[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CFQJPDV0W6RVFZHRVQNSPY":3,"skill-same:01M7CFQJPDV0W6RVFZHRVQNSPY":46},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7CFQJPDV0W6RVFZHRVQNSPY","research-and-recommend",null,"Research an open question or unfamiliar implementation, compare viable approaches against the user's constraints, and recommend the best fit using primary sources and applicable standards. Use when the user wants evidence-backed options and a recommendation; a single documentation lookup belongs to find-docs.","BrianLiDesign\u002Fblidesign-ai-toolkit","BrianLiDesign","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54822500?v=4","01M7CFJ90VGBF0492PJ4E0YB3Y","Brian Li","01M7CFJ91YJ7S88B0YTDDP6A7G",0,"MIT","https:\u002F\u002Fgithub.com\u002FBrianLiDesign\u002Fblidesign-ai-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit-workflows\u002Fskills\u002Fresearch-and-recommend\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: research-and-recommend\ndescription: Research an open question or unfamiliar implementation, compare viable approaches against the user's constraints, and recommend the best fit using primary sources and applicable standards. Use when the user wants evidence-backed options and a recommendation; a single documentation lookup belongs to find-docs.\n---\n\n# Research and recommend\n\nTurn an uncertain question into a defensible decision and a practical next step. Scale the research\nto the decision's cost, reversibility, and uncertainty; keep small questions concise.\n\n## Frame the decision\n\nIdentify the desired outcome, constraints, existing environment, and criteria that would make one\napproach preferable. Inspect available project context before asking the user for facts. Ask only\nwhen a missing preference or constraint could materially change the recommendation; otherwise state\nreasonable assumptions and proceed. Preserve explicit choices and previously authorized work.\n\n## Gather evidence and alternatives\n\n- Search for materially different approaches before selecting a favorite. Normally investigate\n  two to four credible candidates; expand when the decision warrants it. Include the existing\n  approach or a simpler solution when viable. Explain if only one candidate meets the constraints\n  rather than inventing alternatives to fill a quota.\n- Use search to discover candidates, then verify decision-driving claims at their primary sources:\n  official documentation, specifications, standards bodies, original studies, source code, or\n  first-party measurements. Secondary sources can surface experience and alternatives; label their\n  limitations and trace factual claims to the owner where possible. Open the underlying sources\n  rather than relying on search snippets.\n- Identify standards that actually govern the question. Check their edition, status, scope, and\n  applicability. Distinguish mandatory requirements from recommendations and common practice.\n  State when authoritative text is inaccessible or no relevant standard was found.\n- For library, framework, SDK, API, CLI, or cloud-service details, follow\n  [find-docs](..\u002Ffind-docs\u002FSKILL.md) for current documentation. For other subjects, use the available\n  search and browsing tools directly. Verify time-sensitive claims and version compatibility;\n  report access failures and the resulting evidence gaps.\n- Look for evidence that could disqualify the leading candidate, including maintenance status,\n  limitations, and contradictory findings. Cite the source beside each decisive claim. Distinguish\n  verified facts, source claims, assumptions, and your own judgment.\n\nResearch is sufficient when the viable candidates have been assessed against the decisive criteria\nand remaining unknowns either cannot change the choice or are explicitly identified as blockers.\nIf an important uncertainty remains, recommend the smallest useful experiment or information check\ninstead of presenting a tentative choice as settled.\n\n## Compare and recommend\n\nCompare candidates using the user's priorities. Cover relevant tradeoffs such as correctness,\nstandards compliance, compatibility, effort, operating cost, maintainability, performance, and risk.\nUse a compact table when it makes the differences clearer. Explain any scoring weights or estimates;\navoid numerical precision that the evidence cannot support. Vendor benchmarks establish behavior\nonly under their stated conditions; identify what still needs local validation.\n\nRecommend one best fit for the stated context, with its decisive advantages and meaningful costs.