[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M793EXP8BHMBHZSCNDXPBVYJ":3,"skill-same:01M793EXP8BHMBHZSCNDXPBVYJ":70},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M793EXP8BHMBHZSCNDXPBVYJ","pyrit",null,"Use Microsoft PyRIT for generative-AI red teaming, prompt targets, scorers, converters, datasets, attack scenarios, scanner CLI, backend, and troubleshooting.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyrit\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pyrit\ndescription: \"Use Microsoft PyRIT for generative-AI red teaming, prompt targets,\n  scorers, converters, datasets, attack scenarios, scanner CLI, backend, and\n  troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# PyRIT repo skill\n\nUse this skill when a task names PyRIT, `pyrit_scan`, `pyrit_backend`, CoPyRIT, Python Risk Identification Tool, AI red teaming, LLM robustness testing, prompt targets, scorers, converters, seed datasets, attack techniques, or scenario campaigns.\n\nThis skill is for operating PyRIT as a package. It does not authorize live red-team execution against external systems; require explicit user scope, target approval, credentials handling, and data rules before sending prompts to live services.\n\n## First checks\n\n1. Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) if you need to decide whether this skill is current for a checkout.\n2. Read [references\u002Finstall-configuration.md](references\u002Finstall-configuration.md) for package install, optional extras, PyRIT home\u002Fconfig, and no-secret import checks.\n3. Run [scripts\u002Fpyrit_api_smoke.py](scripts\u002Fpyrit_api_smoke.py) when you need a no-secret installed-package sanity check.\n4. Use [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for cross-cutting install\u002Fimport, optional dependency, credential, CLI\u002Fbackend, and layer-boundary problems.\n\n## Route by task\n\n| User need | Read |\n|---|---|\n| Initialize PyRIT, choose `InMemory`\u002FSQLite\u002FAzure SQL, load config\u002Fenv files, inspect registries\u002Fmodels\u002Foutput helpers | [setup-memory-core](sub-skills\u002Fsetup-memory-core\u002FSKILL.md) |\n| Build converters, converter stacks, message normalization, seed prompts\u002Fdatasets, and data\u002FYAML schemas | [converters-datasets](sub-skills\u002Fconverters-datasets\u002FSKILL.md) |\n| Configure prompt targets, target capabilities, scorers, score aggregation\u002Fevaluation, auth\u002Frate-limit\u002Fmodel-service troubleshooting | [targets-scorers](sub-skills\u002Ftargets-scorers\u002FSKILL.md) |\n| Choose\u002Fconfigure attacks, executors, attack techniques, scenarios, benchmarks, prompt generators, concurrency\u002Fretries\u002Fresults | [attacks-scenarios](sub-skills\u002Fattacks-scenarios\u002FSKILL.md) |\n| Use `pyrit_scan`, `pyrit_shell`, `pyrit_backend`, backend REST service, scanner workflows, or CoPyRIT GUI operations | [cli-backend-scanner](sub-skills\u002Fcli-backend-scanner\u002FSKILL.md) |\n\n## Safe operating defaults\n\n- Prefer no-secret import\u002Fsignature checks before running examples or scans.\n- Prefer offline components (`TextTarget`, rule scorers, offline converters, in-memory\u002Ftemporary SQLite memory) for smoke tests.\n- Treat OpenAI\u002FAzure\u002FHuggingFace\u002FLiteLLM\u002FHTTP\u002FPlaywright\u002FAzure SQL paths as credentialed or service-bound.\n- Treat GCG, HuggingFace, media, browser, and benchmark paths as optional\u002Fheavy unless the user explicitly selects them.\n- Keep secrets out of prompts, command lines, logs, generated examples, and persisted memory unless the user explicitly authorizes the storage location.\n\n## Minimal Python check\n\n```python\nimport pyrit\nprint(pyrit.__version__)\nfrom pyrit.converter import Base64Converter\nfrom pyrit.prompt_target import TextTarget\nfrom pyrit.score.true_false.substring_scorer import SubStringScorer\n```\n\nFor deeper checks, run the bundled scripts in the relevant sub-skill. They are designed to work from any directory where PyRIT is installed and do not depend on the original repository checkout.\n","# PyRIT repo skill\n\nUse this skill when a task names PyRIT, `pyrit_scan`, `pyrit_backend`, CoPyRIT, Python Risk Identification Tool, AI red teaming, LLM robustness testing, prompt targets, scorers, converters, seed datasets, attack techniques, or scenario campaigns.