[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71JP2TKS16HH0E5CC00ST5Z":3,"skill-same:01M71JP2TKS16HH0E5CC00ST5Z":84},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":39,"commitSha":40,"skillDirectory":5,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":43,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M71JP2TKS16HH0E5CC00ST5Z","reflect",null,"Review the active session through judgment, tooling, and divergent lenses, then propose durable skill edits or structural backlog items. Use when the user asks to reflect, wants better agent behavior from a session, or when `henry-mode` closes expensive, surprising, or repeated work whose lesson should survive.","caezium\u002Fskills","caezium","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113233555?v=4","01M71JB77ZPBAWEK009Y2W8BP7","Henry Zhang","01M71JB792NVXCWSYD27HQ0964",3,"MIT","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Freflect\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Freflect\u002FSKILL.md",[],[5,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"lesson","work","active","tooling","backlog","behavior","session","mode","structural","judgment","use","when","user","review","2026-11-10 10:12:30",false,"---\nname: reflect\ndescription: Review the active session through judgment, tooling, and divergent lenses, then propose durable skill edits or structural backlog items. Use when the user asks to reflect, wants better agent behavior from a session, or when `henry-mode` closes expensive, surprising, or repeated work whose lesson should survive.\n---\n\n# Reflect\n\nMine the active conversation for durable lessons and route them to concrete improvements. Never auto-apply skill changes: present the synthesized proposal and wait for approval.\n\n## Harness availability\n\n| Need | Cursor | Claude Code | Codex \u002F T3 | Fallback |\n|---|---|---|---|---|\n| Transcript | Harness-supplied path or active workspace history under `~\u002F.cursor\u002Fprojects\u002F` | Harness-supplied path or matching history under `~\u002F.claude\u002Fprojects\u002F` | Harness-supplied path or matching `cwd` metadata under `~\u002F.codex\u002Fsessions\u002F` | Visible-conversation digest |\n| Three reviewers | Available Task\u002Fsubagent facility | Available Agent\u002FTask facility | Three `spawn_agent` calls when slots permit; drain with `wait_agent` | Run the three reference prompts sequentially |\n| Model diversity | Select valid model families only when supported and allowed | Same | Use valid overrides only when exposed; otherwise inherit | Label the review same-model or self-reviewed |\n| Synthesis | A fresh worker after reviewers drain | Same | Spawn after reviewer slots free | Parent synthesizes with the same template |\n\nOnly delegate when current user and system policy permit it. Never invent model aliases.\n\n## 1. Locate the session\n\nPrefer the active transcript path exposed by the harness. Otherwise search only the active workspace's history, ordered by real modification time, and match workspace metadata plus the opening user prompt. Do not glob through unrelated project histories. If no transcript resolves, write a compact digest from the visible conversation.\n\n## 2. Run three lenses\n\nLoad the matching prompt only when launching that lens:\n\n| Lens | Prompt |\n|---|---|\n| Judgment | [`references\u002Fjudgment-reviewer.md`](references\u002Fjudgment-reviewer.md) |\n| Tooling | [`references\u002Ftooling-reviewer.md`](references\u002Ftooling-reviewer.md) |\n| Divergent | [`references\u002Fdivergent-reviewer.md`](references\u002Fdivergent-reviewer.md) |\n\nPass the transcript path or digest and preserve each response verbatim for synthesis. Reviewers are read-only: they may inspect referenced local\u002Fcontext sources when authorized, but they do not edit files, post messages, or create external state.\n\n## 3. Synthesize\n\nAfter all three lenses finish, load [`references\u002Fsynthesizer.md`](references\u002Fsynthesizer.md) and substitute their full outputs. Spot-check citations. The result must contain Accepted, Rejected, and Backlog sections.\n\nMove any proposal enforceable more reliably by a lint rule, script, metadata flag, or runtime check from Accepted to Backlog. Prefer an existing skill over a new one. A lesson must be durable, decision-changing, and grounded in this session.\n\n## 4. Ask before applying\n\nPresent the full synthesis and wait for explicit approval on the Accepted rows. Do not file backlog items externally unless the user authorizes that destination.