[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71JGRB93CTAH3H5C2454CHG":3,"skill-same:01M71JGRB93CTAH3H5C2454CHG":77},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":5,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":48,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M71JGRB93CTAH3H5C2454CHG","henry-mode",null,"Orchestrate Henry's long-running engineering and research work across recall, consultation, specifications, verification, worker fleets, evidence trails, handoffs, and reflection. Use when work spans sessions or machines, needs autonomous agents, crosses risky runtime boundaries, or Henry asks to resume, run a fleet, keep going, or use Henry mode. Skip small self-contained tasks.","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\u002Fhenry-mode\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"henry mode","mode","verification","self","trails","resume","across","tasks","keep","when","use","autonomous","reflection","worker","sessions","long","runtime","evidence","orchestrate","running","2026-11-10 10:12:30",false,"---\nname: henry-mode\ndescription: Orchestrate Henry's long-running engineering and research work across recall, consultation, specifications, verification, worker fleets, evidence trails, handoffs, and reflection. Use when work spans sessions or machines, needs autonomous agents, crosses risky runtime boundaries, or Henry asks to resume, run a fleet, keep going, or use Henry mode. Skip small self-contained tasks.\n---\n\n# Henry mode\n\nTreat this as a router over the installed skills, not a second implementation of them. The objective is a resumable chain of verifiable units whose evidence survives the current context window.\n\n## 1. Reconstruct before deciding\n\n- When prior work matters or the task resumes elsewhere, use `recall` to combine relevant Claude\u002FCodex history with current repository state.\n- Use `why` when intent, history, or an old trade-off is unclear; use `how` when the missing piece is the current runtime flow or ownership map.\n- State the recovered objective, settled decisions, live constraints, and last verified checkpoint. Do not carry old conclusions forward when the code or external state disproves them.\n\nCompletion criterion: the next decision can be made from current evidence without rereading raw history.\n\n## 2. Settle direction\n\n- If meaningful product or design direction remains unresolved, `consult-first` wins. Use model-invocable helpers such as `prototype` or `domain-modeling` only as the question requires. When a persistent decision map or live documented interview would materially help, recommend the user-invoked `\u002Fwayfinder` or `\u002Fgrill-with-docs` workflow and wait for the user's choice.\n- If direction is already approved, do not create another planning ceremony. When a published artifact or independent work units would be useful, recommend `\u002Fto-spec` or `\u002Fto-tickets`; those user-invoked skills own the tracker writes.\n\nCompletion criterion: consequential choices are approved, and every unresolved choice is explicit rather than smuggled into implementation.\n\n## 3. Define proof and worker contracts\n\n- Reuse the project's verification skill when one exists. For a long-lived project without one, use `create-verification-skill`; maintain it with `maintain-verification-skill` when surfaces drift.\n- Use `writing-for-agents` for briefs, acceptance contracts, pointers, and worker output schemas.\n- Use `technical-writing` for a user-invoked documentation pass when the artifact needs an explicit tutorial, how-to, reference, or explanation shape.\n- Apply `principle-prove-it-works`, `principle-build-the-lever`, and `principle-sequence-verifiable-units`: prefer a rerunnable test, evaluator, parser, or harness over a one-off assertion.\n\nCompletion criterion: every implementation unit has an observable success condition and an owner for its output.\n\n## 4. Execute on the smallest safe topology\n\n- Single path: execute the authorized implementation directly, or use `diagnosing-bugs` for a failure → the one shared `tdd` skill where appropriate → `code-review`. Do not invoke `\u002Fimplement` on the user's behalf; that workflow includes commits and remains user-invoked.\n- Boundary-crossing change: add `blast-radius` and prove the one runtime safety fact most likely to fail.\n- At external inputs, apply `principle-boundary-discipline`; for typed code, apply `principle-type-system-discipline` and `typescript-best-practices` where relevant.\n- Parallel coverage: use `swarm`. Give workers isolated directories\u002Fstate, explicit resource budgets, non-overlapping briefs, and a root aggregator. Apply `principle-guard-the-context-window`; return conclusions and artifact paths instead of raw exploration.