[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MZMMT507WJS779VZW7Z6QV":3,"skill-same:01M6MZMMT507WJS779VZW7Z6QV":66},{"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":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M6MZMMT507WJS779VZW7Z6QV","project-pulse",null,"Review what changed in Claude Code upstream and compare against this project's commits and ADRs. Surfaces opportunities, gaps, and ADR status drift. Discovery conversation, not compliance dashboard.","aaronsb\u002Fagent-ways","aaronsb","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F2738471?v=4","01M6MZKZTB1QDZ0YMSVFC2F0RE","Aaron Bockelie","01M6MZKZYG6T75YE9PCBNR72QK",26,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002Faaronsb\u002Fagent-ways\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fproject-pulse\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36],"project pulse","project","pulse","read","compare","upstream","drift","conversation","surfaces","review","adr","Bash","commits","discovery","compliance","code","status","dashboard","2026-11-10 10:12:30",false,"---\nname: project-pulse\ndescription: >\n  Review what changed in Claude Code upstream and compare against this\n  project's commits and ADRs. Surfaces opportunities, gaps, and ADR\n  status drift. Discovery conversation, not compliance dashboard.\nallowed-tools: Bash, Read\n---\n\n# Project Pulse\n\nCompare this project against Claude Code upstream releases, or reconcile ADR statuses against shipped code.\n\n## Usage\n\n```\n\u002Fproject-pulse                    # What's new upstream?\n\u002Fproject-pulse --inward           # Are our ADRs current?\n\u002Fproject-pulse --since 2026-03-01 # Wider window\n\u002Fproject-pulse --full             # Full history\n```\n\n## How to Run\n\nThis is a **project-scoped dev-harness skill** — it lives in the agent-ways repo's\nown `.claude\u002Fskills\u002F` (not the projected framework surface), so it's available when\nyou're developing agent-ways, never shipped into an operator's install. The helper\nlives in the checkout at `scripts\u002Fproject-pulse`, so resolve it against the project:\n\n```bash\nbash \"${CLAUDE_PROJECT_DIR:-$PWD}\u002Fscripts\u002Fproject-pulse\" [flags]\n```\n\nThe script outputs structured markdown. Your job is to interpret it.\n\n## Upstream Mode (default)\n\nThe script outputs:\n1. Claude Code releases in the window (with full changelogs)\n2. Our commits in the same window\n3. An epoch mapping table (our commits mapped to which upstream release was current)\n4. High-delta alerts (periods where many upstream releases passed between our commits)\n\n### Your interpretation\n\nRead the upstream changelogs and filter through what this project cares about:\n\n**Relevant to us** (suggest these):\n- Hooks: new hook types, hook behavior changes, hook lifecycle\n- Settings\u002Fconfig: new settings fields, managed settings, permissions model\n- Skills\u002Fslash commands: new frontmatter fields, skill discovery changes, effort levels\n- Context window: size changes, compaction behavior, token tracking\n- Plugins: marketplace changes, plugin sources, installation flow\n- Subagents\u002Fteams: isolation modes, worktree behavior, agent coordination\n- MCP: new capabilities, server management, tool patterns\n\n**Usually irrelevant** (skip these):\n- UI polish, terminal rendering, keybindings\n- Voice mode, dictation\n- IDE-specific integrations (VSCode, Cursor)\n- API proxy fixes, Bedrock\u002FVertex specifics\n- Remote Control, bridge sessions\n\n### Output format\n\nPick the 2-5 most interesting upstream changes and explain in plain prose why they matter for this project. Reference the specific version. Example:\n\n> Claude Code v2.1.80 added `effort` frontmatter for skills. We author skills — this would let our think strategies control reasoning effort. Worth an ADR?\n\n> v2.1.76 added `PostCompact` hook. Our compaction-checkpoint way currently uses `UserPromptSubmit` at 95% threshold. A PostCompact hook could be a cleaner safety net.\n\nIf nothing interesting happened in the window, say so. That's a valid outcome.