\n\nFor approved rows:\n\n- Make a trivial existing-skill edit directly.\n- Route substantive edits, new personal\u002Fshared skills, and description tuning through `anthropic-skill-creator`. Leave Codex's same-purpose product-managed system skill untouched.\n- Run the environment's skill validator when available and inspect the final diff.\n\n## 5. Report\n\n- Edits applied: path and one-line change.\n- New skills: path and purpose.\n- Backlog: proposed mechanism and whether it was filed.\n- Dropped: rejected finding and reason.\n\n\u003C!-- Adapted from poteto\u002Fpstack reflect, MIT License, Lauren Tan, cursor\u002Fplugins@51a96e0. -->\n","# Reflect\n\nMine the active conversation for durable lessons and route them to concrete improvements. Never auto-apply skill changes: present the synthesized proposal and wait for approval.\n\n## Harness availability\n\n| Need | Cursor | Claude Code | Codex \u002F T3 | Fallback |\n|---|---|---|---|---|\n| Transcript | Harness-supplied path or active workspace history under `~\u002F.cursor\u002Fprojects\u002F` | Harness-supplied path or matching history under `~\u002F.claude\u002Fprojects\u002F` | Harness-supplied path or matching `cwd` metadata under `~\u002F.codex\u002Fsessions\u002F` | Visible-conversation digest |\n| Three reviewers | Available Task\u002Fsubagent facility | Available Agent\u002FTask facility | Three `spawn_agent` calls when slots permit; drain with `wait_agent` | Run the three reference prompts sequentially |\n| Model diversity | Select valid model families only when supported and allowed | Same | Use valid overrides only when exposed; otherwise inherit | Label the review same-model or self-reviewed |\n| Synthesis | A fresh worker after reviewers drain | Same | Spawn after reviewer slots free | Parent synthesizes with the same template |\n\nOnly delegate when current user and system policy permit it. Never invent model aliases.\n\n## 1. Locate the session\n\nPrefer the active transcript path exposed by the harness. Otherwise search only the active workspace's history, ordered by real modification time, and match workspace metadata plus the opening user prompt. Do not glob through unrelated project histories. If no transcript resolves, write a compact digest from the visible conversation.\n\n## 2. Run three lenses\n\nLoad the matching prompt only when launching that lens:\n\n| Lens | Prompt |\n|---|---|\n| Judgment | [`references\u002Fjudgment-reviewer.md`](references\u002Fjudgment-reviewer.md) |\n| Tooling | [`references\u002Ftooling-reviewer.md`](references\u002Ftooling-reviewer.md) |\n| Divergent | [`references\u002Fdivergent-reviewer.md`](references\u002Fdivergent-reviewer.md) |\n\nPass the transcript path or digest and preserve each response verbatim for synthesis. Reviewers are read-only: they may inspect referenced local\u002Fcontext sources when authorized, but they do not edit files, post messages, or create external state.\n\n## 3. Synthesize\n\nAfter all three lenses finish, load [`references\u002Fsynthesizer.md`](references\u002Fsynthesizer.md) and substitute their full outputs. Spot-check citations. The result must contain Accepted, Rejected, and Backlog sections.\n\nMove any proposal enforceable more reliably by a lint rule, script, metadata flag, or runtime check from Accepted to Backlog. Prefer an existing skill over a new one. A lesson must be durable, decision-changing, and grounded in this session.\n\n## 4. Ask before applying\n\nPresent the full synthesis and wait for explicit approval on the Accepted rows. Do not file backlog items externally unless the user authorizes that destination.\n\nFor approved rows:\n\n- Make a trivial existing-skill edit directly.\n- Route substantive edits, new personal\u002Fshared skills, and description tuning through `anthropic-skill-creator`. Leave Codex's same-purpose product-managed system skill untouched.\n- Run the environment's skill validator when available and inspect the final diff.\n\n## 5. Report\n\n- Edits applied: path and one-line change.\n- New skills: path and purpose.\n- Backlog: proposed mechanism and whether it was filed.\n- Dropped: rejected finding and reason.\n\n\u003C!-- Adapted from poteto\u002Fpstack reflect, MIT License, Lauren Tan, cursor\u002Fplugins@51a96e0. -->\n",{"name":5,"description":7},"main","6ef866230c1ba3459fd08fc65141dfd37fffd41a",0,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills","https:\u002F\u002Fskills.henryzh.dev","https:\u002F\u002Fgithub.com\u002Fcaezium","henryzh.dev","quant, data science, full-stack, robotics.