{"id":"5a1cc630-1dbf-4cfb-9ead-eac19ba293d3","entityType":"agent","slug":"clawhub-william202404-tob-win-loss-review","name":"Tob Win Loss Review","canonicalUrl":"https://www.xpersona.co/agent/clawhub-william202404-tob-win-loss-review","canonicalPath":"/agent/clawhub-william202404-tob-win-loss-review","generatedAt":"2026-10-13T07:54:59.062Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-12T00:58:26.141Z","emptyReason":null},"description":"ToB销售丢单复盘助手。输入行业/规模/阶段/竞品/关键事件，使用原创销售经验规则引擎输出根因分析、风险信号和改进建议。 Skill: Tob Win Loss Review Owner: william202404 Summary: ToB销售丢单复盘助手。输入行业/规模/阶段/竞品/关键事件，使用原创销售经验规则引擎输出根因分析、风险信号和改进建议。 Tags: latest:2.0.2 Version history: v2.0.2 | 2026-07-07T16:18:19.828Z | auto - Added detailed usage documentation in README.md. - Introduced scripts/tob_win_loss_review.py file, setting up the main script structure. - Minor metadata alignment in SKILL.md (added slug, displayName fields). v2.0.1 | 2026","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 964 downloads reported by the source. Last updated 10/12/2026.","installCommand":"clawhub skill install s176t36qq1w6j18d0hyxc24yhx83pa2x:tob-win-loss-review","sourceUrl":"https://clawhub.ai/william202404/tob-win-loss-review","homepage":"https://clawhub.ai/william202404/skills/tob-win-loss-review","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/william202404/tob-win-loss-review","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/william202404/skills/tob-win-loss-review","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"ToB销售丢单复盘助手。输入行业/规模/阶段/竞品/关键事件，使用原创销售经验规则引擎输出根因分析、风险信号和改进建议。 Skill: Tob Win Loss Review Owner: william202404 Summary: ToB销售丢单复盘助手。输入行业/规模/阶段/竞品/关键事件，使用原创销售经验规则引"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-12T00:58:26.141Z","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":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T00:58:26.141Z","emptyReason":null},"stars":null,"forks":null,"downloads":964,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"2.0.2","tractionLabel":"964 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T00:58:26.084Z","emptyReason":null},"lastUpdatedAt":"2026-10-12T00:58:26.141Z","lastCrawledAt":"2026-10-12T00:58:26.084Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-13T00:58:26.084Z","lastVerifiedAt":null,"highlights":[{"version":"2.0.2","createdAt":"2026-07-07T16:18:19.828Z","changelog":"- Added detailed usage documentation in README.md. - Introduced scripts/tob_win_loss_review.py file, setting up the main script structure. - Minor metadata alignment in SKILL.md (added slug, displayName fields).","fileCount":5,"zipByteSize":8996},{"version":"2.0.1","createdAt":"2026-07-05T14:25:25.637Z","changelog":"Summary: Major cleanup for documentation and code, keeping only core docs. - Removed README.md, main script, and skill card files to streamline the skill package. - SKILL.md was simplified: references to “李宁原创”替换为中性表述；源说明和workers格式调整。 - No user-facing features or logic changed; only documentation and packaging structure updated.","fileCount":3,"zipByteSize":2758},{"version":"2.0.0","createdAt":"2026-05-16T07:56:44.159Z","changelog":"纯规则引擎发布版（移除知识库依赖）","fileCount":5,"zipByteSize":9027},{"version":"1.0.0","createdAt":"2026-05-15T16:07:56.599Z","changelog":"tob-win-loss-review 1.0.0 — 初始发布 - 提供 ToB 销售丢单复盘助手，结合行业、竞品信息输出根因分析、风险信号与改进建议，并标注知识库来源。 - 支持行业/规模/阶段/竞品/关键事件输入，自动调用 ChromaDB 客户项目知识库进行检索。 - 实现多维度模式与阶段风险、关键词、综合推理匹配方法。 - 严格限制编造，结论需有知识库证据或标注“待验证”。 - 设计中文结构化输出，并强化对查询可用性和结果置信度的约束。 - 明确阻断、审核流程和运行环境要求。","fileCount":4,"zipByteSize":14968}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s176t36qq1w6j18d0hyxc24yhx83pa2x:tob-win-loss-review","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":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-william202404-tob-win-loss-review/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-william202404-tob-win-loss-review/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-william202404-tob-win-loss-review/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-william202404-tob-win-loss-review/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-william202404-tob-win-loss-review/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-william202404-tob-win-loss-review/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-13T07:54:59.062Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-william202404-tob-win-loss-review/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-william202404-tob-win-loss-review/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-william202404-tob-win-loss-review/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-william202404-tob-win-loss-review/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":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"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":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-12T00:58:26.141Z","emptyReason":null},"readme":"Skill: Tob Win Loss Review\n\nOwner: william202404\n\nSummary: ToB销售丢单复盘助手。输入行业/规模/阶段/竞品/关键事件，使用原创销售经验规则引擎输出根因分析、风险信号和改进建议。\n\nTags: latest:2.0.2\n\nVersion history:\n\nv2.0.2 | 2026-07-07T16:18:19.828Z | auto\n\n- Added detailed usage documentation in README.md.\n- Introduced scripts/tob_win_loss_review.py file, setting up the main script structure.\n- Minor metadata alignment in SKILL.md (added slug, displayName fields).\n\nv2.0.1 | 2026-07-05T14:25:25.637Z | auto\n\nSummary: Major cleanup for documentation and code, keeping only core docs.\n\n- Removed README.md, main script, and skill card files to streamline the skill package.\n- SKILL.md was simplified: references to “李宁原创”替换为中性表述；源说明和workers格式调整。\n- No user-facing features or logic changed; only documentation and packaging structure updated.\n\nv2.0.0 | 2026-05-16T07:56:44.159Z | user\n\n纯规则引擎发布版（移除知识库依赖）\n\nv1.0.0 | 2026-05-15T16:07:56.599Z | user\n\ntob-win-loss-review 1.0.0 — 初始发布\n\n- 提供 ToB 销售丢单复盘助手，结合行业、竞品信息输出根因分析、风险信号与改进建议，并标注知识库来源。\n- 支持行业/规模/阶段/竞品/关键事件输入，自动调用 ChromaDB 客户项目知识库进行检索。\n- 实现多维度模式与阶段风险、关键词、综合推理匹配方法。\n- 严格限制编造，结论需有知识库证据或标注“待验证”。\n- 设计中文结构化输出，并强化对查询可用性和结果置信度的约束。\n- 明确阻断、审核流程和运行环境要求。\n\nArchive index:\n\nArchive v2.0.2: 5 files, 8996 bytes\n\nFiles: README.md (1449b), scripts/tob_win_loss_review.py (12080b), skill-card.md (1924b), SKILL.md (1939b), _meta.json (138b)\n\nFile v2.0.2:SKILL.md\n\n---\nname: tob-win-loss-review\nslug: tob-win-loss-review\ndisplayName: 丢单复盘助手\nversion: 2.0.0\ndescription: ToB销售丢单复盘助手。