\n- For retries, restarts, lifecycle commands, or repeated automation, apply `principle-make-operations-idempotent`. For concurrent work, apply `principle-separate-before-serializing-shared-state` before reaching for locks.\n- Keep `show-me-your-work` active for autonomous or expensive work. Record decisions, evidence, attempted approaches, rejection reasons, checkpoints, and the next recovery command.\n\nCompletion criterion: each unit either passes its proof or leaves a precise, non-duplicative failure record; shared mutable state never becomes an accidental coordination channel.\n\n## 5. Close the loop\n\n- Re-run the authoritative verification from a clean enough state to catch hidden dependencies.\n- Update the verification map when the implementation changed a user-visible or operational surface.\n- Use `reflect` after expensive, surprising, or repeated work. Propose durable changes to a test, script, rule, skill, or architecture, but keep shared-skill edits reviewable.\n- If work must continue in another context, recommend `\u002Fhandoff` after verification—not before it—so the user can choose when to create the cross-session artifact.\n\nCompletion criterion: the outcome is proved, the durable lesson has a home, and another agent can resume without reconstructing the whole run.\n\n## Autonomy boundary\n\nAn instruction to keep going increases persistence, not authority. Continue without waiting only when direction is settled, actions remain within the user's authorized scope and host safety rules, and recovery is possible. Otherwise surface the decision with the evidence needed to make it quickly.\n","# Henry mode\n\nTreat this as a router over the installed skills, not a second implementation of them. The objective is a resumable chain of verifiable units whose evidence survives the current context window.\n\n## 1. Reconstruct before deciding\n\n- When prior work matters or the task resumes elsewhere, use `recall` to combine relevant Claude\u002FCodex history with current repository state.\n- Use `why` when intent, history, or an old trade-off is unclear; use `how` when the missing piece is the current runtime flow or ownership map.\n- State the recovered objective, settled decisions, live constraints, and last verified checkpoint. Do not carry old conclusions forward when the code or external state disproves them.\n\nCompletion criterion: the next decision can be made from current evidence without rereading raw history.\n\n## 2. Settle direction\n\n- If meaningful product or design direction remains unresolved, `consult-first` wins. Use model-invocable helpers such as `prototype` or `domain-modeling` only as the question requires. When a persistent decision map or live documented interview would materially help, recommend the user-invoked `\u002Fwayfinder` or `\u002Fgrill-with-docs` workflow and wait for the user's choice.\n- If direction is already approved, do not create another planning ceremony. When a published artifact or independent work units would be useful, recommend `\u002Fto-spec` or `\u002Fto-tickets`; those user-invoked skills own the tracker writes.\n\nCompletion criterion: consequential choices are approved, and every unresolved choice is explicit rather than smuggled into implementation.\n\n## 3. Define proof and worker contracts\n\n- Reuse the project's verification skill when one exists. For a long-lived project without one, use `create-verification-skill`; maintain it with `maintain-verification-skill` when surfaces drift.\n- Use `writing-for-agents` for briefs, acceptance contracts, pointers, and worker output schemas.\n- Use `technical-writing` for a user-invoked documentation pass when the artifact needs an explicit tutorial, how-to, reference, or explanation shape.\n- Apply `principle-prove-it-works`, `principle-build-the-lever`, and `principle-sequence-verifiable-units`: prefer a rerunnable test, evaluator, parser, or harness over a one-off assertion.\n\nCompletion criterion: every implementation unit has an observable success condition and an owner for its output.\n\n## 4. Execute on the smallest safe topology\n\n- Single path: execute the authorized implementation directly, or use `diagnosing-bugs` for a failure → the one shared `tdd` skill where appropriate → `code-review`. Do not invoke `\u002Fimplement` on the user's behalf; that workflow includes commits and remains user-invoked.\n- Boundary-crossing change: add `blast-radius` and prove the one runtime safety fact most likely to fail.\n- At external inputs, apply `principle-boundary-discipline`; for typed code, apply `principle-type-system-discipline` and `typescript-best-practices` where relevant.\n- Parallel coverage: use `swarm`. Give workers isolated directories\u002Fstate, explicit resource budgets, non-overlapping briefs, and a root aggregator. Apply `principle-guard-the-context-window`; return conclusions and artifact paths instead of raw exploration.