[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7961AP3FSDY1RM0E05PW2BB":3,"skill-same:01M7961AP3FSDY1RM0E05PW2BB":67},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M7961AP3FSDY1RM0E05PW2BB","privacy-tests",null,"Routes TensorFlow Privacy users who want membership inference analysis, privacy reports, membership inference callbacks, or secret-sharer exposure checks.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorflow-privacy\u002Fsub-skills\u002Fprivacy-tests\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: privacy-tests\ndescription: \"Routes TensorFlow Privacy users who want membership inference\n  analysis, privacy reports, membership inference callbacks, or secret-sharer\n  exposure checks.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Privacy tests\n\nUse this sub-skill when the user wants to measure memorization or privacy risk from model outputs.\n\n## Trigger phrases\n\n- \"membership inference\"\n- \"privacy report\"\n- \"attack results\"\n- \"epsilon lower bound\"\n- \"privacy callback\"\n- \"secret sharer\"\n- \"exposure\"\n- \"memorization\"\n\n## What this sub-skill covers\n\n- `AttackInputData`, `SlicingSpec`, and `AttackType`\n- `run_attacks()`, `run_membership_probability_analysis()`, and `run_attack_on_keras_model()`\n- `MembershipInferenceCallback` and the `keras_evaluation` callback path\n- `AttackResults`, privacy-report metadata, and pandas summaries\n- `privacy_report` plotting\u002Freport helpers\n- secret-sharer secret generation and exposure computation\n\n## What it does not cover\n\n- DP training or optimizer selection -> `..\u002Ftraining\u002F`\n- privacy budget and epsilon\u002Fnoise search -> `..\u002Fprivacy-accounting\u002F`\n- `DPQuery` internals -> `..\u002Fqueries\u002F`\n- fast clipping internals -> `..\u002Ffast-clipping\u002F`\n\n## Read this before you act\n\n- `references\u002Fapi-reference.md` for attack inputs, outputs, and the bundled smoke pattern.\n- `references\u002Ftroubleshooting.md` for tiny-data, shape, and dependency failures.\n- `..\u002F..\u002Freferences\u002Finstall-and-scope.md` for the minimum CPU runtime.\n\n## Typical workflow\n\n1. Decide whether the user wants membership inference or secret-sharer exposure analysis.\n2. Build the smallest valid `AttackInputData` or secret-sharer fixture.\n3. Use the bundled smoke helper before trying a larger analysis.\n4. If the user is asking for training guidance rather than analysis, route to `training`.\n\n## Bundled helpers\n\n- `scripts\u002Ftiny_mia_smoke.py` runs a threshold membership-inference attack on synthetic losses.\n- `scripts\u002Ftiny_secret_sharer_smoke.py` generates a toy secret set and computes exposure on synthetic perplexities.\n","# Privacy tests\n\nUse this sub-skill when the user wants to measure memorization or privacy risk from model outputs.\n\n## Trigger phrases\n\n- \"membership inference\"\n- \"privacy report\"\n- \"attack results\"\n- \"epsilon lower bound\"\n- \"privacy callback\"\n- \"secret sharer\"\n- \"exposure\"\n- \"memorization\"\n\n## What this sub-skill covers\n\n- `AttackInputData`, `SlicingSpec`, and `AttackType`\n- `run_attacks()`, `run_membership_probability_analysis()`, and `run_attack_on_keras_model()`\n- `MembershipInferenceCallback` and the `keras_evaluation` callback path\n- `AttackResults`, privacy-report metadata, and pandas summaries\n- `privacy_report` plotting\u002Freport helpers\n- secret-sharer secret generation and exposure computation\n\n## What it does not cover\n\n- DP training or optimizer selection -> `..\u002Ftraining\u002F`\n- privacy budget and epsilon\u002Fnoise search -> `..\u002Fprivacy-accounting\u002F`\n- `DPQuery` internals -> `..\u002Fqueries\u002F`\n- fast clipping internals -> `..\u002Ffast-clipping\u002F`\n\n## Read this before you act\n\n- `references\u002Fapi-reference.md` for attack inputs, outputs, and the bundled smoke pattern.\n- `references\u002Ftroubleshooting.md` for tiny-data, shape, and dependency failures.\n- `..\u002F..\u002Freferences\u002Finstall-and-scope.md` for the minimum CPU runtime.\n\n## Typical workflow\n\n1. Decide whether the user wants membership inference or secret-sharer exposure analysis.\n2. Build the smallest valid `AttackInputData` or secret-sharer fixture.\n3. Use the bundled smoke helper before trying a larger analysis.\n4. If the user is asking for training guidance rather than analysis, route to `training`.\n\n## Bundled helpers\n\n- `scripts\u002Ftiny_mia_smoke.py` runs a threshold membership-inference attack on synthetic losses.\n- `scripts\u002Ftiny_secret_sharer_smoke.py` generates a toy secret set and computes exposure on synthetic perplexities.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Ftensorflow-privacy\u002Fsub-skills\u002Fprivacy-tests",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill privacy-tests",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill privacy-tests",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill privacy-tests","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorflow-privacy\u002Fsub-skills\u002Fprivacy-tests\u002FSKILL.md",[47,53,57,63],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",3722,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorflow-privacy\u002Fsub-skills\u002Fprivacy-tests\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",2567,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorflow-privacy\u002Fsub-skills\u002Fprivacy-tests\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Ftiny_mia_smoke.py","SCRIPT","脚本",1185,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorflow-privacy\u002Fsub-skills\u002Fprivacy-tests\u002Fscripts\u002Ftiny_mia_smoke.py",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Ftiny_secret_sharer_smoke.py",1499,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftensorflow-privacy\u002Fsub-skills\u002Fprivacy-tests\u002Fscripts\u002Ftiny_secret_sharer_smoke.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]