[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69BGYAYC16BRSB0EGMCKMF5":3,"skill-same:01M69BGYAYC16BRSB0EGMCKMF5":88},{"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":22,"linkOnly":23,"markdownContent":24,"markdownBody":25,"frontMatter":26,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":37,"updatedAt":38,"install":39,"resources":51},"01M69BGYAYC16BRSB0EGMCKMF5","transcript",null,"Retrieve the prior user and assistant conversation verbatim from the current Context Intelligence capture, or named sessions. Use when a user asks to replay, quote, review, or act on a transcript.","microsoft\u002Famplifier-bundle-context-intelligence","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69BGBVCCWXG1MNNF1E8TCWN",5,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-bundle-context-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Ftranscript\u002FSKILL.md",[],[5,19,20,21],"assistant","review","sessions","2026-11-10 10:12:30",false,"---\nname: transcript\ndescription: Retrieve the prior user and assistant conversation verbatim from the current Context Intelligence capture, or named sessions. Use when a user asks to replay, quote, review, or act on a transcript.\nversion: 1.2.0\nlicense: MIT\nuser-invocable: true\ncompatibility: Amplifier with the session_transcript tool mounted\n---\n\n# Transcript\n\nUse `session_transcript`; never read `events.jsonl` directly.\n\nInvoking this skill is a request to retrieve the transcript, not to explain how\nto retrieve it. Call `session_transcript` in this turn using the arguments below.\nDo not stop after loading the skill, present a proposed tool call, or ask \"shall\nI retrieve it?\" The user's request already authorizes this read. Only ask for\nID clarification after the tool reports ambiguity; honor any actual tool\npermission gate or explicit user restriction.\n\n> **Sensitive content:** stored captures are replayed verbatim and can contain\n> sensitive content. The logging hook's JSON sanitization is not redaction.\n\nInterpret `$ARGUMENTS` as follows:\n\n- **`ID` or `ID -- \u003Cintent>`:** a bare full session ID or a hex ID prefix of\n  at least 8 characters (for example, `\u002Ftranscript abcdef12`) selects that\n  session. Pass it unchanged in `session_ids`; the tool resolves it. Do not\n  ask for the full ID first or treat it as an instruction about the current\n  session. With no intent, replay verbatim; with intent, retrieve first, then\n  perform that intent.\n- **No arguments:** call `session_transcript` with no `session_ids`. Return the\n  complete role-marked transcript pages verbatim. Do not summarize or add\n  commentary.\n- **Intent only:** call `session_transcript` with no `session_ids`, page through\n  the whole transcript, then perform the requested intent using it as source\n  material. State that the answer was based on the native transcript.\n- **`--session ID[,ID...]`:** retrieve those sessions in the listed order. With\n  no further intent, replay each transcript verbatim under its own session\n  heading.\n- **`--session ID[,ID...] -- \u003Cintent>`:** retrieve all named sessions first,\n  then perform the intent using those transcripts.\n\nA bare token selects a session only when it actually looks like a capture ID:\neight or more hex characters (`abcdef12`, a full UUID), or the zero-padded\nsub-agent form `0000000000000000-\u003Chex>[_\u003Cagent>]`. Anything else is intent about\nthe current session, even when it contains a hyphen, underscore, or digit —\n`chapter-2` and `summarize-day-3` are intents, not IDs. When a token could be\nread either way, treat it as intent: a wrong intent is visible and recoverable,\na wrong lookup just fails. For an opaque ID that does not match those shapes,\nuse explicit `--session`, which accepts unique prefixes and exact opaque IDs.\nIf natural language explicitly names a session, pass that ID or prefix to the\ntool as well.\n\nOn an ambiguous prefix, show the tool's candidates and pass on the length it\nreports as needed — it names the character position where the candidates\ndiverge, so relay that rather than asking vaguely for \"a longer prefix\". On a\nmissing session, report that failure. Never choose a candidate, retry against\nthe current session, or delegate to an agent to guess an ID.\n\nA session whose capture directory exists but has no readable `metadata.json` is\nreported as `capture_unavailable`, and an ID whose only captures are derived\n`\u003Cid>_\u003Cagent>` sub-agent sessions is reported as `session_not_found` listing\nthose sub-agents. Neither is a prompt to substitute one of them; report what the\ntool said.\n\nFor a single session, keep calling `session_transcript` with its returned\nfull `session_id` and `next_after_event_line` as the next `after_event_line`\nwhile `has_more` is true. For multiple sessions, retrieve and\npage one session at a time. For a batched follow-up, replace the original prefixes\nin `session_ids` with returned full IDs and use those same full IDs as\n`after_event_lines` keys. A page boundary is normal; preserve the tool's\n`[MORE MESSAGES AVAILABLE ...]` marker between pages. Do not hide capture\nissues, infer missing messages, use graph reconstruction, or fall back to raw\nprovider events.