[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6X9QN0YV60WHECSR6SNSC85":3,"skill-same:01M6X9QN0YV60WHECSR6SNSC85":62},{"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":18,"publishedAt":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M6X9QN0YV60WHECSR6SNSC85","promptfoo-evals",null,"Creates or updates promptfoo evaluation suites, prompts, tests, assertions, and provider configs. Use when adding eval coverage, debugging regressions, or scaffolding a new eval matrix.","gerald-ica\u002Fopencode-config-snapshot","gerald-ica","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F237541018?v=4","01M6NFATQ9M77J6PZF206YKZ8E","Gerald Welly","01M6X937M942ARP9QYR8ADNT85",2,"MIT","https:\u002F\u002Fgithub.com\u002Fgerald-ica\u002Fopencode-config-snapshot\u002Fblob\u002Fmain\u002Fopencode\u002Fskills\u002Fpromptfoo-evals\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35],"promptfoo","promptfoo evals","evals","provider","when","assertions","matrix","updates","promptfoo evaluation","tests","scaffolding","debugging","prompts","use","coverage","eval","Evaluation","2026-11-10 10:12:30",false,"---\nname: promptfoo-evals\ndescription: Creates or updates promptfoo evaluation suites, prompts, tests, assertions, and provider configs. Use when adding eval coverage, debugging regressions, or scaffolding a new eval matrix.\nlicense: MIT\n---\n\n# Promptfoo Evals\n\nUse this skill for:\n\n- `\u002FUsers\u002Fwendyly\u002F.local\u002Fshare\u002Fagent-skills\u002Fexternal\u002Fpromptfoo`\n\n## Scope\n\n- Create or refine maintainable `promptfoo` evaluation suites.\n- Prefer deterministic assertions first and model-graded assertions only where they add real value.\n\n## Workflow\n\n1. Search for existing `promptfooconfig.yaml`, `promptfooconfig.yml`, or `evals\u002F` directories before creating new ones.\n2. For new suites, prefer:\n\n```text\nevals\u002F\u003Csuite-name>\u002F\n  promptfooconfig.yaml\n  prompts\u002F\n  tests\u002F\n```\n\n3. Add the schema header to config files:\n\n```yaml\n# yaml-language-server: $schema=https:\u002F\u002Fpromptfoo.dev\u002Fconfig-schema.json\n```\n\n4. Put prompts in `prompts\u002F*.txt` or `prompts\u002F*.json` and reference them with `file:\u002F\u002F`.\n5. Keep provider count small and aligned with the real system under test.\n6. Use file-backed tests where possible and include edge cases, regressions, safety\u002Frefusal checks, and output-shape validation.\n7. Use deterministic assertions first:\n   - `equals`\n   - `contains`\n   - `regex`\n   - `is-json`\n   - `javascript`\n   - `python`\n8. Use model-graded assertions sparingly:\n   - `llm-rubric`\n   - `factuality`\n   - `answer-relevance`\n   - `context-faithfulness`\n\n## Validation\n\n- During development, run with `--no-cache`.\n- In the promptfoo repo itself, prefer local build commands over published npm packages.\n\nExample:\n\n```bash\nnpm run local -- validate -c \u003Cconfig>\nnpm run local -- eval -c \u003Cconfig> --no-cache --env-file .env\n```\n\n## Output Contract\n\nWhen done, state:\n\n- what the suite evaluates\n- files created or modified\n- how to run it\n- required env vars\n- any unavoidable TODOs\n","# Promptfoo Evals\n\nUse this skill for:\n\n- `\u002FUsers\u002Fwendyly\u002F.local\u002Fshare\u002Fagent-skills\u002Fexternal\u002Fpromptfoo`\n\n## Scope\n\n- Create or refine maintainable `promptfoo` evaluation suites.\n- Prefer deterministic assertions first and model-graded assertions only where they add real value.\n\n## Workflow\n\n1. Search for existing `promptfooconfig.yaml`, `promptfooconfig.yml`, or `evals\u002F` directories before creating new ones.\n2. For new suites, prefer:\n\n```text\nevals\u002F\u003Csuite-name>\u002F\n  promptfooconfig.yaml\n  prompts\u002F\n  tests\u002F\n```\n\n3. Add the schema header to config files:\n\n```yaml\n# yaml-language-server: $schema=https:\u002F\u002Fpromptfoo.dev\u002Fconfig-schema.json\n```\n\n4. Put prompts in `prompts\u002F*.txt` or `prompts\u002F*.json` and reference them with `file:\u002F\u002F`.