[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QWK8VB54WP2H9PJC3PQ7PX":3,"skill-same:01M6QWK8VB54WP2H9PJC3PQ7PX":65},{"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":23,"publishedAt":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":48,"ownerDescription":49,"updatedAt":50,"install":51,"resources":64},"01M6QWK8VB54WP2H9PJC3PQ7PX","session-to-skill",null,"Use when the user wants to turn one or more Entire-tracked sessions, checkpoints, or repeated agent workflows into a reusable agent skill.","entireio\u002Fskills","entireio","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F33188652?v=4","01M6QWH3SDS1SFGPZG68QWNVJJ","Entire","01M6QWH3XNXJ1RQP56F4ED3X02",240,"MIT","https:\u002F\u002Fgithub.com\u002Fentireio\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fsession-to-skill\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36],"session","session to skill","workflows","sessions","user","use","reusable","agent skill","agent workflows","checkpoints","more","entire","when","2026-11-10 10:12:30",false,"---\nname: session-to-skill\ndescription: Use when the user wants to turn one or more Entire-tracked sessions, checkpoints, or repeated agent workflows into a reusable agent skill.\n---\n\n# Session To Skill\n\nUse this skill to help the user turn Entire session history into a focused skill draft.\n\nThe goal is not to convert a whole transcript mechanically. Treat sessions and checkpoints as source material, then extract the reusable workflow the user wants to repeat.\n\n## Response Format\n\nBegin the first response to this skill invocation with the line:\n\n`Entire Session To Skill:`\n\nfollowed by a blank line, then the content.\n\n- Apply the header to the **first response of the invocation only.** Do not re-print it on follow-up turns within the same invocation.\n- Do **not** include the header on error or early-exit responses, such as when Entire is not installed, the current directory is not a git repository, no relevant sessions are found, or the user has not identified what reusable behavior they want.\n\n## Rules\n\n1. First identify the reusable behavior the skill should capture. If the user has not said what the skill should help with, ask that question before reading transcripts.\n2. Use Entire history as evidence. Prefer `entire search`, `entire session current`, session metadata files, and `entire checkpoint explain` over asking the user to paste old transcripts.\n3. A skill draft should be focused on future behavior, not a recap of the session. Preserve durable workflow, repo conventions, user corrections, commands, validation, and things to avoid.\n4. When several sessions may be relevant, summarize the repeated workflow pattern, recommend a source set, and ask the user to confirm before expanding transcripts.\n5. Do not write, install, or overwrite a skill file unless the user explicitly approves the destination. By default, present the `SKILL.md` draft in the response.\n6. Do not include secrets, private credentials, raw logs, or unnecessary transcript detail in the generated skill.\n\n## Workflow\n\n### 1. Clarify The Skill Target\n\nIf the user gives a clear target, continue. Examples:\n\n- \"turn my blog publishing workflow into a skill\"\n- \"make a skill from session 019...\"\n- \"I keep doing release note drafting; make that reusable\"\n\nIf the target is vague, ask:\n\n```text\nWhat should this skill help you do repeatedly?\n```\n\nIf the user wants a specific skill name, use it. Otherwise infer a short hyphen-case name from the target, then confirm it before writing files.\n\n### 2. Infer The Repeated Pattern\n\nIf the user gives a checkpoint ID, skip to checkpoint expansion.\n\nIf the user gives a session ID, read its metadata with:\n\n```bash\nentire session info \u003Csession-id> --json\n```\n\nIt reports `agent`, `status`, `started_at`, `turns`, and, when known, `last_active`, `last_prompt`, and `files_touched`. If the command fails, read the state file directly from the git common directory (shared by every worktree):\n\n```bash\ncat \"$(git rev-parse --path-format=absolute --git-common-dir)\u002Fentire-sessions\u002F\u003Csession-id>.json\"\n```\n\nIf the user describes a repeated workflow but does not give a session or checkpoint, search Entire history with terms from the target:\n\n```bash\nentire search \"\u003Cworkflow terms>\" --json\n```\n\nUse repo, branch, author, or date filters when the user provides them:\n\n```bash\nentire search \"\u003Cworkflow terms>\" --json --repo owner\u002Fname --branch branch-name --author \"Name\" --date month\n```\n\nInterpret search results carefully:\n\n- If `entire search` returns valid JSON with `\"total\": 0` or an empty `results` array, do **not** call it an authentication failure. Say no indexed matches were found, then fall back to local session metadata.