\n","# Transcript\n\nUse `session_transcript`; never read `events.jsonl` directly.\n\nInvoking this skill is a request to retrieve the transcript, not to explain how\nto retrieve it. Call `session_transcript` in this turn using the arguments below.\nDo not stop after loading the skill, present a proposed tool call, or ask \"shall\nI retrieve it?\" The user's request already authorizes this read. Only ask for\nID clarification after the tool reports ambiguity; honor any actual tool\npermission gate or explicit user restriction.\n\n> **Sensitive content:** stored captures are replayed verbatim and can contain\n> sensitive content. The logging hook's JSON sanitization is not redaction.\n\nInterpret `$ARGUMENTS` as follows:\n\n- **`ID` or `ID -- \u003Cintent>`:** a bare full session ID or a hex ID prefix of\n  at least 8 characters (for example, `\u002Ftranscript abcdef12`) selects that\n  session. Pass it unchanged in `session_ids`; the tool resolves it. Do not\n  ask for the full ID first or treat it as an instruction about the current\n  session. With no intent, replay verbatim; with intent, retrieve first, then\n  perform that intent.\n- **No arguments:** call `session_transcript` with no `session_ids`. Return the\n  complete role-marked transcript pages verbatim. Do not summarize or add\n  commentary.\n- **Intent only:** call `session_transcript` with no `session_ids`, page through\n  the whole transcript, then perform the requested intent using it as source\n  material. State that the answer was based on the native transcript.\n- **`--session ID[,ID...]`:** retrieve those sessions in the listed order. With\n  no further intent, replay each transcript verbatim under its own session\n  heading.\n- **`--session ID[,ID...] -- \u003Cintent>`:** retrieve all named sessions first,\n  then perform the intent using those transcripts.\n\nA bare token selects a session only when it actually looks like a capture ID:\neight or more hex characters (`abcdef12`, a full UUID), or the zero-padded\nsub-agent form `0000000000000000-\u003Chex>[_\u003Cagent>]`. Anything else is intent about\nthe current session, even when it contains a hyphen, underscore, or digit —\n`chapter-2` and `summarize-day-3` are intents, not IDs. When a token could be\nread either way, treat it as intent: a wrong intent is visible and recoverable,\na wrong lookup just fails. For an opaque ID that does not match those shapes,\nuse explicit `--session`, which accepts unique prefixes and exact opaque IDs.\nIf natural language explicitly names a session, pass that ID or prefix to the\ntool as well.\n\nOn an ambiguous prefix, show the tool's candidates and pass on the length it\nreports as needed — it names the character position where the candidates\ndiverge, so relay that rather than asking vaguely for \"a longer prefix\". On a\nmissing session, report that failure. Never choose a candidate, retry against\nthe current session, or delegate to an agent to guess an ID.\n\nA session whose capture directory exists but has no readable `metadata.json` is\nreported as `capture_unavailable`, and an ID whose only captures are derived\n`\u003Cid>_\u003Cagent>` sub-agent sessions is reported as `session_not_found` listing\nthose sub-agents. Neither is a prompt to substitute one of them; report what the\ntool said.\n\nFor a single session, keep calling `session_transcript` with its returned\nfull `session_id` and `next_after_event_line` as the next `after_event_line`\nwhile `has_more` is true. For multiple sessions, retrieve and\npage one session at a time. For a batched follow-up, replace the original prefixes\nin `session_ids` with returned full IDs and use those same full IDs as\n`after_event_lines` keys. A page boundary is normal; preserve the tool's\n`[MORE MESSAGES AVAILABLE ...]` marker between pages. Do not hide capture\nissues, infer missing messages, use graph reconstruction, or fall back to raw\nprovider events.\n",{"name":5,"license":15,"version":27,"description":7,"compatibility":28,"user-invocable":29},"1.2.0","Amplifier with the session_transcript tool mounted",true,"main","2a8d7bd1e022971c395ec38ed797bf75fcf7aff7","skills\u002Ftranscript",7,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-bundle-context-intelligence","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-14 02:56:59",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":29},[41,44,47],{"tool":42,"command":43},"npx","npx skills add microsoft\u002Famplifier-bundle-context-intelligence --skill transcript",{"tool":45,"command":46},"bunx","bunx skills add microsoft\u002Famplifier-bundle-context-intelligence --skill transcript",{"tool":48,"command":49},"pnpm","pnpm dlx skills add microsoft\u002Famplifier-bundle-context-intelligence --skill