输入行业/规模/阶段/竞品/关键事件，使用原创销售经验规则引擎输出根因分析、风险信号和改进建议。\npriority: high\nsource: experience-backed\nworkers: [tech, sales, checker]\ncreated: 2026-05-15\ntags: [tob, sales, win-loss, review, rules]\n---\n\n# tob-win-loss-review — 丢单复盘助手\n\n## 何时使用\n\n当用户需要复盘 ToB 销售丢单原因，并希望基于行业、销售阶段、关键事件快速得到可执行改进建议时使用。\n\n本技能为**纯规则引擎**，规则来自多年 ToB 销售与解决方案实践经验；不读取、不打包任何客户商业资产。\n\n## 使用方式\n\n### 交互模式\n\n```bash\ntob-win-loss-review\n```\n\n### 快速模式\n\n```bash\ntob-win-loss-review --industry 零售 --size 大型 --duration 4个月 --stage 报价谈判 --competitor 略 --event \"客户说我们价格比竞品高30%，虽然我们功能更全但对方预算有限\"\n```\n\n### JSON 调试\n\n```bash\ntob-win-loss-review ... --json\n```\n\n## 实现逻辑\n\n1. 行业规则：识别不同行业的共性风险与价值包装重点\n2. 阶段规则：按报价谈判、POC、方案、合同等阶段判断控制点缺口\n3. 事件规则：从关键事件中触发价格、竞品、决策链、POC等风险模式\n4. 概率排序：保留核心原因 / 辅助原因 / 潜在风险结构\n5. 建议输出：短期动作 / 中期能力 / 长期体系化\n\n## 输出约束\n\n- 根因分析使用「规则依据」说明触发逻辑\n- 风险信号对照基于行业 + 阶段 + 事件交叉匹配\n- 中文输出，结构固定：项目画像 → 根因分析 → 风险信号 → 改进建议\n\n## 注意事项\n\n- 本技能不访问外部数据源，默认可离线运行\n- 规则结论用于复盘和下一步行动设计，不替代真实客户访谈\n\nFile v2.0.2:README.md\n\n# tob-win-loss-review — 丢单复盘助手\n\n> 输入行业/规模/阶段/竞品/关键事件，基于原创 ToB 销售经验规则输出根因分析、风险信号和改进建议。\n\n本技能从 v2.0.0 起改为**纯规则引擎**：不打包任何客户商业资产，默认可离线运行。\n\n## 快速开始\n\n```bash\n# 交互模式\npython3 scripts/tob_win_loss_review.py\n\n# 快速模式\npython3 scripts/tob_win_loss_review.py --industry 零售 --size 大型 \\\n --duration 4个月 --stage 报价谈判 --competitor 略 \\\n --event \"客户说我们价格比竞品高30%\"\n```\n\n## 输出结构\n\n```\n项目画像 → 根因分析(规则依据) → 风险信号 → 改进建议\n```\n\n根因分析中的「规则依据」来自行业 + 阶段 + 事件三因素交叉匹配，例如：\n\n```\n规则依据：行业[零售]+阶段[报价谈判]+事件[价格/预算触发] → 价格竞争力风险\n```\n\n## 技术栈\n\n- Python 3 标准库\n- 纯规则引擎：行业 / 阶段 / 事件三因素经验模型\n- 概率排序：核心原因 / 辅助原因 / 潜在风险\n\n## 安装\n\n```bash\nclawhub install tob-win-loss-review\n# 或\nopenclaw skills install tob-win-loss-review\n```\n\n## 版权\n\n规则经验来自原创 ToB 销售与解决方案实践。\n\n## 链接\n\n- GitHub: https://github.com/tob-skills/tob-skills\n- ClawHub: `clawhub search tob-win-loss-review`\n- SkillHub: `skillhub search tob-win-loss-review`\n\n## License\n\nMIT-0 (No Attribution Required)\n\nFile v2.0.2:_meta.json\n\n{\n \"ownerId\": \"kn715matapvxk8f52kcatykw1h82b8z3\",\n \"slug\": \"tob-win-loss-review\",\n \"version\": \"2.0.2\",\n \"publishedAt\": 1783441099828\n}\n\nFile v2.0.2:skill-card.md\n\n## Description:\n\nToB销售丢单复盘助手。输入行业/规模/阶段/竞品/关键事件，使用原创销售经验规则引擎输出根因分析、风险信号和改进建议。\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[william202404](https://clawhub.ai/user/william202404)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and sales teams use this skill to review ToB sales losses from deal context such as industry, account size, sales stage, competitor, and key events. It produces Chinese-language root-cause analysis, risk signals, and practical next-step recommendations.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The generated win/loss analysis may be misleading if treated as a definitive customer truth.\n\nMitigation: Use the output as advisory input and validate conclusions against customer interviews and deal evidence.\n\nRisk: User-entered deal notes may include sensitive customer details.\n\nMitigation: Avoid entering sensitive customer details unless local processing is acceptable; redact or generalize customer identifiers before use.