\n- Only say authentication is required if the command output explicitly says authentication, login, or credentials are required.\n- If search fails for any other reason, report the short error and fall back to local session metadata when available.\n\nWhen falling back locally, run `entire session list --json` and match each entry's `last_prompt`, `files_touched`, `started_at`, `last_active`, and `agent` against the user's workflow terms. If that command fails, inspect `$(git rev-parse --path-format=absolute --git-common-dir)\u002Fentire-sessions\u002F*.json` and match `last_prompt`, `files_touched`, `started_at`, `last_interaction_time`, and `agent_type` instead.\n\nReview the top results and infer the repeated workflow pattern before showing raw session choices. Lead with the pattern, not the IDs.\n\nPresent:\n\n- the repeated workflow you think the user wants to capture\n- the strongest source set you recommend using\n- what each source contributes in plain language, such as \"core workflow\", \"image handling\", \"validation\", or \"copy-editing pattern\"\n- any sessions you plan to ignore because they look metadata-only, duplicate, or one-off\n\nKeep session IDs and checkpoint IDs as supporting details, not the main decision surface. Ask the user to confirm the pattern and source set before expanding detailed transcripts.\n\nExample:\n\n```text\nI found a repeated workflow: publishing blog posts in entire.io from drafts, using repo-specific front matter, slugged asset folders, user-provided images, and website checks.\n\nI recommend using the strongest matching sessions as source material:\n- core workflow: \u003Csession-id>\n- image handling: \u003Csession-id>\n- validation mechanics: \u003Csession-id>\n\nI will ignore metadata-only or one-off edit sessions unless you want them included. Should I continue with this source set?\n```\n\n### 3. Read Source Material\n\nFor a checkpoint, run:\n\n```bash\nentire checkpoint explain --checkpoint \u003Ccheckpoint-id> --full --no-pager\n```\n\nIf full output fails and the user wants more detail, fall back to:\n\n```bash\nentire checkpoint explain --checkpoint \u003Ccheckpoint-id> --raw-transcript --no-pager\n```\n\nFor an active or current session, read its metadata with `entire session current --json`, then stream its transcript to a file:\n\n```bash\nentire session current --transcript > \u002Ftmp\u002Fskill-src-current.jsonl\n```\n\nFor another session, use `entire session info \u003Csession-id> --transcript > \u002Ftmp\u002Fskill-src-\u003Csession-id>.jsonl`. Use the resulting file as `\u003Ctranscript_path>` below.\n\nIf these commands fail, use the session metadata fallback directly: inspect `$(git rev-parse --path-format=absolute --git-common-dir)\u002Fentire-sessions\u002F*.json`, pick the relevant session by `last_interaction_time`, `started_at`, `agent_type`, or the user's requested agent, then extract `transcript_path`.\n\nWhen reading a raw transcript, extract relevant conversation and tool-call lines without dumping them to the user:\n\n```bash\ngrep -E '\"type\":\"(message|function_call|user|assistant)\"' \u003Ctranscript_path> | cut -c1-2000\n```\n\nFor large transcripts, inspect the first prompts and final state first:\n\n```bash\ngrep -E '\"type\":\"(message|function_call|user|assistant)\"' \u003Ctranscript_path> | head -40 | cut -c1-2000\ngrep -E '\"type\":\"(message|function_call|user|assistant)\"' \u003Ctranscript_path> | tail -160 | cut -c1-2000\n```\n\nIf the session metadata lists files touched, inspect only files needed to understand durable conventions. Avoid broad repo exploration unless the skill target requires it.\n\n### 4. Extract Durable Lessons\n\nBefore drafting, privately identify:\n\n- the repeated goal the future skill should accomplish\n- triggers that should activate the skill\n- required inputs the future agent should ask for\n- repo-specific paths, file formats, front matter, naming, or asset placement\n- commands and checks that proved the workflow worked\n- user corrections and preferences from the session\n- failed approaches or behaviors to avoid\n- what was one-off and should not go into the skill\n\nIf multiple sessions were selected, combine only the repeated or clearly reusable lessons. Do not average contradictory instructions; ask the user to choose when sessions disagree.