\n- For retries, restarts, lifecycle commands, or repeated automation, apply `principle-make-operations-idempotent`. For concurrent work, apply `principle-separate-before-serializing-shared-state` before reaching for locks.\n- Keep `show-me-your-work` active for autonomous or expensive work. Record decisions, evidence, attempted approaches, rejection reasons, checkpoints, and the next recovery command.\n\nCompletion criterion: each unit either passes its proof or leaves a precise, non-duplicative failure record; shared mutable state never becomes an accidental coordination channel.\n\n## 5. Close the loop\n\n- Re-run the authoritative verification from a clean enough state to catch hidden dependencies.\n- Update the verification map when the implementation changed a user-visible or operational surface.\n- Use `reflect` after expensive, surprising, or repeated work. Propose durable changes to a test, script, rule, skill, or architecture, but keep shared-skill edits reviewable.\n- If work must continue in another context, recommend `\u002Fhandoff` after verification—not before it—so the user can choose when to create the cross-session artifact.\n\nCompletion criterion: the outcome is proved, the durable lesson has a home, and another agent can resume without reconstructing the whole run.\n\n## Autonomy boundary\n\nAn instruction to keep going increases persistence, not authority. Continue without waiting only when direction is settled, actions remain within the user's authorized scope and host safety rules, and recovery is possible. Otherwise surface the decision with the evidence needed to make it quickly.\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":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add caezium\u002Fskills --skill henry-mode",{"tool":59,"command":60},"bunx","bunx skills add caezium\u002Fskills --skill henry-mode",{"tool":62,"command":63},"pnpm","pnpm dlx skills add caezium\u002Fskills --skill henry-mode","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fhenry-mode\u002FSKILL.md",true,[67,73],{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"agents\u002Fopenai.yaml","REFERENCE","参考文档",104,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fhenry-mode\u002Fagents\u002Fopenai.yaml",{"path":74,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":75,"sourceHtmlUrl":76},"evals\u002Fevals.json",1104,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fhenry-mode\u002Fevals\u002Fevals.json",[78,100,127,144,165,185],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":94,"publishedAt":39},"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",[84,89],{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[95,96,97,98,29,99,28],"writing for agents","for","writing","editing","documents",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":109,"publishedAt":39},"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",[106],{"categoryNo":107,"categoryName":108,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000010","后端与接口",[102,110,111,112,113,114,115,116,117,118,119,120,38,96,121,122,123,124,125,126],"cloudflare","d1","knowledge","workflows","cli","secrets","commands","syntax","cloudflare workers","r2","queues","containers","correct","load","workers","best practices","store",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":39},"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",[],[134,124,125,135,136,137,96,110,32,112,138,102,97,123,28,139,140,141,142,143],"workers best practices","observability","reviews","promises","new","code","common","streaming","state","anti-patterns",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":150,"publishedAt":39},"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",[],[146,38,151,96,152,153,154,155,29,156,28,157,158,159,160,161,162,163,164,115],"setting","up","ci","provisioning infrastructure","only","invoke","Bash","one","interactive","can","credentials","dashboard","generate","human",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":169,"sourceHtmlUrl":170,"categories":171,"keywords":172,"publishedAt":39},"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",[],[167,173,174,36,175,96,35,176,29,177,178,179,180,181,182,183,184],"sources","thresholds","relevant","design","decisions","work","how","behavior","read","data","rationale","returns",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":194,"publishedAt":39},"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",[191],{"categoryNo":192,"categoryName":193,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000023","Skill与智能体开发",[195,196,197,198,199,96,200,201,202,203,29,157,26,204,205,163,206,181,207,208],"week prep","prep","deep","attention","get","search","messages","briefing","MCP","with","slack","calendar","flags","grep"]