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/william202404/skills/tob-win-loss-review)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, JSON, Guidance]\n\n**Output Format:** [Chinese Markdown report, with optional JSON debug output]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Offline rule-engine output; advisory sales review, not a substitute for customer interviews.]\n\n## Skill Version(s):\n\n2.0.2 (source: server release metadata; artifact frontmatter says 2.0.0)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v2.0.1: 3 files, 2758 bytes\n\nFiles: skill-card.md (1938b), SKILL.md (1881b), _meta.json (138b)\n\nFile v2.0.1:SKILL.md\n\n---\nname: tob-win-loss-review\nversion: 2.0.0\ndescription: ToB销售丢单复盘助手。输入行业/规模/阶段/竞品/关键事件，使用原创销售经验规则引擎输出根因分析、风险信号和改进建议。\npriority: high\nsource: experience-backed\nworkers: [tech, sales, checker]\ncreated: 2026-05-15\ntags: [tob, sales, win-loss, review, rules]\n---\n\n# tob-win-loss-review — 丢单复盘助手\n\n## 何时使用\n\n当用户需要复盘 ToB 销售丢单原因，并希望基于行业、销售阶段、关键事件快速得到可执行改进建议时使用。\n\n本技能为**纯规则引擎**，规则来自多年 ToB 销售与解决方案实践经验；不读取、不打包任何客户商业资产。\n\n## 使用方式\n\n### 交互模式\n\n```bash\ntob-win-loss-review\n```\n\n### 快速模式\n\n```bash\ntob-win-loss-review --industry 零售 --size 大型 --duration 4个月 --stage 报价谈判 --competitor 略 --event \"客户说我们价格比竞品高30%，虽然我们功能更全但对方预算有限\"\n```\n\n### JSON 调试\n\n```bash\ntob-win-loss-review ... --json\n```\n\n## 实现逻辑\n\n1. 行业规则：识别不同行业的共性风险与价值包装重点\n2. 阶段规则：按报价谈判、POC、方案、合同等阶段判断控制点缺口\n3. 事件规则：从关键事件中触发价格、竞品、决策链、POC等风险模式\n4. 概率排序：保留核心原因 / 辅助原因 / 潜在风险结构\n5. 建议输出：短期动作 / 中期能力 / 长期体系化\n\n## 输出约束\n\n- 根因分析使用「规则依据」说明触发逻辑\n- 风险信号对照基于行业 + 阶段 + 事件交叉匹配\n- 中文输出，结构固定：项目画像 → 根因分析 → 风险信号 → 改进建议\n\n## 注意事项\n\n- 本技能不访问外部数据源，默认可离线运行\n- 规则结论用于复盘和下一步行动设计，不替代真实客户访谈\n\nFile v2.0.1:_meta.json\n\n{\n \"ownerId\": \"kn715matapvxk8f52kcatykw1h82b8z3\",\n \"slug\": \"tob-win-loss-review\",\n \"version\": \"2.0.1\",\n \"publishedAt\": 1783261525637\n}\n\nFile v2.0.1:skill-card.md\n\n## Description:
\nToB销售丢单复盘助手。输入行业/规模/阶段/竞品/关键事件，使用原创销售经验规则引擎输出根因分析、风险信号和改进建议。
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[william202404](https://clawhub.ai/user/william202404)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nSales, solution, and go-to-market teams use this skill to review lost ToB sales opportunities from industry, deal stage, competitor context, and key events. It produces root-cause analysis, risk signals, and short-, medium-, and long-term improvement guidance.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Review before execution as proposals could introduce incorrect or misleading guidance into skills.
\nMitigation: Review and scan skill before deployment.
\n\n## Reference(s):
\n- [ClawHub Skill Page](https://clawhub.ai/william202404/skills/tob-win-loss-review)
\n- [Server-Resolved GitHub Source](https://github.com/william202404/tob-skills/tree/main/tob-win-loss-review)
\n\n\n## Skill Output:
\n**Output Type(s):** [Analysis, Guidance, JSON]
\n**Output Format:** [Structured Chinese Markdown with optional JSON debug output]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Fixed sections: project profile, root-cause analysis, risk signals, and improvement recommendations; rule-based conclusions should not replace customer interviews.]
