{"id":"af04ca9d-7891-4ad8-9573-e73c5887a8c7","entityType":"agent","slug":"xiamuwnagwang-yce-enhance","name":"yw-enhance","canonicalUrl":"https://www.xpersona.co/agent/xiamuwnagwang-yce-enhance","canonicalPath":"/agent/xiamuwnagwang-yce-enhance","generatedAt":"2026-10-10T04:09:04.185Z","source":"GITHUB_OPENCLEW","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"description":"提示词智能增强 Skill。对用户提示词进行深度增强，内置多源搜索能力 支持两种调用模式（通过 YOUWEN_CALL_MODE 配置）： - `always`：每次收到用户消息后必须先调用增强，再基于增强结果回答。 - `smart`（默认）：仅在语义模糊、缺乏上下文、涉及搜索/研究时自动调用。 【强制规则】调用时必须通过 --history 传入当前会话上下文（最近 3-5 轮或摘要）。 【强制规则】命令执行需 30-60s，必须设置充足超时（timeout ≥ 90s）并一次阻塞等待结果，禁止短 timeout 轮询。stderr 进度和 token 统计不展示给用户。 触发词：优化提示词、增强提示词、enhance prompt、youwen、优问、enhance、提示词优化、prompt enhance、prompt optimize smart 模式额外触发：语义模糊、指代不清、缺乏上下文的技术提问、需要搜索研究的问题、复杂架构设计讨论、实时信息、最新新闻、技术文档查询、开源项目调研 跳过场景：意图明确且上下文充分、纯闲聊/打招呼、简单确认（是/否/好的/继续）、文件/git/系统操作指令、纯数学计算 调用示例：node <skill-dir>/scripts/youwen.js enhance \"用户原始提示词\" --history \"User: ...\\nAI: ...\\nUser: ...\" --auto-confirm --auto-skills --- name: yw-enhance version: 1.2.0 description: | 提示词智能增强 Skill。对用户提示词进行深度增强，内置多源搜索能力 支持两种调用模式（通过 YOUWEN_CALL_MODE 配置）： - always：每次收到用户消息后必须先调用增强，再基于增强结果回答。 - smart（默认）：仅在语义模糊、缺乏上下文、涉及搜索/研究时自动调用。 【强制规则】调用时必须通过 --history 传入当前会话上下文（最近 3-5 轮或摘要）。 【强制规则】命令执行需 30-60s，必须设置充足超时（timeout ≥ 90s）并一次阻塞等待结果，禁止短 timeout 轮询。stderr 进度和 token 统计不展示给用户。 触发词：优化提示词、增强提示词、enhance prompt、youwen、优问、enhance、提示词优化、prompt enhance、prompt opti","descriptionLabel":"Technical summary","evidenceSummary":"Published capability contract available. No trust telemetry is available yet. 5 GitHub stars reported by the source. Last updated 4/15/2026.","installCommand":"git clone https://github.com/xiamuwnagwang/YCE-enhance.git","sourceUrl":"https://github.com/xiamuwnagwang/YCE-enhance","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/xiamuwnagwang/YCE-enhance","kind":"source"}],"safetyScore":100,"overallRank":32.695,"popularityScore":19,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"提示词智能增强 Skill。对用户提示词进行深度增强，内置多源搜索能力 支持两种调用模式（通过 YOUWEN_CALL_MODE 配置）： - `always`：每次收到用户消息后必须先调用增强，再基于增强结果回答。 - `smart`（默认）：仅在语义模糊、缺乏上下文、涉及搜索/研究时自动调用。 【强制规则】调用时必"},"coverage":{"evidence":{"source":"capability-contract + public-profile","verified":true,"confidence":"high","updatedAt":"2026-02-24T19:44:12.529Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"medium","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"stars":5,"forks":1,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":"5 GitHub