[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JVDS79D5ZFPR583W7RA063":3,"skill-same:01M6JVDS79D5ZFPR583W7RA063":63},{"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":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":38,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M6JVDS79D5ZFPR583W7RA063","strategic-compact",null,"上下文优化技能，通过 trigger-based 懒加载和 context composition awareness 自动重组长会话上下文。","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FColin4k1024\u002Ftsp\u002Fskills\u002Fstrategic-compact\u002FSKILL.md",[],[19,20,21,22,23,24,25],"strategic compact","compact","strategic","awareness","Composition","context","trigger","2026-11-10 10:12:30",false,"---\nname: strategic-compact\ndescription: >\n  上下文优化技能，通过 trigger-based 懒加载和 context composition awareness\n  自动重组长会话上下文。\norigin: adapted from ECC\n---\n\n# Strategic Compact Skill\n\n上下文优化技能，通过 trigger-based 懒加载和 context composition awareness 自动重组长会话上下文。\n\n## 何时激活\n\n- Claude Code 触发原生自动或手动 compact\n- 原生 auto-compact 被显式关闭，且会话上下文超过 65% 使用率\n- 需要重组上下文以保留关键信息\n- 长会话中需要压缩早期对话\n- 需要按重要性重新组织 specialist 输出\n\n## 核心功能\n\n### 1. Trigger-Based 懒加载\n\nClaude Code 默认由原生 auto-compact 决定压缩时机；下列百分比 trigger 只用于手动兜底模式：\n\n| Trigger | 条件 | 行为 |\n|---------|------|------|\n| `context_65%` | 上下文使用 > 65% | 触发 advisory 压缩建议 |\n| `context_70%` | 上下文使用 > 70% | 触发压缩建议 |\n| `context_85%` | 上下文使用 > 85% | 强烈建议手动压缩 |\n| `logical_break` | 检测到逻辑断点 | 建议整理 |\n| `specialist_done` | specialist 完成 | 归档输出 |\n\n### 2. Context Composition Awareness\n\n理解上下文不同部分的价值:\n\n**高价值（总是保留）**:\n- 决策和结论\n- 任务输出和验证结果\n- 待处理项和 hints\n- 架构决策记录 (ADR)\n\n**中等价值（根据大小决定）**:\n- 工具输出（超过阈值时压缩）\n- 对话历史（保留首尾，压缩中间）\n- 文件内容（保留路径和关键符号）\n\n**低价值（安全丢弃）**:\n- 纯搜索结果\n- 重复信息\n- 工具调用追踪\n\n## 压缩策略\n\n### Phase 1: 保存决策到内存\n提取所有决策，保存到 `~\u002F.claude\u002Fmemory\u002Ferror_experience\u002Fdecisions\u002F`\n\n### Phase 2: 保存待办到摘要\n提取 pending items 和 next hints，保存到 session summary\n\n### Phase 3: 压缩对话\n保留系统提示和最近 20 轮对话，压缩中间部分\n\n### Phase 4: 精简工具输出\n将长工具输出替换为摘要：`[File X read, Y lines]`\n\n## 与 Other Skills 的关系\n\n| Skill | 关系 |\n|-------|------|\n| Memory Persistence | Strategic Compact 使用其存储来保存决策和摘要 |\n| Error Experience Library | 从压缩的上下文中提取错误模式 |\n| Continuous Learning | Instincts 从归档的上下文中生成 |\n\n## 使用场景\n\n### 场景 1：长会话自动整理\n\n```\n用户：连续工作 2 小时后\nClaude Code：上下文接近原生 auto-compact 阈值\n系统：触发 PreCompact(auto)，保存 compact 轮次并清理旧计量缓存\nClaude Code：自动执行压缩\n系统：下一轮只读取压缩后的新 usage，不复用压缩前的高水位\n```\n\n### 场景 2：Specialist 输出归档\n\n```\n用户：运行 \u002Fcode-review\nSpecialist：输出详细代码审查报告\n系统：检测到 specialist_done trigger\n系统：提取关键结论，丢弃详细追踪\n系统：保存结论到 memory store\n```\n\n## Context 计算与 Compact 轮次\n\n- 运行时使用 `scripts\u002Flib\u002Fcontext-window.js` 统一计算上下文压力。\n- Claude `context_window.used_percentage` \u002F `remaining_percentage` 是官方预计算值，直接使用，不再重复扣除 auto-compact buffer；`context_window_size` 用于区分 200K 与 1M 窗口。