[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78ZBMBNBSCTRK36VX766MA5":3,"skill-same:01M78ZBMBNBSCTRK36VX766MA5":75},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M78ZBMBNBSCTRK36VX766MA5","analyze-project",null,"Read project assets (analysis.json) together with surrounding context (intake.json, edit.json, planning\u002F, README, and past projects), create the interpretation layer interpretation.json, and render a read-only analysis report limited to facts and readings of the material. Use to understand a multi-asset project across sources, integrate completed analyze-footage results, or identify missing primary information for interviews before choosing a direction. plan-edit reads this output before deciding direction.","AkariLabs\u002Fakari-video","AkariLabs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F309052672?v=4","01M78ZAVH5RSSCXA5RVB0RQYMW","01M78ZAVHS38JT84VMB4A3KFFB",214,"MIT","https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fskills\u002Fanalyze-project\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: analyze-project\ndescription: Read project assets (analysis.json) together with surrounding context (intake.json, edit.json, planning\u002F, README, and past projects), create the interpretation layer interpretation.json, and render a read-only analysis report limited to facts and readings of the material. Use to understand a multi-asset project across sources, integrate completed analyze-footage results, or identify missing primary information for interviews before choosing a direction. plan-edit reads this output before deciding direction.\n---\n\n# Analyze a project\n\n> **Language**: Respond in the user's language — conversation, questions, approval prompts, and the reports and records you write (including decision-log rows) follow the language the user writes in.\n\nDo not Read all of `edit.json` \u002F `captions.json`; grep by ID and read only matching lines ([Reading edit.json](https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fedit-json-access.md)).\nIn other stages that need writes, Edit the relevant lines or use edit-store's script API.\n\n## Recommend a playbook after source material arrives\n\nOnly immediately after new material is placed, read `.akari\u002Fintake.json` and existing `analysis.json`\nrecords for speakers, duration, orientation, and media kinds, then run `akari playbook list --json`.\nCompare `category`, `tags.form`, `tags.length`, `tags.materials`, and `requires` to the observed material.\nOffer at most three ranked matches in chat, with a specific reason and any missing required tool for each.\nPortrait material with a target at or below 60 seconds favors vertical explainers or short dramas;\ntalking head plus screen capture favors an explainer; music-led material favors an MV.\nPoint to an existing review sheet or to `.akari\u002Freports\u002Fplaybook-apply.html` as the sheet produced on\napplication. Do not apply a playbook until the user selects one. Do not repeat this recommendation later\nin the analysis workflow.\n\n## Hard rules\n\n- **Do not rerun pass 1.** Delegate per-asset fact extraction (heavy processing such as STT\u002Fframe analysis) to existing\n  [analyze-footage](..\u002Fanalyze-footage\u002FSKILL.md) analysis.json files. Run only for missing assets, 1 asset = 1 execution.\n  Use existing analysis.json without modifying it.\n- **Display absent ledger chapters as “unobserved”.** Do not imply they did not exist or fill them by inference\n  from assets\u002Fother chapters. Keep those report chapters visible and marked unobserved; use `observations[]`\n  execution history as evidence when present.\n- **Do not rewatch footage in pass 2.** Limit it to text reasoning over pass-1 outputs (transcript, keyframe notes, events).\n  Return to footage only at pinpointed locations pass 2 determines are necessary.\n- **Pass-2 inputs are not limited to analysis.json files.** Read surrounding project context (intake.json,\n  `planning\u002F`, README, and referenced past projects), and grep edit.json by ID to read relevant lines only.\n  Field validation (internal multiasset-dogfood run, 2026-07-22) confirmed cases where analysis.json alone\n  could not establish asset provenance (orphan\u002Funclear, etc.) confidently.\n- **Include `memory` connections when reading surrounding project context.** If `.akari\u002Fconnections.json`\n  declares `memory` ([contract-2026-07-25-memory-connection-v0.md](https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fdocs\u002Fcontract-2026-07-25-memory-connection-v0.md), Japanese),\n  start at `entry` (default `INDEX.md`) and read only the `include`\u002F`exclude` scope.\n  Record referenced file paths as sources in `interpretation.json`'s `inputs.context`. Full-text ingestion is forbidden.\n  Do nothing if undeclared; this is not an error.\n- **Every interpretation claim requires evidence**: all `assets[].summary`\u002F`role`\u002F`relations`\u002F`flags` and `arc[]`.