\n\nDo NOT:\n- List every change\n- Score coverage\n- Show red\u002Fyellow\u002Fgreen\n- Say \"you're N releases behind\"\n\n### High-delta periods\n\nWhen the epoch mapping shows high deltas (3+ upstream releases between our commits), note this as context — \"the ground shifted here, worth a closer look at what shipped in that window.\"\n\n## Inward Mode (`--inward`)\n\nThe script outputs a table of ADRs with their status, referencing commit count, branch references, and an assessment.\n\n### Your interpretation\n\nFocus on mismatches:\n- **\"Accepted but no referencing commits\"** — was this ADR adopted based on existing code, or is something missing?\n- **\"Draft with N commits — promote?\"** — the work exists, the ADR may need a status update\n- **\"Dormant\"** — no commits, no branches. Is this still planned?\n\nPresent as conversational observations, not a status report:\n\n> ADR-100 (Ways Scaffolding Wizard) is still Draft but has 4 referencing commits. The testing side exists but the scaffolding wizard itself doesn't. Is this still the plan, or should we scope it down and accept what we have?\n\n## Suggesting ADRs\n\nWhen upstream changes suggest new work, propose ADR topics with the upstream reference:\n\n> Upstream v2.1.80 added `--channels` for MCP server push messages. If we want ways or skills to receive asynchronous notifications, that's a new architectural capability. ADR candidate: \"Channel-based way triggers for async MCP events\" (inspired by Claude Code v2.1.80).\n\n## Tone\n\nYou're a colleague who follows the releases. Casual, suggestive, not prescriptive. The human decides what to act on.\n\n## Not for\n\n- Coverage scoring or \"you're N releases behind\" reporting — it's a discovery conversation, not a compliance dashboard.\n- Applying the changes — it surfaces what's worth discussing; you decide and act (an ADR, an issue, a `\u002Fship`).\n","# Project Pulse\n\nCompare this project against Claude Code upstream releases, or reconcile ADR statuses against shipped code.\n\n## Usage\n\n```\n\u002Fproject-pulse                    # What's new upstream?\n\u002Fproject-pulse --inward           # Are our ADRs current?\n\u002Fproject-pulse --since 2026-03-01 # Wider window\n\u002Fproject-pulse --full             # Full history\n```\n\n## How to Run\n\nThis is a **project-scoped dev-harness skill** — it lives in the agent-ways repo's\nown `.claude\u002Fskills\u002F` (not the projected framework surface), so it's available when\nyou're developing agent-ways, never shipped into an operator's install. The helper\nlives in the checkout at `scripts\u002Fproject-pulse`, so resolve it against the project:\n\n```bash\nbash \"${CLAUDE_PROJECT_DIR:-$PWD}\u002Fscripts\u002Fproject-pulse\" [flags]\n```\n\nThe script outputs structured markdown. Your job is to interpret it.\n\n## Upstream Mode (default)\n\nThe script outputs:\n1. Claude Code releases in the window (with full changelogs)\n2. Our commits in the same window\n3. An epoch mapping table (our commits mapped to which upstream release was current)\n4. High-delta alerts (periods where many upstream releases passed between our commits)\n\n### Your interpretation\n\nRead the upstream changelogs and filter through what this project cares about:\n\n**Relevant to us** (suggest these):\n- Hooks: new hook types, hook behavior changes, hook lifecycle\n- Settings\u002Fconfig: new settings fields, managed settings, permissions model\n- Skills\u002Fslash commands: new frontmatter fields, skill discovery changes, effort levels\n- Context window: size changes, compaction behavior, token tracking\n- Plugins: marketplace changes, plugin sources, installation flow\n- Subagents\u002Fteams: isolation modes, worktree behavior, agent coordination\n- MCP: new capabilities, server management, tool patterns\n\n**Usually irrelevant** (skip these):\n- UI polish, terminal rendering, keybindings\n- Voice mode, dictation\n- IDE-specific integrations (VSCode, Cursor)\n- API proxy fixes, Bedrock\u002FVertex specifics\n- Remote Control, bridge sessions\n\n### Output format\n\nPick the 2-5 most interesting upstream changes and explain in plain prose why they matter for this project. Reference the specific version. Example:\n\n> Claude Code v2.1.80 added `effort` frontmatter for skills. We author skills — this would let our think strategies control reasoning effort. Worth an ADR?