[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78F7GGT9DWMF3DM1PCRWT3S":3,"skill-same:01M78F7GGT9DWMF3DM1PCRWT3S":45},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":44},"01M78F7GGT9DWMF3DM1PCRWT3S","release-notes-html",null,"Build a polished self-contained HTML product launch and release-notes page from work completed in the current session, using available repository state, source-of-truth files, tests, approvals, artifacts, commits, pull requests, previews, and release evidence. Use when the user asks to build release notes, create a launch page, document completed work, produce feature-release HTML, or turn the session into product-facing release notes.","jl-cmd-projects\u002Fclaude-dev-env","jl-cmd-projects","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F338158757?v=4","01M78F4M55P4QY5YPN27XBQA9N","01M78F4M65AGEYC88NV6PW4715",7,"MIT","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Frelease-notes-html\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: release-notes-html\ndescription: Build a polished self-contained HTML product launch and release-notes page from work completed in the current session, using available repository state, source-of-truth files, tests, approvals, artifacts, commits, pull requests, previews, and release evidence. Use when the user asks to build release notes, create a launch page, document completed work, produce feature-release HTML, or turn the session into product-facing release notes.\nwhen_to_use: Invoke for requests such as \"build release notes for the work you've done,\" \"create release notes HTML,\" \"make a product launch page,\" \"document this completed feature,\" or \"turn our work into a polished release page.\"\ndisable-model-invocation: false\nuser-invocable: true\n---\n\nBuild a polished, self-contained HTML product launch and release-notes page for the work completed in this session.\n\nUse the current conversation, task history, repository state, completed changes, test results, approvals, generated artifacts, plans, handoffs, file paths, commits, pull requests, and other evidence already available in the session as the source of truth.\n\nRecover the feature name, purpose, capabilities, specifications, usage instructions, validation results, release status, and first production use directly from the available context. Inspect relevant files and repository artifacts when access is available.\n\nAsk one concise clarification question only when the session does not contain enough information to identify the completed feature or its supporting evidence.\n\n## Execution\n\nAct as the orchestrator.\n\nCreate a task ledger covering:\n\n- Evidence collection\n- Feature and release-state synthesis\n- Page structure\n- HTML creation\n- Evidence audit\n- Visual and browser review\n- Final delivery\n\nAssign file inspection and HTML creation to executor workers when worker tools are available. The orchestrator owns the structure, factual acceptance, and final audit.\n\n## Evidence rules\n\nUse only facts supported by:\n\n- The current conversation\n- Current session tasks and results\n- Repository files and git state\n- Named source-of-truth files\n- Generated reports, ledgers, plans, and acceptance packets\n- Explicit user approvals\n- Test and CI output already available\n- Pull request and commit data available to the session\n\nLocate the strongest source for each claim.\n\nPreserve exact:\n\n- Feature and package names\n- File paths\n- Commands\n- Dimensions\n- Flags\n- Identifiers\n- JSON keys\n- Test totals\n- Pull request numbers\n- Branch and release status\n\nPlace exact technical values inside `\u003Ccode>` elements.\n\nInclude previews, approval claims, test counts, merged status, and production-use claims when the available evidence supports them.\n\n## Page content\n\nProduce one cohesive launch page with a clear hierarchy that a non-engineer can skim.\n\nInclude the sections that the completed work supports:\n\n1. Hero with the feature name and primary benefit\n2. A brief explanation of what the feature enables\n3. Major capability highlights\n4. How to run or use it\n5. Exact specifications\n6. Quality, validation, and safety coverage\n7. First production use, debut project, or approved example\n8. Current availability or completion status\n\nAdapt the section names and structure to the actual project. Give every heading a useful takeaway.\n\n## Tone\n\nWrite the page as the launch of a completed new capability.\n\nUse present-state product copy focused on:\n\n- What it is\n- What the user can accomplish\n- How it works\n- How to use it\n- What guarantees or validations it provides\n- Where it has already been applied\n\nKeep implementation history, discarded approaches, debugging chronology, and internal justification outside the page unless they are essential to using the feature.\n\n## Voice rules\n\nThe reader primarily absorbs headings, bolded leads, and the first sentence of each block.\n\n1. Every title states a plain-language claim.\n2. Each sentence carries one idea.\n3. Lead with reader meaning, then explain the mechanism.\n4. Explain specialized terms at first use.\n5. Keep exact technical values verbatim inside `\u003Ccode>` elements.\n6. Limit cards to two sentences.\n7. Limit list items to three sentences.\n8. Give each section a one-sentence subtitle that adds information.\n9. Make the complete story understandable from headings and bolded leads alone.\n10. Use concise, active sentences.\n11. Use present-state language throughout.\n12. Give every important fact one clear location.\n\n## Design\n\nCreate one valid HTML file with self-contained CSS. CDN-hosted fonts are acceptable.