\n- 优先消费 CCometixLine-compatible remaining context，例如 `ccometixline.context_window.remaining_percentage`、`ccometixline_context_window.remaining_tokens`、`TSP_CONTEXT_WINDOW_JSON` 或 `CCOMETIXLINE_CONTEXT_FILE`。\n- 如果没有外部 remaining 信号，则退回 Claude `context_window`、transcript JSONL usage、bridge file 和 transcript size fallback。\n- `scripts\u002Fhooks\u002Fpre-compact.js` 同时匹配 `auto|manual`，每次 PreCompact 会递增 `.tsp\u002Fcontext\u002Fcompact-state.json` 的 session \u002F total compact count，并清除压缩前的 bridge \u002F debounce 状态。\n- transcript 遇到 compact summary 后不会回读 summary 前的 usage；等待下一次 API 响应提供新窗口指标。\n- `suggest-compact.js` 默认 `auto` 模式，不注入人工 `\u002Fcompact` 提示；仅在 `DISABLE_AUTO_COMPACT=1` 或 `STRATEGIC_COMPACT_MODE=manual` 时启用下表的手动兜底。\n\n## 手动兜底阈值\n\n| 使用率 | 紧迫度 | 建议操作 |\n|--------|--------|---------|\n| \u003C 65% | low | 无需操作 |\n| 65-70% | advisory | 提醒控制上下文增长 |\n| 70-85% | medium | 建议压缩，可选择性执行 |\n| 85-95% | high | 强烈建议压缩 |\n| > 95% | critical | 必须立即压缩 |\n\n## 命令接入\n\n- `\u002Fcompact` - 手动触发压缩\n- `\u002Fcompact status` - 显示当前上下文使用率\n- `\u002Fcompact plan` - 显示压缩计划而不执行\n","# Strategic Compact Skill\n\n上下文优化技能，通过 trigger-based 懒加载和 context composition awareness 自动重组长会话上下文。\n\n## 何时激活\n\n- Claude Code 触发原生自动或手动 compact\n- 原生 auto-compact 被显式关闭，且会话上下文超过 65% 使用率\n- 需要重组上下文以保留关键信息\n- 长会话中需要压缩早期对话\n- 需要按重要性重新组织 specialist 输出\n\n## 核心功能\n\n### 1. Trigger-Based 懒加载\n\nClaude Code 默认由原生 auto-compact 决定压缩时机；下列百分比 trigger 只用于手动兜底模式：\n\n| Trigger | 条件 | 行为 |\n|---------|------|------|\n| `context_65%` | 上下文使用 > 65% | 触发 advisory 压缩建议 |\n| `context_70%` | 上下文使用 > 70% | 触发压缩建议 |\n| `context_85%` | 上下文使用 > 85% | 强烈建议手动压缩 |\n| `logical_break` | 检测到逻辑断点 | 建议整理 |\n| `specialist_done` | specialist 完成 | 归档输出 |\n\n### 2. Context Composition Awareness\n\n理解上下文不同部分的价值:\n\n**高价值（总是保留）**:\n- 决策和结论\n- 任务输出和验证结果\n- 待处理项和 hints\n- 架构决策记录 (ADR)\n\n**中等价值（根据大小决定）**:\n- 工具输出（超过阈值时压缩）\n- 对话历史（保留首尾，压缩中间）\n- 文件内容（保留路径和关键符号）\n\n**低价值（安全丢弃）**:\n- 纯搜索结果\n- 重复信息\n- 工具调用追踪\n\n## 压缩策略\n\n### Phase 1: 保存决策到内存\n提取所有决策，保存到 `~\u002F.claude\u002Fmemory\u002Ferror_experience\u002Fdecisions\u002F`\n\n### Phase 2: 保存待办到摘要\n提取 pending items 和 next hints，保存到 session summary\n\n### Phase 3: 压缩对话\n保留系统提示和最近 20 轮对话，压缩中间部分\n\n### Phase 4: 精简工具输出\n将长工具输出替换为摘要：`[File X read, Y lines]`\n\n## 与 Other Skills 的关系\n\n| Skill | 关系 |\n|-------|------|\n| Memory Persistence | Strategic Compact 使用其存储来保存决策和摘要 |\n| Error Experience Library | 从压缩的上下文中提取错误模式 |\n| Continuous Learning | Instincts 从归档的上下文中生成 |\n\n## 使用场景\n\n### 场景 1：长会话自动整理\n\n```\n用户：连续工作 2 小时后\nClaude Code：上下文接近原生 auto-compact 阈值\n系统：触发 PreCompact(auto)，保存 compact 轮次并清理旧计量缓存\nClaude Code：自动执行压缩\n系统：下一轮只读取压缩后的新 usage，不复用压缩前的高水位\n```\n\n### 场景 2：Specialist 输出归档\n\n```\n用户：运行 \u002Fcode-review\nSpecialist：输出详细代码审查报告\n系统：检测到 specialist_done trigger\n系统：提取关键结论，丢弃详细追踪\n系统：保存结论到 memory store\n```\n\n## Context 计算与 Compact 轮次\n\n- 运行时使用 `scripts\u002Flib\u002Fcontext-window.js` 统一计算上下文压力。\n- Claude `context_window.used_percentage` \u002F `remaining_percentage` 是官方预计算值，直接使用，不再重复扣除 auto-compact buffer；`context_window_size` 用于区分 200K 与 1M 窗口。