\n\n> v2.1.76 added `PostCompact` hook. Our compaction-checkpoint way currently uses `UserPromptSubmit` at 95% threshold. A PostCompact hook could be a cleaner safety net.\n\nIf nothing interesting happened in the window, say so. That's a valid outcome.\n\nDo NOT:\n- List every change\n- Score coverage\n- Show red\u002Fyellow\u002Fgreen\n- Say \"you're N releases behind\"\n\n### High-delta periods\n\nWhen the epoch mapping shows high deltas (3+ upstream releases between our commits), note this as context — \"the ground shifted here, worth a closer look at what shipped in that window.\"\n\n## Inward Mode (`--inward`)\n\nThe script outputs a table of ADRs with their status, referencing commit count, branch references, and an assessment.\n\n### Your interpretation\n\nFocus on mismatches:\n- **\"Accepted but no referencing commits\"** — was this ADR adopted based on existing code, or is something missing?\n- **\"Draft with N commits — promote?\"** — the work exists, the ADR may need a status update\n- **\"Dormant\"** — no commits, no branches. Is this still planned?\n\nPresent as conversational observations, not a status report:\n\n> ADR-100 (Ways Scaffolding Wizard) is still Draft but has 4 referencing commits. The testing side exists but the scaffolding wizard itself doesn't. Is this still the plan, or should we scope it down and accept what we have?\n\n## Suggesting ADRs\n\nWhen upstream changes suggest new work, propose ADR topics with the upstream reference:\n\n> Upstream v2.1.80 added `--channels` for MCP server push messages. If we want ways or skills to receive asynchronous notifications, that's a new architectural capability. ADR candidate: \"Channel-based way triggers for async MCP events\" (inspired by Claude Code v2.1.80).\n\n## Tone\n\nYou're a colleague who follows the releases. Casual, suggestive, not prescriptive. The human decides what to act on.\n\n## Not for\n\n- Coverage scoring or \"you're N releases behind\" reporting — it's a discovery conversation, not a compliance dashboard.\n- Applying the changes — it surfaces what's worth discussing; you decide and act (an ADR, an issue, a `\u002Fship`).\n",{"name":5,"description":42,"allowed-tools":43},"Review what changed in Claude Code upstream and compare against this project's commits and ADRs. Surfaces opportunities, gaps, and ADR status drift. Discovery conversation, not compliance dashboard.\n","Bash, Read","main","e99c7d9ee1f646cdb86d1a215830339837be153a",".claude\u002Fskills\u002Fproject-pulse",13,"https:\u002F\u002Fgithub.com\u002Faaronsb\u002Fagent-ways","https:\u002F\u002Fgithub.com\u002Faaronsb","I like coding with AI tools and making things.","2026-11-11 14:29:16",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add aaronsb\u002Fagent-ways --skill project-pulse",{"tool":58,"command":59},"bunx","bunx skills add aaronsb\u002Fagent-ways --skill project-pulse",{"tool":61,"command":62},"pnpm","pnpm dlx skills add aaronsb\u002Fagent-ways --skill project-pulse","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Faaronsb\u002Fagent-ways\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fproject-pulse\u002FSKILL.md",true,[],[67,86,98,121,146,168],{"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":78,"publishedAt":37},"01M6MZQPWHX5QCS3PVPVY1WAVC","my-skill","A hand-built skill the user keeps in ~\u002F.claude\u002Fskills. The fixture asserts it survives the install.","https:\u002F\u002Fgithub.com\u002Faaronsb\u002Fagent-ways\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fdocker\u002Fseed\u002Fclaude\u002Fskills\u002Fmy-skill\u002FSKILL.md",[73],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[79,80,81,82,83,84,85],"my skill","my","hand","user","it","fixture","install",{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":93,"publishedAt":37},"01M6MZQKYC9X5E94EDSGGGKZ78","work-skill","A