[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7341CMP0KYC24RA2W88AW98":3,"skill-same:01M7341CMP0KYC24RA2W88AW98":45},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":44},"01M7341CMP0KYC24RA2W88AW98","ask-research",null,"Research: Does bounded fact-finding across the repository, docs, code, or external sources. Use when a question needs evidence before an answer or decision. Common triggers: research this, research question, find evidence, compare sources, investigate current state, look into this technology, research documentation.","MarkBovee\u002Fagent-skills-kit","MarkBovee","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1203948?v=4","01M733X7T9ZYGXR05VBXNZEH36","Mark Bovee","01M733X7V1Q57ZK772WYENHFAV",1,"MIT","https:\u002F\u002Fgithub.com\u002FMarkBovee\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fask-research\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: \"ask-research\"\ndescription: \"Research: Does bounded fact-finding across the repository, docs, code, or external sources. Use when a question needs evidence before an answer or decision. Common triggers: research this, research question, find evidence, compare sources, investigate current state, look into this technology, research documentation.\"\ndisable-model-invocation: true\n---\n# ASK Research\n\nAnswer bounded questions with evidence, not recollection. This is fact-finding, not a design decision, code audit, or implementation pass.\n\n## Flow\n\n1. State question, decision it informs, scope, constraints, and unknowns.\n2. Inspect local evidence before external sources when repository state matters: code, tests, fixtures, logs, history, and configuration.\n3. Discover primary sources, then read relevant sections rather than relying on search snippets.\n4. Compare evidence, distinguish `FACT`, `OBSERVATION`, `INFERENCE`, `HYPOTHESIS`, `ASSUMPTION`, and `UNKNOWN`.\n5. Answer with citations, confidence, decision impact, and exact evidence still needed.\n\n## Rules\n\n- Prefer runtime evidence, reproducible tests, source code, official documentation, and standards over secondary sources.\n- For MCP-backed discovery, search for one concrete capability at a time (for example, one entity state, installed-app slug, or add-on log) instead of combining unrelated intents.\n- Prefer the smallest available search result projection\u002Flimit, invoke only the discovered read tool needed for the next diagnostic step, and avoid repeating broad searches when the relevant tool name is already known.\n- If a discovery server returns full schemas only, record the output-size or latency cost and treat compact discovery\u002Fprojection support as a follow-up rather than repeatedly requesting unrelated schemas.\n- Cite external claims with stable URLs; cite local claims as `path:line` or a precise section.\n- Do not implement, settle product or architecture choices, or present an inference as fact.\n- Escalate to `deep-research` for multiple interacting unknowns, several source classes, conflicting evidence, historical\u002Fprotocol analysis, or an exhaustive request.\n- In delegated results, return `ASK_WORKFLOW_PASS phase=RESEARCH` only when the stated question is answered or remaining gaps are explicitly actionable. Use `ASK_WORKFLOW_BLOCKED phase=RESEARCH` when essential evidence is inaccessible. Never include workflow markers in the final user-facing response.\n\n## Output\n\n```text\nAnswer\nEvidence: source - observation\nConfidence: CONFIRMED | HIGH | MEDIUM | LOW | SPECULATIVE | UNKNOWN\nDecision impact\nHandoff: next owner, recommended action, protected scope, and required proof\nOpen questions \u002F next evidence needed\n```\n\n## Use with\n\n- `deep-research` when bounded investigation expands into a multi-track program\n- `intake` to scope a decision after facts are known\n- `debugging` to trace and fix a defect revealed by evidence\n- `develop` to implement an evidence-backed recommendation\n\n## Avoid\n\n- Treating a search-result snippet as evidence\n- Starting broad repository audits; use `improve`\n- Repeated permission questions when the next evidence source is clear\n","# ASK Research\n\nAnswer bounded questions with evidence, not recollection. This is fact-finding, not a design decision, code audit, or implementation pass.\n\n## Flow\n\n1. State question, decision it informs, scope, constraints, and unknowns.\n2. Inspect local evidence before external sources when repository state matters: code, tests, fixtures, logs, history, and configuration.\n3. Discover primary sources, then read relevant sections rather than relying on search snippets.\n4. Compare evidence, distinguish `FACT`, `OBSERVATION`, `INFERENCE`, `HYPOTHESIS`, `ASSUMPTION`, and `UNKNOWN`.\n5. Answer with citations, confidence, decision impact, and exact evidence still needed.\n\n## Rules\n\n- Prefer runtime evidence, reproducible tests, source code, official documentation, and standards over secondary sources.