\n\n### 5. Draft The Skill\n\nCreate a complete `SKILL.md` draft with required front matter:\n\n```markdown\n---\nname: \u003Chyphen-case-skill-name>\ndescription: Use when \u003Cspecific trigger and task>.\n---\n```\n\nThe body should include:\n\n- a short purpose statement\n- clear rules or guardrails\n- a step-by-step workflow\n- exact commands only when they are part of the reusable behavior\n- expected outputs and validation steps\n- failure handling or when to ask the user\n\nKeep the skill concise. Do not include the session recap, full transcript excerpts, checkpoint IDs, or implementation notes unless they are essential to future use.\n\n### 6. Deliver And Offer Installation\n\nPresent the `SKILL.md` draft first unless the user already gave an explicit write path.\n\nAfter presenting the draft, ask whether the user wants it installed globally. Recommend the cross-agent path:\n\n```text\n~\u002F.agents\u002Fskills\u002F\u003Cskill-name>\u002FSKILL.md\n```\n\nUse this install prompt shape:\n\n```text\nDo you want me to install this skill globally?\n\nRecommended:\n- Cross-agent: ~\u002F.agents\u002Fskills\u002F\u003Cskill-name>\u002FSKILL.md\n\nOther options:\n- Codex only: ~\u002F.codex\u002Fskills\u002F\u003Cskill-name>\u002FSKILL.md\n- Write to a repo-local draft: skills\u002F\u003Cskill-name>\u002FSKILL.md\n- Leave as draft only\n```\n\nOnly write files after the user chooses a destination. If the destination already exists, ask before overwriting it.\n\nDo not create symlinks unless the user explicitly asks for a development-linked install. If they ask for a symlink, explain the source and target paths before creating it.\n\nAfter writing a skill file, summarize:\n\n- where it was written\n- which session(s) or checkpoint(s) informed it\n- any assumptions or open questions\n","# Session To Skill\n\nUse this skill to help the user turn Entire session history into a focused skill draft.\n\nThe goal is not to convert a whole transcript mechanically. Treat sessions and checkpoints as source material, then extract the reusable workflow the user wants to repeat.\n\n## Response Format\n\nBegin the first response to this skill invocation with the line:\n\n`Entire Session To Skill:`\n\nfollowed by a blank line, then the content.\n\n- Apply the header to the **first response of the invocation only.** Do not re-print it on follow-up turns within the same invocation.\n- Do **not** include the header on error or early-exit responses, such as when Entire is not installed, the current directory is not a git repository, no relevant sessions are found, or the user has not identified what reusable behavior they want.\n\n## Rules\n\n1. First identify the reusable behavior the skill should capture. If the user has not said what the skill should help with, ask that question before reading transcripts.\n2. Use Entire history as evidence. Prefer `entire search`, `entire session current`, session metadata files, and `entire checkpoint explain` over asking the user to paste old transcripts.\n3. A skill draft should be focused on future behavior, not a recap of the session. Preserve durable workflow, repo conventions, user corrections, commands, validation, and things to avoid.\n4. When several sessions may be relevant, summarize the repeated workflow pattern, recommend a source set, and ask the user to confirm before expanding transcripts.\n5. Do not write, install, or overwrite a skill file unless the user explicitly approves the destination. By default, present the `SKILL.md` draft in the response.\n6. Do not include secrets, private credentials, raw logs, or unnecessary transcript detail in the generated skill.\n\n## Workflow\n\n### 1. Clarify The Skill Target\n\nIf the user gives a clear target, continue. Examples:\n\n- \"turn my blog publishing workflow into a skill\"\n- \"make a skill from session 019...\"\n- \"I keep doing release note drafting; make that reusable\"\n\nIf the target is vague, ask:\n\n```text\nWhat should this skill help you do repeatedly?\n```\n\nIf the user wants a specific skill name, use it. Otherwise infer a short hyphen-case name from the target, then confirm it before writing files.