\n5. Keep provider count small and aligned with the real system under test.\n6. Use file-backed tests where possible and include edge cases, regressions, safety\u002Frefusal checks, and output-shape validation.\n7. Use deterministic assertions first:\n   - `equals`\n   - `contains`\n   - `regex`\n   - `is-json`\n   - `javascript`\n   - `python`\n8. Use model-graded assertions sparingly:\n   - `llm-rubric`\n   - `factuality`\n   - `answer-relevance`\n   - `context-faithfulness`\n\n## Validation\n\n- During development, run with `--no-cache`.\n- In the promptfoo repo itself, prefer local build commands over published npm packages.\n\nExample:\n\n```bash\nnpm run local -- validate -c \u003Cconfig>\nnpm run local -- eval -c \u003Cconfig> --no-cache --env-file .env\n```\n\n## Output Contract\n\nWhen done, state:\n\n- what the suite evaluates\n- files created or modified\n- how to run it\n- required env vars\n- any unavoidable TODOs\n",{"name":5,"license":15,"description":7},"main","41ab4ff4eae03f182f643b44a975d6f88c60194b","opencode\u002Fskills\u002Fpromptfoo-evals",0,"https:\u002F\u002Fgithub.com\u002Fgerald-ica\u002Fopencode-config-snapshot","https:\u002F\u002Fgithub.com\u002Fgerald-ica","2026-04-14 09:37:13",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add gerald-ica\u002Fopencode-config-snapshot --skill promptfoo-evals",{"tool":54,"command":55},"bunx","bunx skills add gerald-ica\u002Fopencode-config-snapshot --skill promptfoo-evals",{"tool":57,"command":58},"pnpm","pnpm dlx skills add gerald-ica\u002Fopencode-config-snapshot --skill promptfoo-evals","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgerald-ica\u002Fopencode-config-snapshot\u002Fblob\u002Fmain\u002Fopencode\u002Fskills\u002Fpromptfoo-evals\u002FSKILL.md",true,[],[63,101,120,135,151,181],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":82,"publishedAt":36},"01M6X9YGEAGNPWZ4DDK38M68XY","web-design-guidelines","Web platform design and accessibility guidelines. Use when building web interfaces, auditing accessibility, implementing responsive layouts, or reviewing web UI code. Triggers on tasks involving HTML, CSS, web components, WCAG compliance, responsive design, or web performance.","https:\u002F\u002Fgithub.com\u002Fgerald-ica\u002Fopencode-config-snapshot\u002Fblob\u002Fmain\u002Fopencode\u002Fskills\u002Fweb\u002FSKILL.md",[69,74,77],{"categoryNo":70,"categoryName":71,"taxonomyType":72,"taxonomyTypeDesc":73},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",{"categoryNo":75,"categoryName":76,"taxonomyType":72,"taxonomyTypeDesc":73},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":78,"categoryName":79,"taxonomyType":80,"taxonomyTypeDesc":81},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[83,84,85,86,87,88,89,90,91,92,93,94,95,32,96,97,98,99,100,23],"design","web","guidelines","web design guidelines","web design","css","performance","components","tasks","code","ui","WCAG","platform design","responsive design","responsive","platform","triggers","implementing",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":109,"publishedAt":36},"01M6X9Y7HKEAQ39S35ZDPTHCH0","watchos-design-guidelines","Apple Human Interface Guidelines for Apple Watch. Use when building watchOS apps, complications, or workout features. Triggers on tasks involving Watch UI, Digital Crown, glanceable interfaces, or wrist-based interactions.","https:\u002F\u002Fgithub.com\u002Fgerald-ica\u002Fopencode-config-snapshot\u002Fblob\u002Fmain\u002Fopencode\u002Fskills\u002Fwatchos\u002FSKILL.md",[107,108],{"categoryNo":75,"categoryName":76,"taxonomyType":72,"taxonomyTypeDesc":73},{"categoryNo":78,"categoryName":79,"taxonomyType":80,"taxonomyTypeDesc":81},[83,85,110,91,93,32,111,112,113,98,114,99,115,116,117,118,119,23],"watchos design