stars"},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-02-23T21:26:40.731Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T05:21:22.124Z","lastCrawledAt":"2026-02-23T21:26:40.731Z","lastIndexedAt":null,"nextCrawlAt":"2026-02-24T21:26:40.731Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"capability-contract","verified":true,"confidence":"high","updatedAt":"2026-02-24T19:44:12.529Z","emptyReason":null},"installCommand":"git clone https://github.com/xiamuwnagwang/YCE-enhance.git","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"ready","authModes":["api_key"],"requires":["openclew","lang:typescript"],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":"https://github.com/xiamuwnagwang/YCE-enhance#input","outputSchemaRef":"https://github.com/xiamuwnagwang/YCE-enhance#output","dataRegion":"global","contractUpdatedAt":"2026-02-24T19:44:12.529Z","sourceUpdatedAt":"2026-02-24T19:44:12.529Z","freshnessSeconds":19643091},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/xiamuwnagwang-yce-enhance/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/xiamuwnagwang-yce-enhance/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/xiamuwnagwang-yce-enhance/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/xiamuwnagwang-yce-enhance/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/xiamuwnagwang-yce-enhance/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/xiamuwnagwang-yce-enhance/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_OPENCLEW","generatedAt":"2026-10-10T04:09:04.185Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/xiamuwnagwang-yce-enhance/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/xiamuwnagwang-yce-enhance/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/xiamuwnagwang-yce-enhance/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/xiamuwnagwang-yce-enhance/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":[],"safeUseWhen":["Contract is available with explicit auth and schema references.","Trust confidence is not low and verification freshness is acceptable."],"riskFlags":["trust_data_unavailable"],"operationalConfidence":"medium"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"readme":"---\nname: yw-enhance\nversion: 1.2.0\ndescription: |\n  提示词智能增强 Skill。对用户提示词进行深度增强，内置多源搜索能力\n  支持两种调用模式（通过 YOUWEN_CALL_MODE 配置）：\n  - `always`：每次收到用户消息后必须先调用增强，再基于增强结果回答。\n  - `smart`（默认）：仅在语义模糊、缺乏上下文、涉及搜索/研究时自动调用。\n  【强制规则】调用时必须通过 --history 传入当前会话上下文（最近 3-5 轮或摘要）。\n  【强制规则】命令执行需 30-60s，必须设置充足超时（timeout ≥ 90s）并一次阻塞等待结果，禁止短 timeout 轮询。stderr 进度和 token 统计不展示给用户。\n  触发词：优化提示词、增强提示词、enhance prompt、youwen、优问、enhance、提示词优化、prompt enhance、prompt optimize\n  smart 模式额外触发：语义模糊、指代不清、缺乏上下文的技术提问、需要搜索研究的问题、复杂架构设计讨论、实时信息、最新新闻、技术文档查询、开源项目调研\n  跳过场景：意图明确且上下文充分、纯闲聊/打招呼、简单确认（是/否/好的/继续）、文件/git/系统操作指令、纯数学计算\n  调用示例：node <skill-dir>/scripts/youwen.js enhance \"用户原始提示词\" --history \"User: ...