[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AWJCKSS554MYFK7V0Y6DF2":3,"skill-same:01M7AWJCKSS554MYFK7V0Y6DF2":50},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":43},"01M7AWJCKSS554MYFK7V0Y6DF2","interview",null,"Run an adaptive context-gathering interview when the user explicitly invokes interview before a decision or task. Reuse known answers and stop when the decision-critical context is sufficient.","chrispalmo\u002Fagent-config","chrispalmo","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F34981948?v=4","01M7AWE0QNCNVY5GQACXXGB2ES","01M7AWE0RRB55TJNCV13ZDM62W",1,"MIT","https:\u002F\u002Fgithub.com\u002Fchrispalmo\u002Fagent-config\u002Fblob\u002Fmain\u002Fskills\u002Finterview\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: interview\ndescription: Run an adaptive context-gathering interview when the user explicitly invokes interview before a decision or task. Reuse known answers and stop when the decision-critical context is sufficient.\ndisable-model-invocation: true\n---\n\n# Interview\n\nStart only when the user requests this workflow, even if a harness ignores invocation metadata. Infer the subject and originating task from the conversation; use the first batch to establish missing scope if necessary.\n\n## Question batches\n\nHonor requested rounds and counts. Otherwise use at most two batches of up to three focused questions each; these are maxima, not quotas. State the subject and planned limit briefly, then ask the first useful batch. Prefer concrete choices with a free-text route when available.\n\nReuse facts already provided and omit questions whose answers would not change the decision. Group independent questions in one message and follow the active conversation's numbering and formatting conventions. Internal round\u002Fquestion IDs need not become restarted display labels. Let the user answer by label, briefly, or skip.\n\nMove from scope and success toward consequential uncertainties and practical choices. Do not chase every skipped answer or infer consent from omission. Reframe an unanswered question only when it blocks the requested outcome, and explain why it matters.\n\n## Finish and continuation\n\nEnd when enough context exists, the configured limit is reached, or the user says DONE or STOP. Do not require another DONE after the final useful batch. Summarize any decision-critical uncertainty and resume an already-authorized originating task once the interview ends. STOP ends interviewing; if it also cancels the task, respect that instruction.\n\nWhile awaiting interview answers, do not begin dependent implementation. Independent work may continue only when the user has authorized it. Do not add a separate confirmation gate unless the user requested one or a consequential choice remains unresolved.\n","# Interview\n\nStart only when the user requests this workflow, even if a harness ignores invocation metadata. Infer the subject and originating task from the conversation; use the first batch to establish missing scope if necessary.\n\n## Question batches\n\nHonor requested rounds and counts. Otherwise use at most two batches of up to three focused questions each; these are maxima, not quotas. State the subject and planned limit briefly, then ask the first useful batch. Prefer concrete choices with a free-text route when available.\n\nReuse facts already provided and omit questions whose answers would not change the decision. Group independent questions in one message and follow the active conversation's numbering and formatting conventions. Internal round\u002Fquestion IDs need not become restarted display labels. Let the user answer by label, briefly, or skip.\n\nMove from scope and success toward consequential uncertainties and practical choices. Do not chase every skipped answer or infer consent from omission. Reframe an unanswered question only when it blocks the requested outcome, and explain why it matters.\n\n## Finish and continuation\n\nEnd when enough context exists, the configured limit is reached, or the user says DONE or STOP. Do not require another DONE after the final useful batch. Summarize any decision-critical uncertainty and resume an already-authorized originating task once the interview ends. STOP ends interviewing; if it also cancels the task, respect that instruction.\n\nWhile awaiting interview answers, do not begin dependent implementation. Independent work may continue only when the user has authorized it. Do not add a separate confirmation gate unless the user requested one or a consequential choice remains unresolved.\n",{"name":5,"description":7,"disable-model-invocation":23},true,"main","113772f3e374658396a52fcca32e06badbdb9556","skills\u002Finterview",0,"https:\u002F\u002Fgithub.com\u002Fchrispalmo\u002Fagent-config","https:\u002F\u002Fgithub.com\u002Fchrispalmo","2026-11-14 00:31:43",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":23},[33,36,39],{"tool":34,"command":35},"npx","npx skills add chrispalmo\u002Fagent-config --skill interview",{"tool":37,"command":38},"bunx","bunx skills add chrispalmo\u002Fagent-config --skill interview",{"tool":40,"command":41},"pnpm","pnpm dlx skills add chrispalmo\u002Fagent-config --skill interview","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fchrispalmo\u002Fagent-config\u002Fblob\u002Fmain\u002Fskills\u002Finterview\u002FSKILL.md",[44],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"agents\u002Fopenai.yaml","REFERENCE","参考文档",43,"https:\u002F\u002Fgithub.com\u002Fchrispalmo\u002Fagent-config\u002Fblob\u002Fmain\u002Fskills\u002Finterview\u002Fagents\u002Fopenai.yaml",[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M7AWJKHA9XNG2FJQCDMGQ2MQ","search-agent-chats","Search retained Cursor, Codex, and Claude Code conversations for past work, decisions, and context when historical recall would help. Exposes archive scope, freshness, coverage, and event citations. Do not run at session start.","https:\u002F\u002Fgithub.com\u002Fchrispalmo\u002Fagent-config\u002Fblob\u002Fmain\u002Fskills\u002Fsearch-agent-chats\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M7AWJGYNF92E7KMBAJ7WCK8R","plaintext","Produce one copyable plain-text payload only when the human explicitly invokes plaintext. Use for prompts, messages, emails, and other requested copy-paste output.","https:\u002F\u002Fgithub.com\u002Fchrispalmo\u002Fagent-config\u002Fblob\u002Fmain\u002Fskills\u002Fplaintext\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M7AWJ9PPHQX3D6ENTHBVA3GY","github-repo-defaults","Apply GitHub ownership and Snowflake1 connection defaults when creating a new repository or publishing a local project to a new GitHub repository. Use for repository creation requests, including project setup that creates a repo.","https:\u002F\u002Fgithub.com\u002Fchrispalmo\u002Fagent-config\u002Fblob\u002Fmain\u002Fskills\u002Fgithub-repo-defaults\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M7AWJ4NTWRKE4KZTG8704T8F","github-init","Initializes the current project as a Git repository, creates a GitHub repository, and pushes the initial branch with upstream tracking. Defaults to a private repository in snowflake1xyz with Snowflake1 guidance connected; explicit text may override owner or visibility. Use only when the human explicitly invokes github-init.","https:\u002F\u002Fgithub.com\u002Fchrispalmo\u002Fagent-config\u002Fblob\u002Fmain\u002Fskills\u002Fgithub-init\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7AWJ24EWEDG1MNVKHETWCFM","decision-criteria","Assess a decision or revisit a prior recommendation against the user's objectives, criteria, constraints, and evidence. Use only when explicitly invoked.","https:\u002F\u002Fgithub.com\u002Fchrispalmo\u002Fagent-config\u002Fblob\u002Fmain\u002Fskills\u002Fdecision-criteria\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M7AWHX9S6FXMQBQXENF4WPSE","concierge","Deliver complete work and anticipate the user's follow-up questions, with concise responses backed by human-readable answers and prepared alternatives. Use only when the user explicitly invokes concierge for sustained iteration or exploration beyond a first pass, including useful progress while resources or decisions are pending.","https:\u002F\u002Fgithub.com\u002Fchrispalmo\u002Fagent-config\u002Fblob\u002Fmain\u002Fskills\u002Fconcierge\u002FSKILL.md",[],[]]