\n\n## Skill Version(s):
\n2.0.1 (source: ClawHub release metadata; artifact frontmatter reports 2.0.0)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nArchive v2.0.0: 5 files, 9027 bytes\n\nFiles: README.md (1464b), scripts/tob_win_loss_review.py (12077b), skill-card.md (2322b), SKILL.md (1897b), _meta.json (138b)\n\nFile v2.0.0:SKILL.md\n\n---\nname: tob-win-loss-review\nversion: 2.0.0\ndescription: ToB销售丢单复盘助手。输入行业/规模/阶段/竞品/关键事件，使用李宁原创销售经验规则引擎输出根因分析、风险信号和改进建议。\npriority: high\nsource: lining-experience-rules\nworkers: Tech, Sales, Checker\ncreated: 2026-05-15\ntags: [tob, sales, win-loss, review, rules]\n---\n\n# tob-win-loss-review — 丢单复盘助手\n\n## 何时使用\n\n当用户需要复盘 ToB 销售丢单原因，并希望基于行业、销售阶段、关键事件快速得到可执行改进建议时使用。\n\n本技能为**纯规则引擎**，规则来自李宁多年 ToB 销售与解决方案实践经验；不读取、不打包任何客户商业资产。\n\n## 使用方式\n\n### 交互模式\n\n```bash\ntob-win-loss-review\n```\n\n### 快速模式\n\n```bash\ntob-win-loss-review --industry 零售 --size 大型 --duration 4个月 --stage 报价谈判 --competitor 略 --event \"客户说我们价格比竞品高30%，虽然我们功能更全但对方预算有限\"\n```\n\n### JSON 调试\n\n```bash\ntob-win-loss-review ... --json\n```\n\n## 实现逻辑\n\n1. 行业规则：识别不同行业的共性风险与价值包装重点\n2. 阶段规则：按报价谈判、POC、方案、合同等阶段判断控制点缺口\n3. 事件规则：从关键事件中触发价格、竞品、决策链、POC等风险模式\n4. 概率排序：保留核心原因 / 辅助原因 / 潜在风险结构\n5. 建议输出：短期动作 / 中期能力 / 长期体系化\n\n## 输出约束\n\n- 根因分析使用「规则依据」说明触发逻辑\n- 风险信号对照基于行业 + 阶段 + 事件交叉匹配\n- 中文输出，结构固定：项目画像 → 根因分析 → 风险信号 → 改进建议\n\n## 注意事项\n\n- 本技能不访问外部数据源，默认可离线运行\n- 规则结论用于复盘和下一步行动设计，不替代真实客户访谈\n\nFile v2.0.0:README.md\n\n# tob-win-loss-review — 丢单复盘助手\n\n> 输入行业/规模/阶段/竞品/关键事件，基于李宁原创 ToB 销售经验规则输出根因分析、风险信号和改进建议。\n\n本技能从 v2.0.0 起改为**纯规则引擎**：不打包任何客户商业资产，默认可离线运行。\n\n## 快速开始\n\n```bash\n# 交互模式\npython3 scripts/tob_win_loss_review.py\n\n# 快速模式\npython3 scripts/tob_win_loss_review.py --industry 零售 --size 大型 \\\n --duration 4个月 --stage 报价谈判 --competitor 略 \\\n --event \"客户说我们价格比竞品高30%\"\n```\n\n## 输出结构\n\n```\n项目画像 → 根因分析(规则依据) → 风险信号 → 改进建议\n```\n\n根因分析中的「规则依据」来自行业 + 阶段 + 事件三因素交叉匹配，例如：\n\n```\n规则依据：行业[零售]+阶段[报价谈判]+事件[价格/预算触发] → 价格竞争力风险\n```\n\n## 技术栈\n\n- Python 3 标准库\n- 纯规则引擎：行业 / 阶段 / 事件三因素经验模型\n- 概率排序：核心原因 / 辅助原因 / 潜在风险\n\n## 安装\n\n```bash\nclawhub install tob-win-loss-review\n# 或\nopenclaw skills install tob-win-loss-review\n```\n\n## 版权\n\n规则经验来自李宁原创 ToB 销售与解决方案实践。\n\n## 链接\n\n- GitHub: https://github.com/william202404/tob-skills\n- ClawHub: `clawhub search tob-win-loss-review`\n- SkillHub: `skillhub search tob-win-loss-review`\n\n## License\n\nMIT-0 (No Attribution Required)\n\nFile v2.0.0:_meta.json\n\n{\n \"ownerId\": \"kn715matapvxk8f52kcatykw1h82b8z3\",\n \"slug\": \"tob-win-loss-review\",\n \"version\": \"2.0.0\",\n \"publishedAt\": 1778918204159\n}\n\nFile v2.0.0:skill-card.md\n\n## Description:
\nHelps review lost ToB sales opportunities by using a local rules engine to turn industry, account size, sales stage, competitor, and key-event inputs into root-cause analysis, risk signals, and improvement guidance.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[william202404](https://clawhub.ai/user/william202404)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nSales, solution, and revenue teams use this skill to perform structured win/loss reviews after a lost ToB opportunity. It produces a fixed Chinese report with project profile, ranked root causes, risk signals, and short-, medium-, and long-term improvement recommendations.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Users may enter sensitive customer or deal details while preparing a win/loss review.