\nExplain why the strongest alternatives lose here and what changed conditions would favor them.\nGive a confidence level with its evidence basis and identify any uncertainty that could reverse\nthe recommendation. A conditional recommendation is appropriate when a decisive fact is missing.\n\n## Deliver and continue within scope\n\nLead with the recommendation, then provide the decision criteria, alternatives and tradeoffs,\nsupporting sources, and material unknowns. End with an implementation outline or concrete next\nstep, including how to validate the choice. Match detail to the question; avoid forcing a lengthy\nreport on a small decision.\n\nAnswer in chat unless the user requests a saved artifact or the project requires one; follow its\nexisting research-note convention when saving. Research alone does not authorize implementation\nor external changes. When implementation is already requested, continue with the selected approach\nwithin that authorization after presenting the rationale, asking only for unresolved decisions\nthat materially affect the work.\n","# Research and recommend\n\nTurn an uncertain question into a defensible decision and a practical next step. Scale the research\nto the decision's cost, reversibility, and uncertainty; keep small questions concise.\n\n## Frame the decision\n\nIdentify the desired outcome, constraints, existing environment, and criteria that would make one\napproach preferable. Inspect available project context before asking the user for facts. Ask only\nwhen a missing preference or constraint could materially change the recommendation; otherwise state\nreasonable assumptions and proceed. Preserve explicit choices and previously authorized work.\n\n## Gather evidence and alternatives\n\n- Search for materially different approaches before selecting a favorite. Normally investigate\n  two to four credible candidates; expand when the decision warrants it. Include the existing\n  approach or a simpler solution when viable. Explain if only one candidate meets the constraints\n  rather than inventing alternatives to fill a quota.\n- Use search to discover candidates, then verify decision-driving claims at their primary sources:\n  official documentation, specifications, standards bodies, original studies, source code, or\n  first-party measurements. Secondary sources can surface experience and alternatives; label their\n  limitations and trace factual claims to the owner where possible. Open the underlying sources\n  rather than relying on search snippets.\n- Identify standards that actually govern the question. Check their edition, status, scope, and\n  applicability. Distinguish mandatory requirements from recommendations and common practice.\n  State when authoritative text is inaccessible or no relevant standard was found.\n- For library, framework, SDK, API, CLI, or cloud-service details, follow\n  [find-docs](..\u002Ffind-docs\u002FSKILL.md) for current documentation. For other subjects, use the available\n  search and browsing tools directly. Verify time-sensitive claims and version compatibility;\n  report access failures and the resulting evidence gaps.\n- Look for evidence that could disqualify the leading candidate, including maintenance status,\n  limitations, and contradictory findings. Cite the source beside each decisive claim. Distinguish\n  verified facts, source claims, assumptions, and your own judgment.\n\nResearch is sufficient when the viable candidates have been assessed against the decisive criteria\nand remaining unknowns either cannot change the choice or are explicitly identified as blockers.\nIf an important uncertainty remains, recommend the smallest useful experiment or information check\ninstead of presenting a tentative choice as settled.\n\n## Compare and recommend\n\nCompare candidates using the user's priorities. Cover relevant tradeoffs such as correctness,\nstandards compliance, compatibility, effort, operating cost, maintainability, performance, and risk.\nUse a compact table when it makes the differences clearer. Explain any scoring weights or estimates;\navoid numerical precision that the evidence cannot support. Vendor benchmarks establish behavior\nonly under their stated conditions; identify what still needs local validation.\n\nRecommend one best fit for the stated context, with its decisive advantages and meaningful costs.\nExplain why the strongest alternatives lose here and what changed conditions would favor them.\nGive a confidence level with its evidence basis and identify any uncertainty that could reverse\nthe recommendation. A conditional recommendation is appropriate when a decisive fact is missing.