\n  Evidence is limited to quoted transcript ranges or keyframe-note references. Fabricate nothing.\n  Do not write unsupported claims; send remaining gaps to open_questions.\n- **open_questions are interview questions only.** Do not ask users to make decisions. Ask only for primary information\n  absent from both footage and the internet. See [interpretation.md](interpretation.md) and\n  [references\u002Fopen-questions-examples.md](references\u002Fopen-questions-examples.md).\n- **Stop condition (80-point line): can the proposed arc form a coherent whole without fabricated facts?**\n  If so, end interviewing. Send later questions to post-edit refinement (`plan-edit`).\n- **Do not display arc in the report.** Keep it as schema data in `interpretation.json` (source of interview\n  questions and seeds for AI proposals during dialogue). Removal from display was settled in the 2026-07-22 revision.\n- Do not add helper fields absent from [interpretation.schema.json](https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fpackages\u002Fschemas\u002Finterpretation.schema.json).\n  Finalize only JSON that passes `validate-interpretation.mjs`.\n- **No decision UI in reports** (choices, knobs, or finalize buttons). Decide direction in chat.\n  The AI proposes with evidence instead of asking “What should we do?”\n- **Connect decision records to existing decision_log conventions (plan-edit).** Do not invent a format.\n  See [decision-record.md](decision-record.md).\n- Use OpenMontage only as structural inspiration; do not copy AGPL text or code.\n\n## Execution order and contents\n\n1. Read [collect.md](collect.md), list project assets, and check for analysis.json.\n   Run analyze-footage only for missing assets, 1 asset = 1 execution.\n2. Read [interpretation.md](interpretation.md); read all analysis.json files with surrounding project context,\n   then create `interpretation.json` with mandatory evidence and zero fabrication.\n3. Read [validate-and-render.md](validate-and-render.md), confirm `validate-interpretation.mjs` PASS,\n   generate a report using renderer `--analysis \u003Cref>=\u003Cpath>`, and open it.\n   Verify absent analysis.json chapters display as unobserved.\n4. Only if open_questions remain, read [interview.md](interview.md) and interview in chat\n   (no decision delegation). Promote answers to interview context and regenerate interpretation\u002Freport (return to steps 2–3).\n5. Read [decision-record.md](decision-record.md); record interview Q&A and major pass-2 decisions in the decision log.\n\nRead only the file for the current stage, without reading ahead.\n","# Analyze a project\n\n> **Language**: Respond in the user's language — conversation, questions, approval prompts, and the reports and records you write (including decision-log rows) follow the language the user writes in.\n\nDo not Read all of `edit.json` \u002F `captions.json`; grep by ID and read only matching lines ([Reading edit.json](https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fedit-json-access.md)).\nIn other stages that need writes, Edit the relevant lines or use edit-store's script API.\n\n## Recommend a playbook after source material arrives\n\nOnly immediately after new material is placed, read `.akari\u002Fintake.json` and existing `analysis.json`\nrecords for speakers, duration, orientation, and media kinds, then run `akari playbook list --json`.\nCompare `category`, `tags.form`, `tags.length`, `tags.materials`, and `requires` to the observed material.\nOffer at most three ranked matches in chat, with a specific reason and any missing required tool for each.\nPortrait material with a target at or below 60 seconds favors vertical explainers or short dramas;\ntalking head plus screen capture favors an explainer; music-led material favors an MV.\nPoint to an existing review sheet or to `.akari\u002Freports\u002Fplaybook-apply.html` as the sheet produced on\napplication. Do not apply a playbook until the user selects one. Do not repeat this recommendation later\nin the analysis workflow.\n\n## Hard rules\n\n- **Do not rerun pass 1.** Delegate per-asset fact extraction (heavy processing such as STT\u002Fframe analysis) to existing\n  [analyze-footage](..\u002Fanalyze-footage\u002FSKILL.md) analysis.json files. Run only for missing assets, 1 asset = 1 execution.\n  Use existing analysis.json without modifying it.\n- **Display absent ledger chapters as “unobserved”.** Do not imply they did not exist or fill them by inference\n  from assets\u002Fother chapters. Keep those report chapters visible and marked unobserved; use `observations[]`\n  execution history as evidence when present.\n- **Do not rewatch footage in pass 2.** Limit it to text reasoning over pass-1 outputs (transcript, keyframe notes, events).\n  Return to footage only at pinpointed locations pass 2 determines are necessary.\n- **Pass-2 inputs are not limited to analysis.json files.