\n- 优先消费 CCometixLine-compatible remaining context，例如 `ccometixline.context_window.remaining_percentage`、`ccometixline_context_window.remaining_tokens`、`TSP_CONTEXT_WINDOW_JSON` 或 `CCOMETIXLINE_CONTEXT_FILE`。\n- 如果没有外部 remaining 信号，则退回 Claude `context_window`、transcript JSONL usage、bridge file 和 transcript size fallback。\n- `scripts\u002Fhooks\u002Fpre-compact.js` 同时匹配 `auto|manual`，每次 PreCompact 会递增 `.tsp\u002Fcontext\u002Fcompact-state.json` 的 session \u002F total compact count，并清除压缩前的 bridge \u002F debounce 状态。\n- transcript 遇到 compact summary 后不会回读 summary 前的 usage；等待下一次 API 响应提供新窗口指标。\n- `suggest-compact.js` 默认 `auto` 模式，不注入人工 `\u002Fcompact` 提示；仅在 `DISABLE_AUTO_COMPACT=1` 或 `STRATEGIC_COMPACT_MODE=manual` 时启用下表的手动兜底。\n\n## 手动兜底阈值\n\n| 使用率 | 紧迫度 | 建议操作 |\n|--------|--------|---------|\n| \u003C 65% | low | 无需操作 |\n| 65-70% | advisory | 提醒控制上下文增长 |\n| 70-85% | medium | 建议压缩，可选择性执行 |\n| 85-95% | high | 强烈建议压缩 |\n| > 95% | critical | 必须立即压缩 |\n\n## 命令接入\n\n- `\u002Fcompact` - 手动触发压缩\n- `\u002Fcompact status` - 显示当前上下文使用率\n- `\u002Fcompact plan` - 显示压缩计划而不执行\n",{"name":5,"origin":31,"description":32},"adapted from ECC","上下文优化技能，通过 trigger-based 懒加载和 context composition awareness 自动重组长会话上下文。\n","main","b0f0a87593c578a7898eccaf1b363f7f87c1f99b","plugins\u002FColin4k1024\u002Ftsp\u002Fskills\u002Fstrategic-compact",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill strategic-compact",{"tool":49,"command":50},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill strategic-compact",{"tool":52,"command":53},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill strategic-compact","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FColin4k1024\u002Ftsp\u002Fskills\u002Fstrategic-compact\u002FSKILL.md",true,[57],{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"agents\u002Fopenai.yaml","REFERENCE","参考文档",263,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FColin4k1024\u002Ftsp\u002Fskills\u002Fstrategic-compact\u002Fagents\u002Fopenai.yaml",[64,74,82,90,98,106],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":69,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":73},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":78,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":73},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":86,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":73},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":94,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":73},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"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":68,"licenseFileUrl":102,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":73},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":110,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":73},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]