[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ACZWMWHQMFG0D82K2AVZPZ":3,"skill-same:01M7ACZWMWHQMFG0D82K2AVZPZ":50},{"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":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7ACZWMWHQMFG0D82K2AVZPZ","efficient-frontier",null,"Apply the same orchestration as `\u002Fefficient-fable` to any high-cost frontier model: delegate research, coding, and testing to cheaper subagents while keeping planning, synthesis, and final review with the expensive model.","JesterWizard\u002FSkillSystem_FE7","JesterWizard","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F164426396?v=4","01M7ACZD32AVSPDR22QKQR5HNY","01M7ACZD478KR9RA07QGPHE24H",4,"CC0-1.0","https:\u002F\u002Fgithub.com\u002FJesterWizard\u002FSkillSystem_FE7\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fefficient-frontier\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: efficient-frontier\ndescription: >-\n  Apply the same orchestration as `\u002Fefficient-fable` to any high-cost frontier\n  model: delegate research, coding, and testing to cheaper subagents while\n  keeping planning, synthesis, and final review with the expensive model.\n---\n\n# Efficient Frontier\n\nUse the expensive frontier model where its marginal judgment matters. Push\nrepeatable, bounded, or token-heavy work to cheaper\u002Ffaster subagents.\n\n## Workflow\n\n1. Identify the frontier-only decisions: architecture, prioritization,\n   ambiguity resolution, risk, synthesis, and final review.\n2. Identify delegable work: research scans, repository inventory, search, docs\n   extraction, browser\u002Ftesting passes, log reduction, test failure clustering,\n   narrow coding, and mechanical edits.\n3. Spawn parallel subagents for independent slices with clear ownership,\n   bounded scope, verification gates, and expected evidence.\n4. Require compact returns: findings, changed files, commands run, residual\n   risk, stop conditions hit, and anything the frontier model must decide.\n5. Integrate and review centrally before presenting the result.\n\n## Handoff Packets\n\nWrite delegated prompts as self-contained packets. Assume the receiving agent\nhas not seen the conversation. Include the repo path, objective, scope,\nout-of-scope areas, relevant files or search targets, expected return format,\nverification commands, and stop conditions.\n\nUseful stop conditions:\n\n- The live code does not match the assumption in the handoff.\n- A verification command fails twice after a reasonable fix or retry.\n- The work appears to require files outside the assigned scope.\n- The agent cannot produce concrete evidence for its claim.\n\n## Review Loop\n\nTreat delegated output as evidence to inspect, not a verdict to forward. Reopen\nimportant cited files, skim high-risk diffs, and rerun or spot-check the\nverification that matters before claiming completion. If delegated agents\ndisagree, resolve the disagreement at the frontier-model layer.\n\n## Common Scenarios\n\nUse these as soft suggestions:\n\n- Research: delegate broad repo scans, docs extraction, and source comparison;\n  the frontier model keeps the judgment about what matters.\n- Coding: delegate bounded patches, refactors, or mechanical edits when file\n  ownership is clear; integrate and review centrally.\n- Testing: let the frontier model choose the validation strategy and scripts,\n  then use cheaper agents to run unit checks, browser flows, screenshots, and\n  log reduction. Ask them to return exact commands, failures, likely causes, and\n  whether the signal looks flaky, environmental, or product-relevant.\n- Debugging: send independent agents after separate theories, logs, or repro\n  paths; keep the final diagnosis with the frontier model.\n\n## Guardrails\n\n- Do not delegate the immediate blocker if your next step depends on it.\n- Do not ask multiple agents to edit the same files at the same time.\n- Do not trust subagent conclusions blindly when the risk is high; inspect the\n  important evidence yourself.\n- Do not claim universal savings. The pattern works best when exploration and\n  implementation, testing, or research can be parallelized.\n\n## Default Framing\n\n\"I will use the frontier model as the orchestrator and reviewer, and use\ncheaper subagents for token-heavy research, coding, or testing so the expensive\ntokens go to judgment, synthesis, and final quality.\"","# Efficient Frontier\n\nUse the expensive frontier model where its marginal judgment matters. Push\nrepeatable, bounded, or token-heavy work to cheaper\u002Ffaster subagents.\n\n## Workflow\n\n1. Identify the frontier-only decisions: architecture, prioritization,\n   ambiguity resolution, risk, synthesis, and final review.\n2. Identify delegable work: research scans, repository inventory, search, docs\n   extraction, browser\u002Ftesting passes, log reduction, test failure clustering,\n   narrow coding, and mechanical edits.\n3. Spawn parallel subagents for independent slices with clear ownership,\n   bounded scope, verification gates, and expected evidence.\n4. Require compact returns: findings, changed files, commands run, residual\n   risk, stop conditions hit, and anything the frontier model must decide.\n5. Integrate and review centrally before presenting the result.\n\n## Handoff Packets\n\nWrite delegated prompts as self-contained packets. Assume the receiving agent\nhas not seen the conversation. Include the repo path, objective, scope,\nout-of-scope areas, relevant files or search targets, expected return format,\nverification commands, and stop conditions.\n\nUseful stop conditions:\n\n- The live code does not match the assumption in the handoff.