\n\nThis skill is for operating PyRIT as a package. It does not authorize live red-team execution against external systems; require explicit user scope, target approval, credentials handling, and data rules before sending prompts to live services.\n\n## First checks\n\n1. Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) if you need to decide whether this skill is current for a checkout.\n2. Read [references\u002Finstall-configuration.md](references\u002Finstall-configuration.md) for package install, optional extras, PyRIT home\u002Fconfig, and no-secret import checks.\n3. Run [scripts\u002Fpyrit_api_smoke.py](scripts\u002Fpyrit_api_smoke.py) when you need a no-secret installed-package sanity check.\n4. Use [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for cross-cutting install\u002Fimport, optional dependency, credential, CLI\u002Fbackend, and layer-boundary problems.\n\n## Route by task\n\n| User need | Read |\n|---|---|\n| Initialize PyRIT, choose `InMemory`\u002FSQLite\u002FAzure SQL, load config\u002Fenv files, inspect registries\u002Fmodels\u002Foutput helpers | [setup-memory-core](sub-skills\u002Fsetup-memory-core\u002FSKILL.md) |\n| Build converters, converter stacks, message normalization, seed prompts\u002Fdatasets, and data\u002FYAML schemas | [converters-datasets](sub-skills\u002Fconverters-datasets\u002FSKILL.md) |\n| Configure prompt targets, target capabilities, scorers, score aggregation\u002Fevaluation, auth\u002Frate-limit\u002Fmodel-service troubleshooting | [targets-scorers](sub-skills\u002Ftargets-scorers\u002FSKILL.md) |\n| Choose\u002Fconfigure attacks, executors, attack techniques, scenarios, benchmarks, prompt generators, concurrency\u002Fretries\u002Fresults | [attacks-scenarios](sub-skills\u002Fattacks-scenarios\u002FSKILL.md) |\n| Use `pyrit_scan`, `pyrit_shell`, `pyrit_backend`, backend REST service, scanner workflows, or CoPyRIT GUI operations | [cli-backend-scanner](sub-skills\u002Fcli-backend-scanner\u002FSKILL.md) |\n\n## Safe operating defaults\n\n- Prefer no-secret import\u002Fsignature checks before running examples or scans.\n- Prefer offline components (`TextTarget`, rule scorers, offline converters, in-memory\u002Ftemporary SQLite memory) for smoke tests.\n- Treat OpenAI\u002FAzure\u002FHuggingFace\u002FLiteLLM\u002FHTTP\u002FPlaywright\u002FAzure SQL paths as credentialed or service-bound.\n- Treat GCG, HuggingFace, media, browser, and benchmark paths as optional\u002Fheavy unless the user explicitly selects them.\n- Keep secrets out of prompts, command lines, logs, generated examples, and persisted memory unless the user explicitly authorizes the storage location.\n\n## Minimal Python check\n\n```python\nimport pyrit\nprint(pyrit.__version__)\nfrom pyrit.converter import Base64Converter\nfrom pyrit.prompt_target import TextTarget\nfrom pyrit.score.true_false.substring_scorer import SubStringScorer\n```\n\nFor deeper checks, run the bundled scripts in the relevant sub-skill. They are designed to work from any directory where PyRIT is installed and do not depend on the original repository checkout.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fpyrit",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill pyrit",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill pyrit",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill pyrit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyrit\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Finstall-configuration.md","REFERENCE","参考文档",2198,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyrit\u002Freferences\u002Finstall-configuration.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-provenance.md",1603,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyrit\u002Freferences\u002Frepo-provenance.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frepo-routing-metadata.json",409,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyrit\u002Freferences\u002Frepo-routing-metadata.json",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",1556,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyrit\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fpyrit_api_smoke.py","SCRIPT","脚本",2823,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpyrit\u002Fscripts\u002Fpyrit_api_smoke.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]