\n\n### 2. Infer The Repeated Pattern\n\nIf the user gives a checkpoint ID, skip to checkpoint expansion.\n\nIf the user gives a session ID, read its metadata with:\n\n```bash\nentire session info \u003Csession-id> --json\n```\n\nIt reports `agent`, `status`, `started_at`, `turns`, and, when known, `last_active`, `last_prompt`, and `files_touched`. If the command fails, read the state file directly from the git common directory (shared by every worktree):\n\n```bash\ncat \"$(git rev-parse --path-format=absolute --git-common-dir)\u002Fentire-sessions\u002F\u003Csession-id>.json\"\n```\n\nIf the user describes a repeated workflow but does not give a session or checkpoint, search Entire history with terms from the target:\n\n```bash\nentire search \"\u003Cworkflow terms>\" --json\n```\n\nUse repo, branch, author, or date filters when the user provides them:\n\n```bash\nentire search \"\u003Cworkflow terms>\" --json --repo owner\u002Fname --branch branch-name --author \"Name\" --date month\n```\n\nInterpret search results carefully:\n\n- If `entire search` returns valid JSON with `\"total\": 0` or an empty `results` array, do **not** call it an authentication failure. Say no indexed matches were found, then fall back to local session metadata.\n- Only say authentication is required if the command output explicitly says authentication, login, or credentials are required.\n- If search fails for any other reason, report the short error and fall back to local session metadata when available.\n\nWhen falling back locally, run `entire session list --json` and match each entry's `last_prompt`, `files_touched`, `started_at`, `last_active`, and `agent` against the user's workflow terms. If that command fails, inspect `$(git rev-parse --path-format=absolute --git-common-dir)\u002Fentire-sessions\u002F*.json` and match `last_prompt`, `files_touched`, `started_at`, `last_interaction_time`, and `agent_type` instead.\n\nReview the top results and infer the repeated workflow pattern before showing raw session choices. Lead with the pattern, not the IDs.\n\nPresent:\n\n- the repeated workflow you think the user wants to capture\n- the strongest source set you recommend using\n- what each source contributes in plain language, such as \"core workflow\", \"image handling\", \"validation\", or \"copy-editing pattern\"\n- any sessions you plan to ignore because they look metadata-only, duplicate, or one-off\n\nKeep session IDs and checkpoint IDs as supporting details, not the main decision surface. Ask the user to confirm the pattern and source set before expanding detailed transcripts.\n\nExample:\n\n```text\nI found a repeated workflow: publishing blog posts in entire.io from drafts, using repo-specific front matter, slugged asset folders, user-provided images, and website checks.\n\nI recommend using the strongest matching sessions as source material:\n- core workflow: \u003Csession-id>\n- image handling: \u003Csession-id>\n- validation mechanics: \u003Csession-id>\n\nI will ignore metadata-only or one-off edit sessions unless you want them included. Should I continue with this source set?\n```\n\n### 3. Read Source Material\n\nFor a checkpoint, run:\n\n```bash\nentire checkpoint explain --checkpoint \u003Ccheckpoint-id> --full --no-pager\n```\n\nIf full output fails and the user wants more detail, fall back to:\n\n```bash\nentire checkpoint explain --checkpoint \u003Ccheckpoint-id> --raw-transcript --no-pager\n```\n\nFor an active or current session, read its metadata with `entire session current --json`, then stream its transcript to a file:\n\n```bash\nentire session current --transcript > \u002Ftmp\u002Fskill-src-current.jsonl\n```\n\nFor another session, use `entire session info \u003Csession-id> --transcript > \u002Ftmp\u002Fskill-src-\u003Csession-id>.jsonl`. Use the resulting file as `\u003Ctranscript_path>` below.\n\nIf these commands fail, use the session metadata fallback directly: inspect `$(git rev-parse --path-format=absolute --git-common-dir)\u002Fentire-sessions\u002F*.json`, pick the relevant session by `last_interaction_time`, `started_at`, `agent_type`, or the user's requested agent, then extract `transcript_path`.