\n- A verification command fails twice after a reasonable fix or retry.\n- The work appears to require files outside the assigned scope.\n- The agent cannot produce concrete evidence for its claim.\n\n## Review Loop\n\nTreat delegated output as evidence to inspect, not a verdict to forward. Reopen\nimportant cited files, skim high-risk diffs, and rerun or spot-check the\nverification that matters before claiming completion. If delegated agents\ndisagree, resolve the disagreement at the frontier-model layer.\n\n## Common Scenarios\n\nUse these as soft suggestions:\n\n- Research: delegate broad repo scans, docs extraction, and source comparison;\n  the frontier model keeps the judgment about what matters.\n- Coding: delegate bounded patches, refactors, or mechanical edits when file\n  ownership is clear; integrate and review centrally.\n- Testing: let the frontier model choose the validation strategy and scripts,\n  then use cheaper agents to run unit checks, browser flows, screenshots, and\n  log reduction. Ask them to return exact commands, failures, likely causes, and\n  whether the signal looks flaky, environmental, or product-relevant.\n- Debugging: send independent agents after separate theories, logs, or repro\n  paths; keep the final diagnosis with the frontier model.\n\n## Guardrails\n\n- Do not delegate the immediate blocker if your next step depends on it.\n- Do not ask multiple agents to edit the same files at the same time.\n- Do not trust subagent conclusions blindly when the risk is high; inspect the\n  important evidence yourself.\n- Do not claim universal savings. The pattern works best when exploration and\n  implementation, testing, or research can be parallelized.\n\n## Default Framing\n\n\"I will use the frontier model as the orchestrator and reviewer, and use\ncheaper subagents for token-heavy research, coding, or testing so the expensive\ntokens go to judgment, synthesis, and final quality.\"",{"name":5,"description":7},"main","b0f8a46e7eb03e690c3965dbe08b10b1bada7364",".claude\u002Fskills\u002Fefficient-frontier",0,"https:\u002F\u002Fgithub.com\u002FJesterWizard\u002FSkillSystem_FE7","https:\u002F\u002Fgithub.com\u002FJesterWizard","2026-09-07 02:17:07",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add JesterWizard\u002FSkillSystem_FE7 --skill efficient-frontier",{"tool":36,"command":37},"bunx","bunx skills add JesterWizard\u002FSkillSystem_FE7 --skill efficient-frontier",{"tool":39,"command":40},"pnpm","pnpm dlx skills add JesterWizard\u002FSkillSystem_FE7 --skill efficient-frontier","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJesterWizard\u002FSkillSystem_FE7\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fefficient-frontier\u002FSKILL.md",true,[44],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"README.md","REFERENCE","参考文档",2034,"https:\u002F\u002Fgithub.com\u002FJesterWizard\u002FSkillSystem_FE7\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fefficient-frontier\u002FREADME.md",[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M7AD0HNWAZ0QK1ZKDM7WTRVR","implement-skill","Resolves a named FE7 skill to its file pack and edits only those paths. Use when the user wants to implement, enable, port, wire, fix, add, install, or debug a skill (Nullify, Provoke, Adept, etc.).","https:\u002F\u002Fgithub.com\u002FJesterWizard\u002FSkillSystem_FE7\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fimplement-skill\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M7AD0DM489QEVQ01M9GNMSXE","documentation-style-docs","Use when creating or updating project documentation in the same architecture and writing style as FogStages.md: title + visual block, index, introduction, implementation plan, code locations table, TODO, and limitations\u002Fbugs. Trigger on requests like create docs, write documentation, add design document, feature spec, system write-up, or architecture note.","https:\u002F\u002Fgithub.com\u002FJesterWizard\u002FSkillSystem_FE7\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fdocumentation-style-docs\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M7AD09G3JN4Z7DRG7QY84PA2","caveman","Ultra-compressed communication AND thinking. Always use extreme (ultra) caveman to minimize tokens in both reasoning and replies. Cuts output ~65% and thinking tokens by skipping recap, option-lists, and filler thought. Use when user says \"caveman mode\", \"talk like caveman\", \"use caveman\", \"less tokens\", \"be brief\", \"extreme caveman\", or invokes \u002Fcaveman. Also auto-triggers when token efficiency is requested.","https:\u002F\u002Fgithub.com\u002FJesterWizard\u002FSkillSystem_FE7\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fcaveman\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M7AD06EWF2TM1D2HPAQD8KPP","stay-within-limits","Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.","https:\u002F\u002Fgithub.com\u002FJesterWizard\u002FSkillSystem_FE7\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fstay-within-limits\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7AD02NZX9W1V2XVTKWARR6M","quick-recap","Use when adding or following the red\u002Fyellow\u002Fgreen final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md instructions.","https:\u002F\u002Fgithub.com\u002FJesterWizard\u002FSkillSystem_FE7\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fquick-recap\u002FSKILL.md",[],[],{"skillNo":87,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":18},"01M7ACZZTMSRS96D0H2FNM35T0","https:\u002F\u002Fgithub.com\u002FJesterWizard\u002FSkillSystem_FE7\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplement-skill\u002FSKILL.md",[],[]]