\n\nUse:\n\n- Strong visual hierarchy\n- Spacious typography\n- Scannable cards and sections\n- Responsive desktop and narrow-screen layouts\n- Accessible contrast\n- Clear treatment of code, specifications, and commands\n- An inviting product-launch presentation rather than dense documentation\n\nUse an approved preview or product image when one is already available and supported by the session.\n\n## Output location\n\nChoose the output location from an explicit path already stated in the session.\n\nWhen no output path has been established, write the file beside the project’s existing results, release, report, or acceptance artifacts using a clear name such as:\n\n`RELEASE_NOTES.html`\n\nUse the operating-system temporary directory only when no project location can be determined safely.\n\nWrite the file atomically and create its parent directory when required.\n\n## Acceptance audit\n\nBefore delivery:\n\n- Verify every factual claim against the available evidence.\n- Review every heading for a clear takeaway.\n- Review every sentence for one idea.\n- Confirm specialized terms receive plain explanations.\n- Confirm exact technical values remain verbatim.\n- Confirm headings and bolded leads communicate the whole story.\n- Confirm the page is readable at desktop and narrow browser widths.\n- Confirm the output is one complete, valid HTML file.\n- Open the completed page in Chrome or the available default browser when the environment supports it.\n- Correct every issue found during the audit.\n\n## Delivery\n\nReply with:\n\n1. The full absolute path to the HTML file.\n2. One sentence describing what the release-notes page covers.\n\nStop after delivering the completed page.\n","Build a polished, self-contained HTML product launch and release-notes page for the work completed in this session.\n\nUse the current conversation, task history, repository state, completed changes, test results, approvals, generated artifacts, plans, handoffs, file paths, commits, pull requests, and other evidence already available in the session as the source of truth.\n\nRecover the feature name, purpose, capabilities, specifications, usage instructions, validation results, release status, and first production use directly from the available context. Inspect relevant files and repository artifacts when access is available.\n\nAsk one concise clarification question only when the session does not contain enough information to identify the completed feature or its supporting evidence.\n\n## Execution\n\nAct as the orchestrator.\n\nCreate a task ledger covering:\n\n- Evidence collection\n- Feature and release-state synthesis\n- Page structure\n- HTML creation\n- Evidence audit\n- Visual and browser review\n- Final delivery\n\nAssign file inspection and HTML creation to executor workers when worker tools are available. The orchestrator owns the structure, factual acceptance, and final audit.\n\n## Evidence rules\n\nUse only facts supported by:\n\n- The current conversation\n- Current session tasks and results\n- Repository files and git state\n- Named source-of-truth files\n- Generated reports, ledgers, plans, and acceptance packets\n- Explicit user approvals\n- Test and CI output already available\n- Pull request and commit data available to the session\n\nLocate the strongest source for each claim.\n\nPreserve exact:\n\n- Feature and package names\n- File paths\n- Commands\n- Dimensions\n- Flags\n- Identifiers\n- JSON keys\n- Test totals\n- Pull request numbers\n- Branch and release status\n\nPlace exact technical values inside `\u003Ccode>` elements.\n\nInclude previews, approval claims, test counts, merged status, and production-use claims when the available evidence supports them.\n\n## Page content\n\nProduce one cohesive launch page with a clear hierarchy that a non-engineer can skim.\n\nInclude the sections that the completed work supports:\n\n1. Hero with the feature name and primary benefit\n2. A brief explanation of what the feature enables\n3. Major capability highlights\n4. How to run or use it\n5. Exact specifications\n6. Quality, validation, and safety coverage\n7. First production use, debut project, or approved example\n8. Current availability or completion status\n\nAdapt the section names and structure to the actual project. Give every heading a useful takeaway.\n\n## Tone\n\nWrite the page as the launch of a completed new capability.\n\nUse present-state product copy focused on:\n\n- What it is\n- What the user can accomplish\n- How it works\n- How to use it\n- What guarantees or validations it provides\n- Where it has already been applied\n\nKeep implementation history, discarded approaches, debugging chronology, and internal justification outside the page unless they are essential to using the feature.\n\n## Voice rules\n\nThe reader primarily absorbs headings, bolded leads, and the first sentence of each block.\n\n1. Every title states a plain-language claim.\n2. Each sentence carries one idea.\n3. Lead with reader meaning, then explain the mechanism.\n4. Explain specialized terms at first use.\n5. Keep exact technical values verbatim inside `\u003Ccode>` elements.\n6. Limit cards to two sentences.\n7. Limit list items to three sentences.\n8. Give each section a one-sentence subtitle that adds information.\n9. Make the complete story understandable from headings and bolded leads alone.\n10. Use concise, active sentences.\n11. Use present-state language throughout.\n12. Give every important fact one clear location.\n\n## Design\n\nCreate one valid HTML file with self-contained CSS. CDN-hosted fonts are acceptable.