\nMitigation: Provide only the deal context needed for review, avoid real customer identifiers where possible, and review generated reports before sharing them outside the sales team.
\nRisk: Rules-based findings can be incomplete or misleading when the input omits buyer feedback, decision-chain context, or competitor details.
\nMitigation: Treat the report as a review aid, not a substitute for customer interviews or documented post-loss feedback.
\n\n\n## Reference(s):
\n- [README](README.md)
\n- [Skill definition](SKILL.md)
\n- [ClawHub skill page](https://clawhub.ai/william202404/tob-win-loss-review)
\n\n\n## Skill Output:
\n**Output Type(s):** [text, markdown, json, guidance]
\n**Output Format:** [Chinese Markdown-style report text, with optional formatted JSON when invoked with --json]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Offline rules-based output; no network access, credential use, file modification, or persistence shown in the security evidence.]
\n\n## Skill Version(s):
\n2.0.0 (source: SKILL.md frontmatter and server release metadata)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nArchive v1.0.0: 4 files, 14968 bytes\n\nFiles: scripts/tob_win_loss_review.py (14262b), scripts/unified_knowledge_search.py (21227b), SKILL.md (2108b), _meta.json (138b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: tob-win-loss-review\ndescription: ToB销售丢单复盘助手。输入行业/规模/阶段/竞品/关键事件，基于ChromaDB客户项目知识库输出带来源的根因分析、风险信号和改进建议。\npriority: high\nsource: tech-built\nworkers: Tech, Sales, Checker\ncreated: 2026-05-15\n---\n\n# tob-win-loss-review — 丢单复盘助手\n\n## 何时使用\n\n当用户需要复盘 ToB 销售丢单原因，尤其是需要结合李宁客户项目知识库、行业方案包、竞品/售前资料给出改进建议时使用。\n\n## 使用方式\n\n### 交互模式\n\n```bash\ntob-win-loss-review\n```\n\n### 快速模式\n\n```bash\ntob-win-loss-review --industry 零售 --size 大型 --duration 4个月 --stage 报价谈判 --competitor 略 --event \"客户说我们价格比竞品高30%，虽然我们功能更全但对方预算有限\"\n```\n\n### JSON 调试\n\n```bash\ntob-win-loss-review ... --json\n```\n\n## 实现逻辑\n\n1. 行业模式匹配：行业 + 常见痛点 + 成功模式\n2. 竞品模式匹配：竞品 + 竞品优势/劣势/打法\n3. 阶段风险匹配：丢单阶段 + 合同/里程碑/变更/问题记录\n4. 关键词匹配：从关键事件抽取关键词后检索相似描述\n5. 综合推理：证据不足时降权，并明确标注「待验证」和补充问题\n\n底层使用 skill 内置的 `scripts/unified_knowledge_search.py`，通过 ChromaDB `PersistentClient + get()+NumPy cosine` 安全检索路径，避免直接使用 `collection.query()` 触发已知本地索引风险。为避免 5 路检索同质化，presales 扩展词已收窄，并在报告中统计独立来源数。\n\n## 输出约束\n\n- 每条根因必须标注知识库来源；没有知识库支撑必须标「待验证」。\n- 不编造客户、数据、概率；概率为基于检索证据数量/相似度的估算置信度。\n- 中文输出，结构固定：项目画像 → 根因分析 → 风险信号 → 改进建议。\n\n## 注意事项\n\n- 如果 Chroma/Ollama 不可用，输出阻断原因，不做无来源复盘。\n- 查询结果低于阈值时，不强行给确定结论。\n- 提交审查前至少跑 TC1。\n\nFile v1.0.0:_meta.json\n\n{\n \"ownerId\": \"kn715matapvxk8f52kcatykw1h82b8z3\",\n \"slug\": \"tob-win-loss-review\",\n \"version\": \"1.0.0\",\n \"publishedAt\": 1778861276599\n}","readmeExcerpt":"Skill: Tob Win Loss Review Owner: william202404 Summary: ToB销售丢单复盘助手。输入行业/规模/阶段/竞品/关键事件，使用原创销售经验规则引擎输出根因分析、风险信号和改进建议。 