\n\n## Deliver and continue within scope\n\nLead with the recommendation, then provide the decision criteria, alternatives and tradeoffs,\nsupporting sources, and material unknowns. End with an implementation outline or concrete next\nstep, including how to validate the choice. Match detail to the question; avoid forcing a lengthy\nreport on a small decision.\n\nAnswer in chat unless the user requests a saved artifact or the project requires one; follow its\nexisting research-note convention when saving. Research alone does not authorize implementation\nor external changes. When implementation is already requested, continue with the selected approach\nwithin that authorization after presenting the rationale, asking only for unresolved decisions\nthat materially affect the work.\n",{"name":5,"description":7},"main","b8aa90af52b15176766c4ee334689ce6828a6a38","plugins\u002Ftoolkit-workflows\u002Fskills\u002Fresearch-and-recommend","https:\u002F\u002Fgithub.com\u002FBrianLiDesign\u002Fblidesign-ai-toolkit","https:\u002F\u002Fgithub.com\u002FBrianLiDesign","https:\u002F\u002Fbrianlidesign.vercel.app\u002F","Computer Engineer, Designer, Developer, & Student @ California Polytechnic University, San Luis Obispo","2026-11-10 23:39:35",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add BrianLiDesign\u002Fblidesign-ai-toolkit --skill research-and-recommend",{"tool":38,"command":39},"bunx","bunx skills add BrianLiDesign\u002Fblidesign-ai-toolkit --skill research-and-recommend",{"tool":41,"command":42},"pnpm","pnpm dlx skills add BrianLiDesign\u002Fblidesign-ai-toolkit --skill research-and-recommend","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FBrianLiDesign\u002Fblidesign-ai-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit-workflows\u002Fskills\u002Fresearch-and-recommend\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7CFQW0KNR2PJ3RG8Q41JNA2","toolkit-smoke-test","Verify a toolkit update across installed agent hosts using skill discovery, installed versions, MCP startup, and harmless tool calls. Use after installation or for cross-host release checks.","https:\u002F\u002Fgithub.com\u002FBrianLiDesign\u002Fblidesign-ai-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit-workflows\u002Fskills\u002Ftoolkit-smoke-test\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7CFQS0V2Y73C12GZXYDN06D","security-check","Assess security implications of a software change using project scanners, dependency and secret checks, and changed trust boundaries. Use for requested security checks or changes affecting authentication, permissions, untrusted input, or sensitive data.","https:\u002F\u002Fgithub.com\u002FBrianLiDesign\u002Fblidesign-ai-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit-workflows\u002Fskills\u002Fsecurity-check\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7CFQE64C9HEW9PD7YCBKBHK","release-acceptance","Verify a deployed release against public behavior and persistence requirements, recording inspectable evidence and cleaning up owned test data.","https:\u002F\u002Fgithub.com\u002FBrianLiDesign\u002Fblidesign-ai-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit-workflows\u002Fskills\u002Frelease-acceptance\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7CFQA2D5G5WAB34KVHX1P1N","project-check","Discover and run a project's verification commands, recording commit-specific results and missing checks. Use to validate a change or establish the repository's verification gate.","https:\u002F\u002Fgithub.com\u002FBrianLiDesign\u002Fblidesign-ai-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit-workflows\u002Fskills\u002Fproject-check\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7CFQ76Z5ZSENWP9NB1TTY7X","pr-closeout","Finish an authorized GitHub PR through review remediation, CI, metadata, merge, and post-merge verification. Use for PR closeout; keep assessment-only requests read-only.","https:\u002F\u002Fgithub.com\u002FBrianLiDesign\u002Fblidesign-ai-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit-workflows\u002Fskills\u002Fpr-closeout\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7CFQ3Z6TM4EKW4VVMT8HD9E","orchestrate","Coordinate native subagents for substantial independent research, review, or implementation tasks, with bounded delegation, isolated edits, and verified integration. Keep small or tightly dependent tasks in the main agent.","https:\u002F\u002Fgithub.com\u002FBrianLiDesign\u002Fblidesign-ai-toolkit\u002Fblob\u002Fmain\u002Fplugins\u002Ftoolkit-workflows\u002Fskills\u002Forchestrate\u002FSKILL.md",[],[]]