\n\nUse:\n\n- Strong visual hierarchy\n- Spacious typography\n- Scannable cards and sections\n- Responsive desktop and narrow-screen layouts\n- Accessible contrast\n- Clear treatment of code, specifications, and commands\n- An inviting product-launch presentation rather than dense documentation\n\nUse an approved preview or product image when one is already available and supported by the session.\n\n## Output location\n\nChoose the output location from an explicit path already stated in the session.\n\nWhen no output path has been established, write the file beside the project’s existing results, release, report, or acceptance artifacts using a clear name such as:\n\n`RELEASE_NOTES.html`\n\nUse the operating-system temporary directory only when no project location can be determined safely.\n\nWrite the file atomically and create its parent directory when required.\n\n## Acceptance audit\n\nBefore delivery:\n\n- Verify every factual claim against the available evidence.\n- Review every heading for a clear takeaway.\n- Review every sentence for one idea.\n- Confirm specialized terms receive plain explanations.\n- Confirm exact technical values remain verbatim.\n- Confirm headings and bolded leads communicate the whole story.\n- Confirm the page is readable at desktop and narrow browser widths.\n- Confirm the output is one complete, valid HTML file.\n- Open the completed page in Chrome or the available default browser when the environment supports it.\n- Correct every issue found during the audit.\n\n## Delivery\n\nReply with:\n\n1. The full absolute path to the HTML file.\n2. One sentence describing what the release-notes page covers.\n\nStop after delivering the completed page.\n",{"name":5,"description":7,"when_to_use":23,"user-invocable":24,"disable-model-invocation":19},"Invoke for requests such as \"build release notes for the work you've done,\" \"create release notes HTML,\" \"make a product launch page,\" \"document this completed feature,\" or \"turn our work into a polished release page.\"",true,"main","974284b42eeb4609e94d4ebc1f6e36df400d54ca","packages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Frelease-notes-html",1,"https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects","2026-11-15 05:02:47",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":24},[34,37,40],{"tool":35,"command":36},"npx","npx skills add jl-cmd-projects\u002Fclaude-dev-env --skill release-notes-html",{"tool":38,"command":39},"bunx","bunx skills add jl-cmd-projects\u002Fclaude-dev-env --skill release-notes-html",{"tool":41,"command":42},"pnpm","pnpm dlx skills add jl-cmd-projects\u002Fclaude-dev-env --skill release-notes-html","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fpackages\u002Fclaude-dev-env\u002F.agents\u002Fskills-archived\u002Frelease-notes-html\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":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M78FER7S09AE87MMJFT1E87E","update","Fast-forwards a local repository's main branch to a remote's main after confirming the repo path and source remote through AskUserQuestion. Use when the user says '\u002Fupdate', 'update main', 'fast-forward main', 'sync main from origin', 'pull latest main into \u003Cpath>', or 'bring main up to date'.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fupdate\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M78FENWZS01MB4PMGX6801X6","source-command-sr-loop","Converging cleanup loop: repeat \u002Fsimplify until clean, then repeat \u002Fcode-review --fix until clean","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsource-command-sr-loop\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M78FEGZ7JDWEG3RM78M9Y8F8","skill-builder","Skill lifecycle: classify, scaffold, write via the skill-writer-agent, self-audit, compose sub-skills, polish description triggers, enforce deterministic scripts. Triggers: build a skill, new skill workflow, improve this skill, optimize skill description, skill development lifecycle, skill modularity, skill composition, description trigger catalog, deterministic skill scripts.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fskill-builder\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M78FEDEYHJYKTER9S566DMEZ","session-tidy","Audit, clean, and consolidate session logs in the Obsidian vault. Fixes format drift, resolves orphaned next-steps, updates stale statuses, and generates project rollup summaries. Use when session logs feel cluttered or before starting a new project milestone. Triggers on '\u002Fsession-tidy', 'tidy sessions', 'clean up session logs', 'session audit'.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsession-tidy\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M78FE8QR789SKBF3A78N2T13","session-log","Logs a session report as an HTML page, tracks vault context, extracts decisions, and outputs a \u002Frename command. Use for \u002Fsession-log, 'journal this session', 'log this work', 'session report', 'summarize\u002Flog\u002Frecord this session', 'save session', 'capture session', or 'document what we did'.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Fsession-log\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M78FE4JDJHKTJPWRWNQEX2HT","run-claude-dev-env","Build, install, run, and test the claude-dev-env installer. Use when asked to run claude-dev-env, install the Claude Code config into ~\u002F.claude, drive the installer, smoke-test it against a sandbox, or run its test suite.","https:\u002F\u002Fgithub.com\u002Fjl-cmd-projects\u002Fclaude-dev-env\u002Fblob\u002Fmain\u002Fskill-archive\u002Frun-claude-dev-env\u002FSKILL.md",[],[]]