Tags: latest:2.0.2 Version history: v2.0.2 | 2026-07-07T16:18:19.828Z | auto - Added detailed usage documentation in README.md. - Introduced scripts/tob_win_loss_review.py file, setting up the main script structure. - Minor metadata alignment in SKILL.md (added slug, displayName fields). v2.0.1 | 2026","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"tob-win-loss-review"},{"language":"bash","snippet":"tob-win-loss-review --industry 零售 --size 大型 --duration 4个月 --stage 报价谈判 --competitor 略 --event \"客户说我们价格比竞品高30%，虽然我们功能更全但对方预算有限\""},{"language":"bash","snippet":"tob-win-loss-review ... --json"},{"language":"bash","snippet":"# 交互模式\npython3 scripts/tob_win_loss_review.py\n\n# 快速模式\npython3 scripts/tob_win_loss_review.py --industry 零售 --size 大型 \\\n --duration 4个月 --stage 报价谈判 --competitor 略 \\\n --event \"客户说我们价格比竞品高30%\""},{"language":"text","snippet":"项目画像 → 根因分析(规则依据) → 风险信号 → 改进建议"},{"language":"text","snippet":"规则依据：行业[零售]+阶段[报价谈判]+事件[价格/预算触发] → 价格竞争力风险"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: tob-win-loss-review\nslug: tob-win-loss-review\ndisplayName: 丢单复盘助手\nversion: 2.0.0\ndescription: ToB销售丢单复盘助手。输入行业/规模/阶段/竞品/关键事件，使用原创销售经验规则引擎输出根因分析、风险信号和改进建议。\npriority: high\nsource: experience-backed\nworkers: [tech, sales, checker]\ncreated: 2026-05-15\ntags: [tob, sales, win-loss, review, rules]\n---\n\n# tob-win-loss-review — 丢单复盘助手\n\n## 何时使用\n\n当用户需要复盘 ToB 销售丢单原因，并希望基于行业、销售阶段、关键事件快速得到可执行改进建议时使用。\n\n本技能为**纯规则引擎**，规则来自多年 ToB 销售与解决方案实践经验；不读取、不打包任何客户商业资产。\n\n## 使用方式\n\n### 交互模式\n\n```bash\ntob-win-loss-review\n```\n\n### 快速模式\n\n```bash\ntob-win-loss-review --industry 零售 --size 大型 --duration 4个月 --stage 报价谈判 --competitor 略 --event \"客户说我们价格比竞品高30%，虽然我们功能更全但对方预算有限\"\n```\n\n### JSON 调试\n\n```bash\ntob-win-loss-review ... --json\n```\n\n## 实现逻辑\n\n1. 行业规则：识别不同行业的共性风险与价值包装重点\n2. 阶段规则：按报价谈判、POC、方案、合同等阶段判断控制点缺口\n3. 事件规则：从关键事件中触发价格、竞品、决策链、POC等风险模式\n4. 概率排序：保留核心原因 / 辅助原因 / 潜在风险结构\n5. 建议输出：短期动作 / 中期能力 / 长期体系化\n\n## 输出约束\n\n- 根因分析使用「规则依据」说明触发逻辑\n- 风险信号对照基于行业 + 阶段 + 事件交叉匹配\n- 中文输出，结构固定：项目画像 → 根因分析 → 风险信号 → 改进建议\n\n## 注意事项\n\n- 本技能不访问外部数据源，默认可离线运行\n- 规则结论用于复盘和下一步行动设计，不替代真实客户访谈"},{"path":"README.md","content":"# tob-win-loss-review — 丢单复盘助手\n\n> 输入行业/规模/阶段/竞品/关键事件，基于原创 ToB 销售经验规则输出根因分析、风险信号和改进建议。\n\n本技能从 v2.0.0 起改为**纯规则引擎**：不打包任何客户商业资产，默认可离线运行。\n\n## 快速开始\n\n```bash\n# 交互模式\npython3 scripts/tob_win_loss_review.py\n\n# 快速模式\npython3 scripts/tob_win_loss_review.py --industry 零售 --size 大型 \\\n --duration 4个月 --stage 报价谈判 --competitor 略 \\\n --event \"客户说我们价格比竞品高30%\"\n```\n\n## 输出结构\n\n```\n项目画像 → 根因分析(规则依据) → 风险信号 → 改进建议\n```\n\n根因分析中的「规则依据」来自行业 + 阶段 + 事件三因素交叉匹配，例如：\n\n```\n规则依据：行业[零售]+阶段[报价谈判]+事件[价格/预算触发] → 价格竞争力风险\n```\n\n## 技术栈\n\n- Python 3 标准库\n- 纯规则引擎：行业 / 阶段 / 事件三因素经验模型\n- 概率排序：核心原因 / 辅助原因 / 潜在风险\n\n## 安装\n\n```bash\nclawhub install tob-win-loss-review\n# 或\nopenclaw skills install tob-win-loss-review\n```\n\n## 版权\n\n规则经验来自原创 ToB 销售与解决方案实践。