** Read surrounding project context (intake.json,\n  `planning\u002F`, README, and referenced past projects), and grep edit.json by ID to read relevant lines only.\n  Field validation (internal multiasset-dogfood run, 2026-07-22) confirmed cases where analysis.json alone\n  could not establish asset provenance (orphan\u002Funclear, etc.) confidently.\n- **Include `memory` connections when reading surrounding project context.** If `.akari\u002Fconnections.json`\n  declares `memory` ([contract-2026-07-25-memory-connection-v0.md](https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fdocs\u002Fcontract-2026-07-25-memory-connection-v0.md), Japanese),\n  start at `entry` (default `INDEX.md`) and read only the `include`\u002F`exclude` scope.\n  Record referenced file paths as sources in `interpretation.json`'s `inputs.context`. Full-text ingestion is forbidden.\n  Do nothing if undeclared; this is not an error.\n- **Every interpretation claim requires evidence**: all `assets[].summary`\u002F`role`\u002F`relations`\u002F`flags` and `arc[]`.\n  Evidence is limited to quoted transcript ranges or keyframe-note references. Fabricate nothing.\n  Do not write unsupported claims; send remaining gaps to open_questions.\n- **open_questions are interview questions only.** Do not ask users to make decisions. Ask only for primary information\n  absent from both footage and the internet. See [interpretation.md](interpretation.md) and\n  [references\u002Fopen-questions-examples.md](references\u002Fopen-questions-examples.md).\n- **Stop condition (80-point line): can the proposed arc form a coherent whole without fabricated facts?**\n  If so, end interviewing. Send later questions to post-edit refinement (`plan-edit`).\n- **Do not display arc in the report.** Keep it as schema data in `interpretation.json` (source of interview\n  questions and seeds for AI proposals during dialogue). Removal from display was settled in the 2026-07-22 revision.\n- Do not add helper fields absent from [interpretation.schema.json](https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fpackages\u002Fschemas\u002Finterpretation.schema.json).\n  Finalize only JSON that passes `validate-interpretation.mjs`.\n- **No decision UI in reports** (choices, knobs, or finalize buttons). Decide direction in chat.\n  The AI proposes with evidence instead of asking “What should we do?”\n- **Connect decision records to existing decision_log conventions (plan-edit).** Do not invent a format.\n  See [decision-record.md](decision-record.md).\n- Use OpenMontage only as structural inspiration; do not copy AGPL text or code.\n\n## Execution order and contents\n\n1. Read [collect.md](collect.md), list project assets, and check for analysis.json.\n   Run analyze-footage only for missing assets, 1 asset = 1 execution.\n2. Read [interpretation.md](interpretation.md); read all analysis.json files with surrounding project context,\n   then create `interpretation.json` with mandatory evidence and zero fabrication.\n3. Read [validate-and-render.md](validate-and-render.md), confirm `validate-interpretation.mjs` PASS,\n   generate a report using renderer `--analysis \u003Cref>=\u003Cpath>`, and open it.\n   Verify absent analysis.json chapters display as unobserved.\n4. Only if open_questions remain, read [interview.md](interview.md) and interview in chat\n   (no decision delegation). Promote answers to interview context and regenerate interpretation\u002Freport (return to steps 2–3).\n5. Read [decision-record.md](decision-record.md); record interview Q&A and major pass-2 decisions in the decision log.\n\nRead only the file for the current stage, without reading ahead.\n",{"name":5,"description":7},"main","12b63130cc05dfc1efff973508a33f4fe3a27129","skills\u002Fanalyze-project",25,"https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video","https:\u002F\u002Fakari.video","https:\u002F\u002Fgithub.com\u002FAkariLabs","2026-10-22 01:34:40",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add AkariLabs\u002Fakari-video --skill analyze-project",{"tool":37,"command":38},"bunx","bunx skills add AkariLabs\u002Fakari-video --skill analyze-project",{"tool":40,"command":41},"pnpm","pnpm dlx skills add AkariLabs\u002Fakari-video --skill analyze-project","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fskills\u002Fanalyze-project\u002FSKILL.md",true,[45,51,55,59,63,67,71],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"collect.md","REFERENCE","参考文档",2606,"https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fskills\u002Fanalyze-project\u002Fcollect.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"decision-record.md",4176,"https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fskills\u002Fanalyze-project\u002Fdecision-record.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"interpretation.md",8404,"https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fskills\u002Fanalyze-project\u002Finterpretation.