomatic.py) to prepare one matched\nPacBio HiFi tumor\u002Fnormal pair, generate a samplesheet and reproducible launch\nartifacts, and launch locally or submit the **Nextflow driver** to a scheduler.\nThe pipeline realigns input BAMs; this helper targets unaligned HiFi BAMs and\noptional PacBio `.pbi` indexes. Do not substitute short reads or treat a BAM\nfilename as evidence of platform, matched identity, or methylation information.\n\nThe reviewed upstream `dev` commit is\n`24c84cb371b0339c1d65a4de9451671945e19772`. GitHub had no releases or tags on\n2026-10-01, despite the internal manifest saying `1.0.0`. The helper pins that\ncommit by default for `nf-core\u002Fpacsomatic`; it does not invent a release tag.\nThis is a source-reviewed development workflow, not a clinically validated assay.\nSee [references\u002Fpacsomatic_guide.md](references\u002Fpacsomatic_guide.md) for sources\nand scientific checks.\n\n## Workflow\n\n1. Obtain distinct tumor and normal BAM paths, patient ID, distinct sample IDs,\n   output directory, and exactly one reference mode: `--fasta` or `--genome`.\n   IDs and BAM\u002FPBI\u002FFASTA paths must have no whitespace. Local inputs must be\n   nonempty regular files. Remote BAM\u002FPBI\u002FFASTA URIs are passed through without\n   downloading or authenticating; use managed filesystem\u002Fcloud credentials,\n   never embed secrets or signed URLs in generated files.\n2. Confirm PacBio HiFi read groups and sample identity from acquisition metadata;\n   confirm that MM\u002FML modification tags needed for methylation have been retained.\n   Verify reference sequence\u002Fcontig compatibility for every annotation resource.\n3. Generate artifacts with `--dry-run`. This performs helper checks and writes\n   files, but does **not** invoke the pipeline, validate BAM contents, check remote\n   availability, resolve every pipeline parameter, or verify biological suitability.\n   Missing runtime tools are warnings here. `--dry-run` cannot be combined with\n   `--run`\u002F`--submit`, cloning, or environment creation.\n4. Review samplesheet, generated params YAML, script, pipeline revision, profiles,\n   and branch-specific resources\u002Fskips. Existing artifacts require explicit\n   `--overwrite`; input files can never be artifact targets. `config.yaml` is an\n   operator reference, not an automatically loaded configuration file.\n5. For execution, select the actual runtime with `--use-current-path` or an\n   existing `--conda-env`. Load cluster modules **before** invoking the helper;\n   `--module-load` only repeats those commands in the generated script. No Conda\n   YAML is bundled; creating an environment needs `--conda-env-file` explicitly.\n6. Use `--run` only for requested execution. For HPC, distinguish the outer\n   launcher scheduler (`--executor`) from Nextflow's per-task `process.executor`,\n   configured by a site profile or `--nextflow-config`. Driver CPU\u002Fmemory requests\n   do not constrain task resources. Read [references\u002Fconfig-and-output.md](references\u002Fconfig-and-output.md).\n7. Report artifact paths, revision, checks\u002Fwarnings, run type, submission ID if\n   present, and a concrete next QC or failure-triage step. Scheduler acceptance\n   is not pipeline completion. Keep the output directory and work\u002Fcache state\n   stable for `--resume`; scripts run with the output directory as their cwd.\n\n## Examples\n\nRun these from the repository root. Paths and site settings are **illustrative**;\nlocal tests use synthetic placeholders only, not human genomic data.\n\n```bash\npython skills\u002Fpacsomatic\u002Fscripts\u002Frun_pacsomatic.py \\\n  --tumor-bam \u002Fdata\u002FP001_T.bam --normal-bam \u002Fdata\u002FP001_N.bam \\\n  --patient-id P001 --tumor-sample-id P001_T --normal-sample-id P001_N \\\n  --outdir \u002Fresults\u002FP001 --fasta \u002Frefs\u002FGRCh38.fa \\\n  --profile apptainer --use-current-path --dry-run\n```\n\nAfter reviewing artifacts, a Slurm launch can use the same inputs plus the\nfollowing options (replace `--dry-run` with `--run`):\n\n```text\n--executor slurm --queue compute --project my_account\n--cpus 2 --memory-gb 8 --walltime 48:00\n--nextflow-config \u002Fconfigs\u002Fslurm.config --overwrite --run\n```\n\nThose resources are for the driver, assuming the reviewed infrastructure config\nsets `process.executor = 'slurm'` and suitable task queue\u002Fresources. The helper\nnormalizes `48:00` to Slurm `48:00:00` (48 hours). Do not add a `sanger` profile\nunless actually using that institution's LSF infrastructure.\n\nCustom pipeline parameters go in `--params-file`; infrastructure goes in\n`--nextflow-config` (`-c`). The helper's explicit input\u002Foutdir\u002Freference options\nwin over params-file values. `--extra-args` is tokenized and shell-quoted, but\ncannot override these managed inputs\u002Fconfiguration options. Keep paths inside\nexternal params\u002Fconfig files absolute because the launcher cwd is the outdir.