skill in a second Claude Code config directory. The fixture asserts the directory is untouched.","https:\u002F\u002Fgithub.com\u002Faaronsb\u002Fagent-ways\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fdocker\u002Fseed\u002Fclaude-work\u002Fskills\u002Fwork-skill\u002FSKILL.md",[92],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},[94,95,96,97,34,84],"work","work skill","config","directory",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":105,"publishedAt":37},"01M6MZQE8ZJARAB2WGCNHN9JB8","wrap","Wrap up a session at a natural seam — land in-flight work, square the TaskList honestly, write a copy-paste continuation prompt, then hand off to a directed \u002Fcompact. Use when the user says \"wrap up\", \"wrap this up\", \"let's wrap\", \"end of session\", \"checkpoint and compact\", \"hand off\", or invokes \u002Fwrap.","https:\u002F\u002Fgithub.com\u002Faaronsb\u002Fagent-ways\u002Fblob\u002Fmain\u002Fskills\u002Fwrap\u002FSKILL.md",[104],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},[100,106,107,108,109,110,111,112,113,114,115,116,117,118,22,119,120,94,81,30],"compact","use","up","end","session","checkpoint","continuation","wrap up","when","prompt","grep","square","write","at","paste",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":128,"publishedAt":37},"01M6MZQ8GDE7JHXY907BF0B495","ways-update","Update the agent-ways installation to the latest version — preview the update with `ways manage update --what-if` (versions, release notes, the commits, local changes, the actions, dev links), read it back to the user, then apply it with `ways manage update --commit`, which pulls the app source in $XDG_DATA, refreshes the binaries and corpus, and reprojects ~\u002F.claude. Use when the user wants to update agent-ways, pull the latest ways\u002Fhooks, or refresh their ways framework install. Not for editing or authoring individual ways (that is the ways skill) or upgrading project dependencies.","https:\u002F\u002Fgithub.com\u002Faaronsb\u002Fagent-ways\u002Fblob\u002Fmain\u002Fskills\u002Fways-update\u002FSKILL.md",[127],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},[129,130,131,132,133,107,134,135,136,137,138,139,140,31,141,142,143,144,145,20],"ways update","update","version","editing","update agent","manage","actions","hooks","release notes","dev","local","for","which","links","app","pull","back",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":37},"01M6MZQ3N4FRH6A5Z56P034ZQW","ways-tests","Score way matching via embedding similarity, analyze vocabulary, and validate frontmatter. Use when testing how well a way matches prompts, checking cosine similarity scores, inspecting the embedding engine status, or validating way files.","https:\u002F\u002Fgithub.com\u002Faaronsb\u002Fagent-ways\u002Fblob\u002Fmain\u002Fskills\u002Fways-tests\u002FSKILL.md",[],[153,154,155,156,157,107,116,158,159,35,160,161,22,162,163,164,165,166,167,30],"tests","ways tests","files","testing","embedding","frontmatter","prompts","validate","edit","matching","how","via","similarity","engine","analyze",{"skillNo":169,"name":170,"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},"01M6MZPXNGYKM1YG02F7Z5VRFW","ways-localize","Localize agent-ways into the operator's language — translate every way's matching metadata against the English root, tune it clean, and switch ways (and Claude Code) into that language. Use when the operator asks to run ways in their language (\"set up ways in Spanish\", \"localiza ways al español\", \"ways auf Deutsch\"). Not for authoring or editing individual ways (that is the ways skill), not for English installs (already built), and not for changing Claude Code's language alone (that is a settings.json edit).","https:\u002F\u002Fgithub.com\u002Faaronsb\u002Fagent-ways\u002Fblob\u002Fmain\u002Fskills\u002Fways-localize\u002FSKILL.md",[],[175,176,30,177,22,162,178,179,180,34,107,181,182,108,183,132,140,184,185,186],"localize","ways localize","settings","json","run","english","settings.json","clean","translate","switch","spanish","SET"]