\n- For MCP-backed discovery, search for one concrete capability at a time (for example, one entity state, installed-app slug, or add-on log) instead of combining unrelated intents.\n- Prefer the smallest available search result projection\u002Flimit, invoke only the discovered read tool needed for the next diagnostic step, and avoid repeating broad searches when the relevant tool name is already known.\n- If a discovery server returns full schemas only, record the output-size or latency cost and treat compact discovery\u002Fprojection support as a follow-up rather than repeatedly requesting unrelated schemas.\n- Cite external claims with stable URLs; cite local claims as `path:line` or a precise section.\n- Do not implement, settle product or architecture choices, or present an inference as fact.\n- Escalate to `deep-research` for multiple interacting unknowns, several source classes, conflicting evidence, historical\u002Fprotocol analysis, or an exhaustive request.\n- In delegated results, return `ASK_WORKFLOW_PASS phase=RESEARCH` only when the stated question is answered or remaining gaps are explicitly actionable. Use `ASK_WORKFLOW_BLOCKED phase=RESEARCH` when essential evidence is inaccessible. Never include workflow markers in the final user-facing response.\n\n## Output\n\n```text\nAnswer\nEvidence: source - observation\nConfidence: CONFIRMED | HIGH | MEDIUM | LOW | SPECULATIVE | UNKNOWN\nDecision impact\nHandoff: next owner, recommended action, protected scope, and required proof\nOpen questions \u002F next evidence needed\n```\n\n## Use with\n\n- `deep-research` when bounded investigation expands into a multi-track program\n- `intake` to scope a decision after facts are known\n- `debugging` to trace and fix a defect revealed by evidence\n- `develop` to implement an evidence-backed recommendation\n\n## Avoid\n\n- Treating a search-result snippet as evidence\n- Starting broad repository audits; use `improve`\n- Repeated permission questions when the next evidence source is clear\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","cef5fa0ba7fd07c76ac37b31c2d09db85419e0b9",".github\u002Fskills\u002Fask-research",0,"https:\u002F\u002Fgithub.com\u002FMarkBovee\u002Fagent-skills-kit","https:\u002F\u002Fgithub.com\u002FMarkBovee","2026-11-09 02:17:08",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":24},[34,37,40],{"tool":35,"command":36},"npx","npx skills add MarkBovee\u002Fagent-skills-kit --skill ask-research",{"tool":38,"command":39},"bunx","bunx skills add MarkBovee\u002Fagent-skills-kit --skill ask-research",{"tool":41,"command":42},"pnpm","pnpm dlx skills add MarkBovee\u002Fagent-skills-kit --skill ask-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMarkBovee\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fask-research\u002FSKILL.md",[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7343K5655Z7JCBPJKXMC24K","ask-write-skill","Write Skill: Creates and revises skills and guardrails from reusable workflow gaps. Use when making a skill or when agent behavior exposes a routing gap.","https:\u002F\u002Fgithub.com\u002FMarkBovee\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002Fskills\u002Fask-write-skill\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7343G7HSVYVB1BKK49ZD04R","ask-verification","Verification: Proves work is fixed or ready and cleans up changed repos. Use before claiming something works or handing off.","https:\u002F\u002Fgithub.com\u002FMarkBovee\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002Fskills\u002Fask-verification\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7343D2RDXYZRRQWJKW15MHW","ask-text-writing","Text Writing: Writes emails, posts, articles, bios, READMEs, and docs that sound human and avoid AI writing patterns. Use when drafting or rewriting prose.","https:\u002F\u002Fgithub.com\u002FMarkBovee\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002Fskills\u002Fask-text-writing\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7343A980X77TDWV0FZAYBS2","ask-summary","Summary: Explains what changed and what is proven, walks through code, or re-pitches unclear output. Use when work is done or the user asks what changed.","https:\u002F\u002Fgithub.com\u002FMarkBovee\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002Fskills\u002Fask-summary\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M73438ARMNM8W991A7EPGRG1","ask-session-review","Session Review: Reflects on skill usage and gaps and files GitHub issues from bugs, findings, or follow-ups. Use after completing work.","https:\u002F\u002Fgithub.com\u002FMarkBovee\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002Fskills\u002Fask-session-review\u002FSKILL.md",[],[],{"skillNo":82,"name":5,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M734362MZYM4CT488AAFX84G","Research: Does bounded fact-finding across the repository, docs, code, or external sources. Use when a question needs evidence before an answer or decision.","https:\u002F\u002Fgithub.com\u002FMarkBovee\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002Fskills\u002Fask-research\u002FSKILL.md",[],[]]