← 返回 Skills 市场
ykitty

review-writer

作者 strive · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ✓ 安全检测通过
109
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install review-writer
功能描述
Data-driven writing and polishing for professional workplace documents. Use when the user asks to write or refine: (1) 述职/复盘/年终总结, (2) 简历/项目经历/STAR 改写, (3) 周...
使用说明 (SKILL.md)

Review Writer

Overview

把零散要点快速变成可交付的初稿,再按反馈迭代到“数据驱动、结构清晰、可量化、可复用”的最终版本。根据用户输入语言自动用中文或英文输出(混合输入则先给中文,再给英文或相反,以用户指令为准)。

Default workflow(先初稿,再迭代)

0) Minimal intake(不阻塞出稿)

除非用户明确要求“先问清楚再写”,否则默认先出 70% 初稿。只在缺少关键信息会导致方向错误时,追加不超过 5 个问题(优先选项题/填空题)。

优先询问的最小信息集(按需挑选):

  • 文档类型与读者:述职/简历/周报/年终/OKR/PRD;读者是直属/HR/跨部门/高层
  • 时间范围:本周/本月/季度/全年;是否要对标目标/OKR
  • “数据口径”:指标定义、统计周期、分母分子、样本量/覆盖率
  • 可公开边界:可否写金额/客户名/内部系统名(不确定时做脱敏占位)
  • 口吻:默认数据驱动;是否需要更谦逊/更强势/更叙事

1) Draft 1(结构先行)

把用户要点归类为:背景/目标/动作/产出/结果/影响/复盘/下一步。优先用小标题 + 列表,避免长段落堆砌。

默认输出顺序:

  1. 一页摘要(3–6 条 bullet,强结果)
  2. 结构化正文(按文档类型套模板)
  3. 指标/成果表(如适用)
  4. 风险与复盘 + 下一步(闭环)

2) Iterate(按反馈改到可交付)

每轮迭代只做三类改动(保持可控):

  • 结构:顺序、层级、是否需要摘要/表格/附录
  • 证据:补齐数字、对比基线、口径解释、因果链
  • 表达:更短、更具体、更面向读者;把“做了什么”改成“带来什么结果”

Templates(按需选用)

述职 / 复盘(季度/半年/年度)

推荐结构(可按情况增删):

  • 一页摘要:关键结果(含数字)+ 关键能力体现 + 最大复盘点 + 下阶段重点
  • 目标与范围:本周期目标/职责范围/关键约束
  • 关键项目(3–6 个):每个用“目标-动作-结果-影响-复盘-下一步”
  • 指标与业务影响:核心指标、基线、提升幅度、样本量与口径
  • 问题与复盘:根因、权衡、避免再犯的机制
  • 下阶段计划:目标、里程碑、依赖与风险

周报 / 月报

推荐结构:

  • 本周期产出(Top 3–5):每条尽量量化(完成率/耗时/影响面/节省成本)
  • 进行中(Top 3):当前进度、阻塞点、预计完成时间
  • 风险与依赖:需要谁支持、何时、如果不支持的影响
  • 下周期计划:目标、动作、验收标准

简历 / 项目经历(STAR / CAR)

单条经历优先格式(中英任选):

  • Context/Situation:一句话背景(规模/约束)
  • Task/Goal:你的目标(指标化)
  • Action:你的关键动作(3–5 点,突出 ownership 与方法)
  • Result/Impact:结果(数字 + 对比基线 + 业务影响)

写作规则:

  • 动词开头(Designed/Owned/Delivered/Improved…)
  • 结果优先,技术/过程其次
  • 重要数字用同一口径(例如:从 X 提升到 Y,提升 ( (Y-X)/X ))

OKR

输出要求:

  • O(Objective):面向结果、可感知、不过度技术化
  • KR(Key Results):量化、可验收、定义口径(时间范围/分母分子/数据源)
  • Initiatives:做什么来保证 KR(可选)

PRD / 方案文档(轻量但完整)

推荐结构:

  • 背景 & 目标(含非目标)
  • 用户/场景/问题定义
  • 方案概述(1 页)
  • 详细设计(流程/交互/数据/权限)
  • 指标口径(北极星指标 + 过程指标)
  • 风险 & 备选方案
  • 里程碑 & 资源评估
  • 验收标准(必须可测试/可验证)