\\nAI: ...\\nUser: ...\" --auto-confirm --auto-skills\nuser-invocable: true\n---\n\n# 提示词智能增强\n\n\n## 快速调用（AI Agent 复制即用）\n\n\n**📌 路径说明**：命令使用相对路径 `./scripts/`，表示相对于 skill 根目录。\n- 设置环境变量：`export SKILLS_ROOT=~/.agents/skills`\n- 实际调用：`node $SKILLS_ROOT/yw-enhance/scripts/youwen.js ...`\n\n**📌 安装说明**：\n- 安装到 `.agents` 目录：`bash install.sh --target agents`（需要 `~/.agents/skills` 目录存在）\n- 安装到其他工具：`bash install.sh --target claude` / `cursor` / `windsurf` 等\n- `agents` 选项会动态检测 `~/.agents/skills` 目录，不存在时不显示该选项\n\n```bash\nnode $SKILLS_ROOT/yw-enhance/scripts/youwen.js enhance \"用户提示词\" \\\n  --history \"User: ...\\nAI: ...\\nUser: ...\" \\\n  --auto-confirm --auto-skills\n```\n\n- 超时设置 ≥ 90s（4-Agent 流水线需要 30-60s）\n- 一次阻塞等待结果，禁止短 timeout 轮询\n- macOS 下不要用 `timeout` 命令包裹\n\n## 调用判断（smart 模式决策树）\n\n```\n用户消息 → 是否包含触发词？ → 是 → 调用\n                ↓ 否\n         语义模糊/指代不清？ → 是 → 调用\n                ↓ 否\n         缺乏上下文的技术提问？ → 是 → 调用\n                ↓ 否\n         需要搜索/研究/实时信息？ → 是 → 调用\n                ↓ 否\n         复杂架构/设计讨论？ → 是 → 调用\n                ↓ 否\n         跳过（直接回答）\n```\n\n## 输出处理\n\nstdout 输出 XML 标签格式：\n\n```xml\n<enhanced>\n增强后的提示词内容...\n</enhanced>\n<auto-skills>\n<skill name=\"ace\" reason=\"推荐使用 ace 辅助完成任务\" command=\"bash ...\" />\n<skill name=\"pplx\" reason=\"联网搜索实时信息\" />\n</auto-skills>\n```\n\nAI Agent 处理步骤：\n1. 读取 `<enhanced>` 内容作为增强提示词\n2. 解析 `<auto-skills>` 中的推荐工具，按需调用\n3. 基于增强提示词继续回答用户（而非原始提示词）\n4. stderr 进度信息和 `--- Token 统计 ---` 不展示给用户\n5. exit code 非 0 → 失败，直接用原始提示词回答\n\n## 参数说明\n\n| 参数 | 必须 | 说明 |\n|------|:---:|------|\n| `--history <text>` | ✅ | 对话上下文，格式：`User: ...\\nAI: ...\\nUser: ...` |\n| `--auto-confirm` | ✅ | 跳过交互式确认（AI Agent 无法交互输入） |\n| `--auto-skills` | ✅ | 自动注入可用 skill 上下文 |\n| `--no-search` | 可选 | 禁用搜索（简单问题可加此参数加速） |\n| `--token <code>` | 可选 | 兑换码，覆盖环境变量 `YOUWEN_TOKEN` |\n| `--force` | 可选 | 强制执行（忽略 disabled 模式） |\n\n## 上下文传入策略\n\n| 对话长度 | 策略 |\n|---------|------|\n| < 2000 字 | 直接传入完整对话 |\n| > 2000 字 | 最近 3-5 轮 + 关键上下文摘要 |\n| 涉及代码 | 将关键代码片段包含在 history 中 |\n| 首轮对话 | history 留空或传入项目背景信息 |\n\n## 配置\n\n环境变量通过 `<skill-dir>/.env` 配置：\n\n| 变量 | 说明 | 默认值 |\n|------|------|--------|\n| `YOUWEN_CALL_MODE` | `smart`（智能判断）/ `always`（每次调用） | `smart` |\n| `YOUWEN_API_URL` | 后端地址 | `https://b.aigy.de` |\n| `YOUWEN_TOKEN` | 兑换码 | 空 |\n| `YOUWEN_ENHANCE_MODE` | `agent` / `disabled` | `agent` |\n| `YOUWEN_ENABLE_SEARCH` | `true` / `false` | `true` |\n| `YOUWEN_MGREP_API_KEY` | 语义检索增强 Key | 空 |\n\n## References\n\n详见 `references/` 目录。