\n\nWhen reading a raw transcript, extract relevant conversation and tool-call lines without dumping them to the user:\n\n```bash\ngrep -E '\"type\":\"(message|function_call|user|assistant)\"' \u003Ctranscript_path> | cut -c1-2000\n```\n\nFor large transcripts, inspect the first prompts and final state first:\n\n```bash\ngrep -E '\"type\":\"(message|function_call|user|assistant)\"' \u003Ctranscript_path> | head -40 | cut -c1-2000\ngrep -E '\"type\":\"(message|function_call|user|assistant)\"' \u003Ctranscript_path> | tail -160 | cut -c1-2000\n```\n\nIf the session metadata lists files touched, inspect only files needed to understand durable conventions. Avoid broad repo exploration unless the skill target requires it.\n\n### 4. Extract Durable Lessons\n\nBefore drafting, privately identify:\n\n- the repeated goal the future skill should accomplish\n- triggers that should activate the skill\n- required inputs the future agent should ask for\n- repo-specific paths, file formats, front matter, naming, or asset placement\n- commands and checks that proved the workflow worked\n- user corrections and preferences from the session\n- failed approaches or behaviors to avoid\n- what was one-off and should not go into the skill\n\nIf multiple sessions were selected, combine only the repeated or clearly reusable lessons. Do not average contradictory instructions; ask the user to choose when sessions disagree.\n\n### 5. Draft The Skill\n\nCreate a complete `SKILL.md` draft with required front matter:\n\n```markdown\n---\nname: \u003Chyphen-case-skill-name>\ndescription: Use when \u003Cspecific trigger and task>.\n---\n```\n\nThe body should include:\n\n- a short purpose statement\n- clear rules or guardrails\n- a step-by-step workflow\n- exact commands only when they are part of the reusable behavior\n- expected outputs and validation steps\n- failure handling or when to ask the user\n\nKeep the skill concise. Do not include the session recap, full transcript excerpts, checkpoint IDs, or implementation notes unless they are essential to future use.\n\n### 6. Deliver And Offer Installation\n\nPresent the `SKILL.md` draft first unless the user already gave an explicit write path.\n\nAfter presenting the draft, ask whether the user wants it installed globally. Recommend the cross-agent path:\n\n```text\n~\u002F.agents\u002Fskills\u002F\u003Cskill-name>\u002FSKILL.md\n```\n\nUse this install prompt shape:\n\n```text\nDo you want me to install this skill globally?\n\nRecommended:\n- Cross-agent: ~\u002F.agents\u002Fskills\u002F\u003Cskill-name>\u002FSKILL.md\n\nOther options:\n- Codex only: ~\u002F.codex\u002Fskills\u002F\u003Cskill-name>\u002FSKILL.md\n- Write to a repo-local draft: skills\u002F\u003Cskill-name>\u002FSKILL.md\n- Leave as draft only\n```\n\nOnly write files after the user chooses a destination. If the destination already exists, ask before overwriting it.\n\nDo not create symlinks unless the user explicitly asks for a development-linked install. If they ask for a symlink, explain the source and target paths before creating it.\n\nAfter writing a skill file, summarize:\n\n- where it was written\n- which session(s) or checkpoint(s) informed it\n- any assumptions or open questions\n",{"name":5,"description":7},"main","11902e22deddf7b867ea1cf958c0220288be4d63","skills\u002Fsession-to-skill",28,"https:\u002F\u002Fgithub.com\u002Fentireio\u002Fskills","https:\u002F\u002Fgithub.com\u002Fentireio","https:\u002F\u002Fentire.com","Entire is a new developer platform that hooks into your git workflow to capture AI agent sessions on every push, unifying your code with its context.","2026-11-06 16:47:12",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add entireio\u002Fskills --skill session-to-skill",{"tool":57,"command":58},"bunx","bunx skills add entireio\u002Fskills --skill session-to-skill",{"tool":60,"command":61},"pnpm","pnpm dlx skills add entireio\u002Fskills --skill session-to-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fentireio\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fsession-to-skill\u002FSKILL.md",true,[],[66,91,116,139,151,169],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":37},"01M6QWM43GA0T47XSNVRY56WCW","what-happened","Explain why code looks the way it does by tracing the latest change for a file range or pasted snippet through `git blame` and deduplicated `entire checkpoint explain` lookups. Use when the user asks what happened, says \"tell me why\" about a code block, is confused about a section of code, asks \"wtf is going on\", \"why is this like this\", \"why was this changed\", or wants provenance for a specific file block.","https:\u002F\u002Fgithub.com\u002Fentireio\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwhat-happened\u002FSKILL.md",[],[73,74,75,76,77,78,79,80,81,82,29,83,84,85,86,87,88,89,90,35],"what