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"interview.md",3319,"https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fskills\u002Fanalyze-project\u002Finterview.md",{"path":64,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Finterpretation-shape.md",2030,"https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fskills\u002Fanalyze-project\u002Freferences\u002Finterpretation-shape.md",{"path":68,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fopen-questions-examples.md",3136,"https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fskills\u002Fanalyze-project\u002Freferences\u002Fopen-questions-examples.md",{"path":72,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":73,"sourceHtmlUrl":74},"validate-and-render.md",3340,"https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fskills\u002Fanalyze-project\u002Fvalidate-and-render.md",[76,83,90,97,104,111],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M78ZECT6QNHG9XCEJAF779V4","verify-project","Verify an AKARI Video project with the L0 \u002F L1 \u002F L2 verification ladder required by an AKARI Video task contract on the current Theia stack. Read when acceptance criteria specify levels such as L0 or L0+L1, to determine exactly what to run and how at each level.（旧名: verify）","https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fskills\u002Fverify-project\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M78ZE9H36DBKGW1DH7PRZ526","verify-edit","Verify edit.json and optional analysis.json \u002F captions.json \u002F media with a deterministic CLI, then finish QA with frame inspection and reporting after PASS. Use immediately after writing or modifying edit.json, before export, and after applying review feedback.（旧名: edit-lint）","https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fskills\u002Fverify-edit\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M78ZE5CYGEAKZG6M5SEP2B20","setup-remote","Set up remote access to approval reports and previews from another device such as a phone, and send footage to the workspace. Use doctor to assess Tailscale, guide installation and login (human actions), expose the preview server (default 4567) and approval report helper over tailnet-only HTTPS with tailscale serve, connect Taildrop reception to workspace inbox\u002F, and verify access from another device. Use for requests to view reports on a phone, approve remotely, send footage from a phone, or set up remote access. Public internet exposure (funnel) is outside the default scope.","https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fskills\u002Fsetup-remote\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":18},"01M78ZE2HZR93E1ZJ5GPG2V0K5","setup-project","Set up an AKARI Video project headlessly. Recursively copy `templates\u002Fproject-default\u002F`, record the template version, initialize git only when safe, and generate an HTML creation report. No app launch is needed. Use to create a video project or fill in an existing folder as an AKARI Video project.（旧名: create-project）","https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fskills\u002Fsetup-project\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":18},"01M78ZDWRXJJF2B98WGQ35W53E","setup-library","Use for first-time AKARI Video setup or when the current project needs more usable assets. This first-run skill checks ffmpeg \u002F whisper-cli (and can install with approval), reads the bundled catalog with akari assets to propose a starter pack, obtains explicit human approval, then acquires, places, validates, and updates INDEX entries. It also covers the audio library (BGM and sound effects): bulk acquisition of first-party AKARI Sounds from GitHub Releases, a free-source candidate HTML list with drop-folder matching or assisted acquisition for missing families, and keep\u002Fdrop decisions in the listening gallery. Use for requests such as \"I want more BGM\" or \"add sound effects to the library\".（旧名: setup-audio-library）","https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fskills\u002Fsetup-library\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":18},"01M78ZDNSC34WR5NYJYNZ4HC28","setup-connections","Set up and inspect AKARI Video connections: AI-service keys, which models are allowed, cost-approval policy, the tool and media-service state, and 3D settings. Use for first-time setup, adding a provider or key later, checking what is usable (「何が使える？」 'what can I use?'), setting a key such as fal (「fal の鍵を設定したい」), 3D settings (「3D の設定を使いたい」), connection checks, and gates before paid generation or external publication. Model selection belongs to the production skills (they read the ledger and preferences); this skill decides allowed models and the cost policy. Works with `.akari\u002Fconnections.json` and a free, read-only doctor.（旧名: manage-connections）（旧名: connect）","https:\u002F\u002Fgithub.com\u002FAkariLabs\u002Fakari-video\u002Fblob\u002Fmain\u002Fskills\u002Fsetup-connections\u002FSKILL.md",[],[]]