transcript","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-bundle-context-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Ftranscript\u002FSKILL.md",[52,58,64,70,74,78,82],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"examples\u002Fappinsights.bicep","OTHER","其他",759,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fappinsights-instrumentation\u002Fexamples\u002Fappinsights.bicep",{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"LICENSE.txt","LICENSE","许可证",1078,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fappinsights-instrumentation\u002FLICENSE.txt",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002FASPNETCORE.md","REFERENCE","参考文档",1717,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fappinsights-instrumentation\u002Freferences\u002FASPNETCORE.md",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002FAUTO.md",891,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fappinsights-instrumentation\u002Freferences\u002FAUTO.md",{"path":75,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002FNODEJS.md",1815,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fappinsights-instrumentation\u002Freferences\u002FNODEJS.md",{"path":79,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002FPYTHON.md",1812,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fappinsights-instrumentation\u002Freferences\u002FPYTHON.md",{"path":83,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":86,"sourceHtmlUrl":87},"scripts\u002Fappinsights.ps1","SCRIPT","脚本",1221,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fappinsights-instrumentation\u002Fscripts\u002Fappinsights.ps1",[89,105,122,130,138,154],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":100,"publishedAt":22},"01M69BGZVPJBKSZV5N0WMVGR3N","workflow-pattern-analysis","Use when asked how a workflow is failing, what separates a successful run from a failing one, which steps are the most common failure points, or what patterns recur across sessions — analyses failure\u002Fsuccess patterns and signals across many runs using context-intelligence session data.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-bundle-context-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-pattern-analysis\u002FSKILL.md",[95],{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[101,102,21,103,104],"workflow","workflow pattern analysis","run","reasoning",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":119,"publishedAt":22},"01M69BGWQGCEN13DHHAQGTQ609","context-intelligence-tool-design","Use when selecting a detection strategy and implementation primitive for a context-intelligence signal. Classifies signals as deterministic, probabilistic, llm-evaluated, or hybrid, and applies the cheapest-sufficient-capability principle.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-bundle-context-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fcontext-intelligence-tool-design\u002FSKILL.md",[111,114],{"categoryNo":112,"categoryName":113,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":115,"categoryName":116,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[120,121,104],"design","context intelligence tool design",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":22},"01M69BGVHJJFCNZMGM21FNWMFS","context-intelligence-session-reconstruction","Use when local Amplifier session files are missing, broken, or incomplete — rebuilds events.jsonl, transcript.jsonl, and metadata.json from the context-intelligence graph server.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-bundle-context-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fcontext-intelligence-session-reconstruction\u002FSKILL.md",[],[129],"context intelligence session reconstruction",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":22},"01M69BGT14VQD1M3P12WZGTQCS","context-intelligence-session-navigation","Use for workspace-scoped local session discovery and event, tool, error, or capture inspection in JSONL files, independent of graph availability.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-bundle-context-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fcontext-intelligence-session-navigation\u002FSKILL.md",[],[137],"context intelligence session navigation",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":150,"publishedAt":22},"01M69BGRET24BR6PTYANVE57F4","context-intelligence-server-data-ops","Exact step order, wording, and the \"session details\" block format for the delete flows the server-data-ops agent drives — delete the current session, clean up every session from the current working directory, find-then-delete a session by description, and delete a session someone else created.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-bundle-context-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fcontext-intelligence-server-data-ops\u002FSKILL.md",[144,147],{"categoryNo":145,"categoryName":146,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":148,"categoryName":149,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000033","数据分析师",[151,152,153],"context intelligence server data ops","delete","directory",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":160,"publishedAt":22},"01M69BGQ0B4G6VY99C6RGS8Z8T","context-intelligence-hill-climbing","Use when an investigation needs more than one step — track it in todo as a hill climb so progress and dead leads leave an audit trail. Governs HOW you track the climb, not how you query or extract — that stays in graph-query \u002F session-navigation.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-bundle-context-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fcontext-intelligence-hill-climbing\u002FSKILL.md",[],[161],"context intelligence hill climbing"]