guidelines","workout","human","apple","watch","apps","interface","for","platform-design","features",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":128,"publishedAt":36},"01M6X9Y2VCWR29YKF4SBSRX47B","visionos-design-guidelines","Apple Human Interface Guidelines for Apple Vision Pro. Use when building spatial computing apps, implementing eye\u002Fhand input, or designing immersive experiences. Triggers on tasks involving visionOS, RealityKit, spatial UI, or mixed reality.","https:\u002F\u002Fgithub.com\u002Fgerald-ica\u002Fopencode-config-snapshot\u002Fblob\u002Fmain\u002Fopencode\u002Fskills\u002Fvisionos\u002FSKILL.md",[126,127],{"categoryNo":75,"categoryName":76,"taxonomyType":72,"taxonomyTypeDesc":73},{"categoryNo":78,"categoryName":79,"taxonomyType":80,"taxonomyTypeDesc":81},[83,85,129,130,91,32,112,113,98,99,115,131,116,132,133,100,117,118,23,134],"visionos design guidelines","visionos","mixed reality","pro","hand","spatial computing",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":143,"publishedAt":36},"01M6X9X510STJ022C8VGRQAHSE","tvos-design-guidelines","Apple Human Interface Guidelines for Apple TV. Use when building tvOS apps with focus-based navigation, Siri Remote input, or living room viewing experiences. Triggers on tasks involving Apple TV, tvOS, 10-foot UI, or media playback.","https:\u002F\u002Fgithub.com\u002Fgerald-ica\u002Fopencode-config-snapshot\u002Fblob\u002Fmain\u002Fopencode\u002Fskills\u002Ftvos\u002FSKILL.md",[141,142],{"categoryNo":75,"categoryName":76,"taxonomyType":72,"taxonomyTypeDesc":73},{"categoryNo":78,"categoryName":79,"taxonomyType":80,"taxonomyTypeDesc":81},[83,85,144,91,145,32,146,112,113,98,99,115,147,148,149,116,150,117,118,23],"tvos design guidelines","Media","focus","input","remote","with","tv",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":155,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":161,"publishedAt":36},"01M6X9WSHY020TK0TDZRTNZZK4","timesfm-forecasting","Zero-shot time series forecasting with Google's TimesFM foundation model. Use this skill when forecasting ANY univariate time series — sales, sensor readings, stock prices, energy demand, patient vitals, weather, or scientific measurements — without training a custom model. Supports both basic forecasting and advanced covariate forecasting (XReg) with dynamic and static exogenous variables. Automatically checks system RAM\u002FGPU before loading the model, validates dataset fit before processing, supports CSV\u002FDataFrame\u002Farray inputs, and returns point forecasts with calibrated prediction intervals. Includes a preflight system checker script that MUST be run before first use to verify the machine can load the model and handle your specific dataset.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgerald-ica\u002Fopencode-config-snapshot\u002Fblob\u002Fmain\u002Fopencode\u002Fskills\u002Ftimesfm-forecasting\u002FSKILL.md",[158],{"categoryNo":159,"categoryName":160,"taxonomyType":72,"taxonomyTypeDesc":73},"01JBSEEDCAT000000000000004","电子表格",[162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,23,180],"forecasting","timesfm forecasting","training","model","time","stock","patient","dataset","processing","loading","advanced","Variables","checker","prices","vitals","static","energy","sensor","prediction",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":185,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":188,"publishedAt":36},"01M6X9TZJ5QZM13B0AR1VSNHKS","sqlmap-defensive-audit","Use when working with sqlmap for defensive SQL injection research, local lab validation, code reading, or safe remediation guidance around SQLi testing workflows.","GPL-2.0","https:\u002F\u002Fgithub.com\u002Fgerald-ica\u002Fopencode-config-snapshot\u002Fblob\u002Fmain\u002Fopencode\u002Fskills\u002Fsqlmap-defensive-audit\u002FSKILL.md",[],[189,190,191,192,193,194,195,196,197,92,198,199,32,200,201,149,202,203,117,23],"audit","sqlmap","defensive","sqlmap defensive audit","testing","safe","research","workflows","sql","validation","remediation","guidance","local","reading","lab"]