\r\nbuilding cool stuff","2026-08-24 19:21:44",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add caezium\u002Fskills --skill reflect",{"tool":54,"command":55},"bunx","bunx skills add caezium\u002Fskills --skill reflect",{"tool":57,"command":58},"pnpm","pnpm dlx skills add caezium\u002Fskills --skill reflect","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Freflect\u002FSKILL.md",true,[62,66,72,76,80],{"path":63,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":16},"LICENSE","许可证",1067,{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fdivergent-reviewer.md","REFERENCE","参考文档",3936,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Freflect\u002Freferences\u002Fdivergent-reviewer.md",{"path":73,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fjudgment-reviewer.md",3302,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Freflect\u002Freferences\u002Fjudgment-reviewer.md",{"path":77,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fsynthesizer.md",4197,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Freflect\u002Freferences\u002Fsynthesizer.md",{"path":81,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Ftooling-reviewer.md",4775,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Freflect\u002Freferences\u002Ftooling-reviewer.md",[85,107,135,153,174,194],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":101,"publishedAt":34},"01M71JT4RYCAS18RF6003YYR1D","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FSKILL.md",[91,96],{"categoryNo":92,"categoryName":93,"taxonomyType":94,"taxonomyTypeDesc":95},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[102,103,104,105,30,106,31],"writing for agents","for","writing","editing","documents",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":116,"publishedAt":34},"01M71JT0GES4AZ5ADH8EADNN1Z","wrangler","Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwrangler\u002FSKILL.md",[113],{"categoryNo":114,"categoryName":115,"taxonomyType":94,"taxonomyTypeDesc":95},"01JBSEEDCAT000000000000010","后端与接口",[109,117,118,119,120,121,122,123,124,125,126,127,128,103,129,130,131,132,133,134],"cloudflare","d1","knowledge","workflows","cli","secrets","commands","syntax","cloudflare workers","r2","queues","running","containers","correct","load","workers","best practices","store",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":34},"01M71JSWX4R203M32K9A18AAW8","workers-best-practices","Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fworkers-best-practices\u002FSKILL.md",[],[142,132,133,143,144,145,103,117,146,119,147,109,104,131,31,148,149,150,151,152],"workers best practices","observability","reviews","promises","worker","new","code","common","streaming","state","anti-patterns",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":34},"01M71JST6P88MXGT2MWDTPJGEG","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwizard\u002FSKILL.md",[],[155,128,160,103,161,162,163,164,30,165,31,166,167,168,169,170,171,172,173,122],"setting","up","ci","provisioning infrastructure","only","invoke","Bash","one","interactive","can","credentials","dashboard","generate","human",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":178,"sourceHtmlUrl":179,"categories":180,"keywords":181,"publishedAt":34},"01M71JSQ95S7BQ61DAPN95X2W4","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available evidence sources, searches each relevant category, and returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwhy\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwhy\u002FSKILL.md",[],[176,182,183,184,185,103,186,187,30,188,21,189,25,190,191,192,193],"sources","thresholds","evidence","relevant","runtime","design","decisions","how","read","data","rationale","returns",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":203,"publishedAt":34},"01M71JSMHFVSH8HK8GXN6YAX6J","week-prep","Generate a briefing with calendar, tasks, and attention flags. Use for \"week prep\", \"briefing\", or \"what's on this week\".","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fweek-prep\u002FSKILL.md",[200],{"categoryNo":201,"categoryName":202,"taxonomyType":94,"taxonomyTypeDesc":95},"01JBSEEDCAT000000000000023","Skill与智能体开发",[204,205,206,207,208,103,209,210,211,212,30,166,213,214,215,172,216,190,217,218],"week prep","prep","deep","attention","get","search","messages","briefing","MCP","tasks","with","slack","calendar","flags","grep"]