Data-driven writing checklist(默认开启)

在输出前做快速自检并按需补齐:

  • 对比基线:提升/下降相对谁(上周/上月/去年同期/对照组)
  • 口径:统计周期、数据源、样本量;避免“显著/大幅”但没数字
  • 影响链:动作 → 指标变化 → 业务影响(收入/成本/效率/体验/风险)
  • 可归因:你的贡献边界是什么(owner/主导/参与/协作)
  • 可复用:抽象方法论/机制(流程、看板、自动化、SOP)

Bilingual behavior(CN/EN auto)

语言策略:

  • 跟随用户最近一次明确指令;否则跟随用户输入的主要语言
  • 如果用户说“给英文版/中英双语/发给海外同事”,输出对应版本
  • 术语处理:首次出现给中英对照(如关键指标名、系统名);后续统一用一种语言
安全使用建议
This skill appears coherent and safe from a permissions perspective because it asks for no installs or credentials. Before using it: (1) avoid pasting sensitive PII or confidential numbers into prompts—when needed, redact or use placeholders; (2) if you want to avoid any chance of fabricated metrics, tell the agent to "先问清楚再写" (ask clarifying questions before drafting); (3) review any autogenerated numbers/claims and replace placeholders with real data; and (4) explicitly request the language/format desired (CN/EN/bilingual) to avoid unintended output. If you need stronger privacy guarantees, do not paste client names, financial amounts, or internal IDs into the editor.
功能分析
Type: OpenClaw Skill Name: review-writer Version: 1.0.1 The 'review-writer' skill bundle consists solely of Markdown instructions (SKILL.md) and metadata, providing templates and workflows for generating professional documents like resumes, OKRs, and reports. It contains no executable code, network requests, or instructions that attempt to exfiltrate data or bypass security controls; it even includes explicit guidance on data anonymization for sensitive information.
能力评估
Purpose & Capability
Name, description, and templates all describe workplace document drafting (述职、简历、周报、OKR、PRD etc.). The skill declares no binaries, env vars, or config paths—this is proportionate and expected for a writing helper.
Instruction Scope
SKILL.md provides detailed, bounded runtime instructions (produce a 70% first draft by default, ask up to ~5 targeted questions when needed, use specific templates and a data-driven checklist). It does not instruct reading system files, environment variables, or sending data to external endpoints. Minor functional risk: the default behavior of producing a draft even when some metrics are missing can lead to placeholders or fabricated numbers unless the user requires clarifying questions first—this is a correctness/privacy concern rather than a security incoherence.
Install Mechanism
Instruction-only skill with no install spec and no code files. Nothing is written to disk; this is the lowest-risk install model.
Credentials
The skill requests no environment variables, credentials, or config paths. There is no disproportionate access requested for its stated purpose.
Persistence & Privilege
always is false and model invocation is allowed (platform default). The skill does not request permanent presence, nor does it instruct modifying other skills or system-wide settings.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install review-writer
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /review-writer 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.1
- No user-facing changes. - No file or documentation updates in this version. - Version bump only; functionality and features remain unchanged.
v1.0.0
- Initial release of review-writer skill for data-driven writing and polishing of professional workplace documents. - Supports structured drafting and iterative refinement for reports, resumes, OKRs, PRDs, and more. - Default workflow produces a rapid first draft with minimal questions; iterates based on feedback focusing on structure, evidence, and clarity. - Automatically outputs in Chinese or English, supports bilingual drafts, and aligns tone and document structure to user needs. - Includes best-practice templates for 述职/复盘, 周报/月报, 简历/STAR, OKR, and PRD/方案文档. - Adds built-in checklists for data-driven writing, quantifiable results, and bilingual strategy.
元数据
Slug review-writer
版本 1.0.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

review-writer 是什么?

Data-driven writing and polishing for professional workplace documents. Use when the user asks to write or refine: (1) 述职/复盘/年终总结, (2) 简历/项目经历/STAR 改写, (3) 周... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 109 次。

如何安装 review-writer?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install review-writer」即可一键安装,无需额外配置。

review-writer 是免费的吗?

是的,review-writer 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

review-writer 支持哪些平台?

review-writer 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 review-writer?

由 strive(@ykitty)开发并维护,当前版本 v1.0.1。

💬 留言讨论