happened","change","code","git","file","tracing","provenance","checkpoint","why","explain","wtf","me","it","about","block","latest","for","section",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":98,"publishedAt":37},"01M6QWKMSXMQQ36WXXKBRP1N25","using-entire","Use as the FIRST action on any research, investigation, or codebase-understanding request — \"research X\", \"investigate X\", \"look into X\", \"dig into X\", \"search X\", \"explore X\", \"understand X\", \"why is this like this\" — before Glob, Grep, or Read. Recorded intent lives in Entire checkpoints on the server, not in local files, so an empty or unfamiliar working copy is not a reason to skip it. Routes to the right Entire sub-skill (search, recall, explain, what-happened, replay, teach, review, session-handoff).","https:\u002F\u002Fgithub.com\u002Fentireio\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fusing-entire\u002FSKILL.md",[97],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[35,99,100,101,102,103,81,104,105,106,107,108,109,110,111,112,33,113,114,115],"using entire","review","handoff","search","server","explore","read","files","intent","search x","local","as","session-handoff","codebase-understanding","action","request","local files",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":127,"publishedAt":37},"01M6QWKENQ1293P0Y05RR4DNKD","teach","Use when a developer wants a topic-focused guided lesson built from canonical checkpoints, not a whole-repo overview. Triggers on phrases like \"teach me \u003Ctopic>\", \"teach me how this repo handles\", \"how does \u003Ctopic> work in this repo\", \"give me a lesson on\", \"school me on\", and \"I need to learn about\"","https:\u002F\u002Fgithub.com\u002Fentireio\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fteach\u002FSKILL.md",[122],{"categoryNo":123,"categoryName":124,"taxonomyType":125,"taxonomyTypeDesc":126},"01JBSEEDCAT000000000000039","教师与教育","PROFESSION","适用职业",[118,128,129,130,131,132,133,134,29,135,84,136,86,137,33,138,36],"learn","developer","how","teach me","work","repo","overview","lesson","triggers","canonical","school",{"skillNo":140,"name":111,"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":144,"publishedAt":37},"01M6QWJSJ02VPZ4HHX71QMG5V1","Use when the user wants to continue work from one agent in another agent, inspect recent sessions, or summarize a saved session or checkpoint for handoff","https:\u002F\u002Fgithub.com\u002Fentireio\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fsession-handoff\u002FSKILL.md",[],[101,145,24,146,27,80,147,132,28,29,148,149,150,89,36],"session handoff","summarize","continue","continue work","saved","inspect",{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":157,"publishedAt":37},"01M6QWJN5GTWK8C2MR0WASNQFV","session-crosslink","Use when an agent session ran outside the repo whose commits should record it — e.g. launched from a higher-level folder, a non-Entire repo, or one repo but editing another — to attach the session to each affected Entire-enabled repo's HEAD commit.","https:\u002F\u002Fgithub.com\u002Fentireio\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fsession-crosslink\u002FSKILL.md",[],[24,158,159,160,161,133,29,162,163,164,165,85,166,167,35,36,168],"session crosslink","commit","commits","editing","attach","but","record","head","folder","affected","agent session",{"skillNo":170,"name":102,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":174,"publishedAt":37},"01M6QWJHAAEM30G2KG1MMKEEN0","Use when the user asks to research, investigate, look into, dig into, or search for anything — a topic, feature, bug, decision, or \"what do we know about X\". Invoke this as the FIRST action on such requests, before Glob, Grep, or Read: the answer is in Entire's recorded history (prompts, transcripts, and decisions, across repos), not in the local files, and a working copy that looks empty or unfamiliar is not a reason to skip it. Also use to find code across repositories (\"where is X implemented in our other repos\"). Not for grepping the current working copy on its own, and not for the current active session.","https:\u002F\u002Fgithub.com\u002Fentireio\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fsearch\u002FSKILL.md",[],[102,175,75,176,177,105,178,106,179,180,181,109,182,110,183,113,89,115,184,36],"repos","decision","history","bug","do","active","across","feature","answer","invoke"]