\n\n## Verification and references\n\n```bash\nuv run skills-ref validate skills\u002Fpacsomatic\npython tests\u002Frun_all.py --isolated pacsomatic\n```\n\nThe standard-library suite checks local artifact behavior, path protections,\nCLI modes, runtime failures and mocked scheduler submissions. Native Nextflow\nchecks use a tiny local workflow; they do not establish that pacsomatic's full\ncontainerized scientific pipeline succeeds on a given dataset or cluster.\n\n- [Operator playbook](references\u002Fagent-playbook.md)\n- [Configuration, scheduler and output contracts](references\u002Fconfig-and-output.md)\n- [Upstream sources and scientific checks](references\u002Fpacsomatic_guide.md)\n",{"name":5,"license":15,"metadata":25,"description":7,"compatibility":32},{"version":26,"contributors":27,"skill-author":28,"last-reviewed":29,"upstream-pipeline":30,"upstream-revision":31},"1.4","Haidong, Wenchao","Beifang Niu","2026-10-01","https:\u002F\u002Fgithub.com\u002Fnf-core\u002Fpacsomatic","24c84cb371b0339c1d65a4de9451671945e19772","Requires Python 3.10+ for the standard-library helper. Execution requires Bash, Nextflow >=24.04.2, a compatible Java runtime (current Nextflow supports Java 17-26), the selected container runtime and optionally a scheduler. Network access is needed for uncached pipeline code, plugins, references and containers.","master","fd76f882a04e445e899d5cfb2732f2105ea054ee","skills\u002Fawesome-skills\u002Fpacsomatic",0,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS","https:\u002F\u002Fbg-szy.github.io\u002FTOP-SKILLS\u002F","https:\u002F\u002Fgithub.com\u002Fbg-szy","https:\u002F\u002Fwww.ecust.edu.cn\u002F","a student of East China University of Science and Technology","2026-11-13 06:26:27",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add bg-szy\u002FTOP-SKILLS --skill pacsomatic",{"tool":49,"command":50},"bunx","bunx skills add bg-szy\u002FTOP-SKILLS --skill pacsomatic",{"tool":52,"command":53},"pnpm","pnpm dlx skills add bg-szy\u002FTOP-SKILLS --skill pacsomatic","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fawesome-skills\u002Fpacsomatic\u002FSKILL.md",true,[57],{"path":58,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":16},"LICENSE","许可证",1068,[62,71,78,85,94,102],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":66,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":70},"01M76KTXGSTXVVDC7YSBM41ZZS","wxpusher-integration","Use when（适用场景）：用户明确询问、指定或上下文已选定 WxPusher，需要了解、接入或排查通知（含微信 ClawBot\u002FiLink、appToken、UID、Topic、SPT）；仅说“微信通知”、未选服务商，或只出现通用 UID\u002FTopic 时不触发。","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fwxpusher-integration\u002FLICENSE.md","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fwxpusher-integration\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":20},"01M748C5DS5BQBVBMG22FCGG34","branding","When the user wants to define, audit, or apply brand strategy—purpose, values, positioning, storytelling, voice, narrative (not only visuals). Also use when the user mentions \"brand strategy\", \"brand story\", \"brand storytelling\" or \"brand voice\". For typography, colors, design tokens, and frontend visuals, use brand-visual-generator.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fsuperskills\u002Fbranding\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":20},"01M748C1GXJ9WRKP18X45DKP6G","brand-visual-generator","When the user wants to define, audit, or apply visual identity (typography, colors, spacing, design tokens, frontend aesthetics). Also use when the user mentions \"brand style guide\", \"visual identity\", \"design system\" or \"typography\". For brand story, positioning, and voice, use branding.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fsuperskills\u002Fbrand-visual-generator\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":20},"01M747T565TFEP3RAVWM0Y899Y","mcp-builder","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node\u002FTypeScript (MCP SDK).","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fskills\u002Fmcp-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fskills\u002Fmcp-builder\u002FSKILL.md",[],[],{"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":89,"licenseFileUrl":98,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":20},"01M747RAJGMBZ2QN4563STB5SH","frontend-design","Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fskills\u002Ffrontend-design\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fskills\u002Ffrontend-design\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":106,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":20},"01M747NHAY5BE9GXEB31H255R1","claude-api","Reference for the Claude API \u002F Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude\u002FAnthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing\u002Fmodel choice\u002Flimits\u002Fcaching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent\u002FMCP\u002Ftool-definition\u002Fmulti-agent\u002FRAG\u002FLLM-judge\u002Fcomputer-use; generate\u002Fsummarize\u002Fextract\u002Fclassify\u002Frewrite\u002Fconverse over NL; debugging refusals\u002Fcutoffs\u002Fstreaming\u002Ftool-calls\u002Ftokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI\u002FGPT\u002FGemini\u002FLlama\u002FMistral\u002FCohere\u002FOllama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fskills\u002Fclaude-api\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fskills\u002Fclaude-api\u002FSKILL.md",[],[]]