\n\n## 链接\n\n- GitHub: https://github.com/tob-skills/tob-skills\n- ClawHub: `clawhub search tob-win-loss-review`\n- SkillHub: `skillhub search tob-win-loss-review`\n\n## License\n\nMIT-0 (No Attribution Required)"},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn715matapvxk8f52kcatykw1h82b8z3\",\n \"slug\": \"tob-win-loss-review\",\n \"version\": \"2.0.2\",\n \"publishedAt\": 1783441099828\n}"},{"path":"skill-card.md","content":"## Description:\n\nToB销售丢单复盘助手。输入行业/规模/阶段/竞品/关键事件，使用原创销售经验规则引擎输出根因分析、风险信号和改进建议。\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[william202404](https://clawhub.ai/user/william202404)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and sales teams use this skill to review ToB sales losses from deal context such as industry, account size, sales stage, competitor, and key events. It produces Chinese-language root-cause analysis, risk signals, and practical next-step recommendations.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The generated win/loss analysis may be misleading if treated as a definitive customer truth.\n\nMitigation: Use the output as advisory input and validate conclusions against customer interviews and deal evidence.\n\nRisk: User-entered deal notes may include sensitive customer details.\n\nMitigation: Avoid entering sensitive customer details unless local processing is acceptable; redact or generalize customer identifiers before use.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/william202404/skills/tob-win-loss-review)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, JSON, Guidance]\n\n**Output Format:** [Chinese Markdown report, with optional JSON debug output]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Offline rule-engine output; advisory sales review, not a substitute for customer interviews.]\n\n## Skill Version(s):\n\n2.0.2 (source: server release metadata; artifact frontmatter says 2.0.0)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"ToB销售丢单复盘助手。输入行业/规模/阶段/竞品/关键事件，使用原创销售经验规则引擎输出根因分析、风险信号和改进建议。 Skill: Tob Win Loss Review Owner: william202404 Summary: ToB销售丢单复盘助手。输入行业/规模/阶段/竞品/关键事件，使用原创销售经验规则引擎输出根因分析、风险信号和改进建议。 Tags: latest:2.0.2 Version history: v2.0.2 | 2026-07-07T16:18:19.828Z | auto - Added detailed usage documentation in README.md. - Introduced scripts/tob_win_loss_review.py file, setting up the main script structure. - Minor metadata alignment in SKILL.md (added slug, displayName fields). v2.0.1 | 2026","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":765,"uniquenessScore":58,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-12T00:58:26.141Z","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":"2026-10-12T00:58:26.141Z","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":"2026-10-13T07:54:59.062Z","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/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}