\n","readmeExcerpt":"--- name: yw-enhance version: 1.2.0 description: | 提示词智能增强 Skill。对用户提示词进行深度增强，内置多源搜索能力 支持两种调用模式（通过 YOUWEN_CALL_MODE 配置）： - always：每次收到用户消息后必须先调用增强，再基于增强结果回答。 - smart（默认）：仅在语义模糊、缺乏上下文、涉及搜索/研究时自动调用。 【强制规则】调用时必须通过 --history 传入当前会话上下文（最近 3-5 轮或摘要）。 【强制规则】命令执行需 30-60s，必须设置充足超时（timeout ≥ 90s）并一次阻塞等待结果，禁止短 timeout 轮询。stderr 进度和 token 统计不展示给用户。 触发词：优化提示词、增强提示词、enhance prompt、youwen、优问、enhance、提示词优化、prompt enhance、prompt opti","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"node $SKILLS_ROOT/yw-enhance/scripts/youwen.js enhance \"用户提示词\" \\\n  --history \"User: ...\\nAI: ...\\nUser: ...\" \\\n  --auto-confirm --auto-skills"},{"language":"text","snippet":"用户消息 → 是否包含触发词？ → 是 → 调用\n                ↓ 否\n         语义模糊/指代不清？ → 是 → 调用\n                ↓ 否\n         缺乏上下文的技术提问？ → 是 → 调用\n                ↓ 否\n         需要搜索/研究/实时信息？ → 是 → 调用\n                ↓ 否\n         复杂架构/设计讨论？ → 是 → 调用\n                ↓ 否\n         跳过（直接回答）"},{"language":"xml","snippet":"<enhanced>\n增强后的提示词内容...\n</enhanced>\n<auto-skills>\n<skill name=\"ace\" reason=\"推荐使用 ace 辅助完成任务\" command=\"bash ...\" />\n<skill name=\"pplx\" reason=\"联网搜索实时信息\" />\n</auto-skills>"}],"parameters":{},"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["typescript"],"docsSourceLabel":"GITHUB OPENCLEW","editorialOverview":"提示词智能增强 Skill。对用户提示词进行深度增强，内置多源搜索能力 支持两种调用模式（通过 YOUWEN_CALL_MODE 配置）： - `always`：每次收到用户消息后必须先调用增强，再基于增强结果回答。 - `smart`（默认）：仅在语义模糊、缺乏上下文、涉及搜索/研究时自动调用。 【强制规则】调用时必须通过 --history 传入当前会话上下文（最近 3-5 轮或摘要）。 【强制规则】命令执行需 30-60s，必须设置充足超时（timeout ≥ 90s）并一次阻塞等待结果，禁止短 timeout 轮询。stderr 进度和 token 统计不展示给用户。 触发词：优化提示词、增强提示词、enhance prompt、youwen、优问、enhance、提示词优化、prompt enhance、prompt optimize smart 模式额外触发：语义模糊、指代不清、缺乏上下文的技术提问、需要搜索研究的问题、复杂架构设计讨论、实时信息、最新新闻、技术文档查询、开源项目调研 跳过场景：意图明确且上下文充分、纯闲聊/打招呼、简单确认（是/否/好的/继续）、文件/git/系统操作指令、纯数学计算 调用示例：node <skill-dir>/scripts/youwen.js enhance \"用户原始提示词\" --history \"User: ...\\nAI: ...\\nUser: ...\" --auto-confirm --auto-skills --- name: yw-enhance version: 1.2.0 description: | 提示词智能增强 Skill。对用户提示词进行深度增强，内置多源搜索能力 支持两种调用模式（通过 YOUWEN_CALL_MODE 配置）： - always：每次收到用户消息后必须先调用增强，再基于增强结果回答。 - smart（默认）：仅在语义模糊、缺乏上下文、涉及搜索/研究时自动调用。 【强制规则】调用时必须通过 --history 传入当前会话上下文（最近 3-5 轮或摘要）。 【强制规则】命令执行需 30-60s，必须设置充足超时（timeout ≥ 90s）并一次阻塞等待结果，禁止短 timeout 轮询。stderr 进度和 token 统计不展示给用户。 触发词：优化提示词、增强提示词、enhance prompt、youwen、优问、enhance、提示词优化、prompt enhance、prompt opti","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":370,"uniquenessScore":65,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T04:09:04.185Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_openclew","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}