Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Performance Review Builder

ASecurity

当绩效季启动、需要做自评/经理评语/校准(calibration)准备,或要把模糊反馈改写成具体行为示例时使用;做绩效评估结构化,产出自评模板、经理评估模板、校准准备文档(评分分布+晋升案例);不适用于实时绩效改进计划(PIP)起草、薪酬数值核算或法律合规裁决。触发词:绩效评估、自评、校准、晋升评定

3 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsperformance

Works with

cursorcli

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add findscripter/everything-skills --skill performance-review-builder --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Performance Review Builder?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Performance Review Builder
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/findscripter-performance-review-builder/badge)](https://www.skillsdirectory.com/skills/findscripter-performance-review-builder)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: performance-review-builder
title: 绩效评估结构化
description: 当绩效季启动、需要做自评/经理评语/校准(calibration)准备,或要把模糊反馈改写成具体行为示例时使用;做绩效评估结构化,产出自评模板、经理评估模板、校准准备文档(评分分布+晋升案例);不适用于实时绩效改进计划(PIP)起草、薪酬数值核算或法律合规裁决。触发词:绩效评估、自评、校准、晋升评定
domain: 商业/copy
triggers: [绩效评估, 绩效review, 自评, self-assessment, 经理评估, manager review, 校准准备, calibration, 评分分布, 晋升案例, 绩效反馈, performance review]
tags: [商业, misc, 人力资源, 绩效管理, 绩效评估, 校准, 晋升评定, 反馈, 模板]
level: 进阶
status: stable
agents: [claude-code, codex, cursor, gemini-cli]
tools: [Markdown 编辑器, HRIS(可选), 项目管理工具(可选)]
requires: []
related: [compensation-analysis, interview-plan-builder, new-hire-onboarding-plan, hr-partner-pro]
combines_with: [compensation-analysis, new-hire-onboarding-plan]
license: Apache-2.0
source: anthropics/knowledge-work-plugins
source_license: Apache-2.0
---
## 何时使用

绩效季(review season)启动、需要把绩效评估流程结构化时使用。三种典型模式:

- **自评(self-assessment)**——员工总结本周期成就、目标达成、成长与挑战。
- **经理评估(manager review)**——为某位下属写一份结构化评语:评级、优势、发展项、影响、发展计划与薪酬建议。
- **校准准备(calibration)**——汇报前整理团队评分分布、晋升候选与薪酬动作,准备好对抗式讨论点。

横向能力:把「干得不错」这类模糊反馈改写成**具体行为示例**(带情境—贡献—影响)。

**不该用的边界:**
- 不用于起草绩效改进计划(PIP)/解雇文书——那是合规与风险流程,口径不同。
- 不做薪酬数值核算/调薪幅度计算——本技能只给「方向性建议+理由」,具体数额交给薪酬体系。
- 不替代劳动法/合规裁决——涉及法律风险时转人力与法务。
- 缺数据时用占位符(如 `[待补充: Q3 目标达成率]`),绝不臆造员工业绩数字。

## 步骤

1. **定模式**:未指定时先问对方要哪种——`self-assessment` / `manager [员工]` / `calibration`。
2. **拉证据**(若有连接器):HRIS 取历史评级与目标数据、预填员工角色信息;项目管理工具取本周期完成的工作与里程碑,作为评语佐证。
3. **套对应模板**(见「示例」),逐字段填真实数据,空缺处用显式占位符。
4. **行为化反馈**:每条优势/发展项都落到「具体行为 + 可衡量影响 + 可执行动作」,删掉性格评判与空泛形容。
5. **过四条质量检查**(见「注意事项」)后定稿。

## 指令

源调用约定(参数化):

```
/performance-review self-assessment       # 生成自评模板
/performance-review manager [员工]         # 为指定下属生成经理评估模板
/performance-review calibration            # 生成校准准备文档
```

**连接器增强:**
- **HRIS 已连接** → 拉取历史评语与目标跟踪、预填员工当前角色与基本信息。
- **项目管理工具已连接** → 拉取本周期完成工作,引用具体工单/项目里程碑作为评语证据。

## 示例

**自评模板(核心字段):**

```markdown
## 自评:[评估周期]

### 关键成就
1. **[成就]**
   - 情境(Situation):[背景]
   - 贡献(Contribution):[你做了什么]
   - 影响(Impact):[可衡量的结果]

### 目标回顾
| 目标 | 状态(达成/超额/未达成) | 证据 |
|------|--------|------|

### 成长领域 / 挑战 / 下周期目标 / 对经理的反馈
[逐项填写,目标须具体可衡量]
```

**经理评估模板(核心字段):**

```markdown
## 绩效评估:[员工姓名]
**周期:**[起止] | **经理:**[你的姓名]

### 总体评级:[超出预期 / 符合预期 / 低于预期]
### 绩效摘要:[2-3 句总评]
### 关键优势 / 待发展项
- [优势 + 具体示例]
- [发展项 + 具体可执行的指导]

### 目标达成 / 影响与贡献
| 目标 | 评级 | 具体观察 |

### 发展计划
| 技能 | 当前水平 | 目标水平 | 行动 |

### 薪酬建议
[晋升 / 股权刷新 / 调整 / 维持 —— 附理由]
```

**校准准备文档(核心字段):**

```markdown
## 校准准备:[评估周期]
### 团队总览:员工 | 角色 | 级别 | 司龄 | 拟定评级 | 关键背景
### 评分分布(对照公司目标)
| 评级 | 人数 | 占比 | 公司目标 |
| 超出预期 | X | X% | ~15-20% |
| 符合预期 | X | X% | ~60-70% |
| 低于预期 | X | X% | ~10-15% |

### 校准讨论点:[临界、首次该级评估、近期换岗等需讨论的人]
### 晋升候选:员工 | 现级别 | 拟晋升级别 | 下一级表现证据
### 薪酬动作:员工 | 动作(晋升/股权刷新/市场调整/挽留)| 理由
### 经理备注:[校准组应知的团队/组织/项目变动背景]
```

## 注意事项

定稿前过这四条(源 Tips):

1. **要具体**——「干得好」不是反馈。「你通过上线新 CI 流水线把部署时间降了 40%」才是。
2. **正向与建设性并重**——两者都不可缺,且都不该让对方在评估时才第一次听到(no surprises)。
3. **对事不对人**——说「你的文档一直不完整」而非「你做事马虎」;评行为,不评性格。
4. **发展项要可执行**——「提升沟通」太空泛;「在下次全员会上做一次分享」才可落地。

补充:评分分布须贴近公司目标区间,强行压钟形曲线会失真;坏评级别在评估当场首次揭晓,提前 1:1 沟通。

## 互见

- related:`board-meeting-prep`、`cfo-financial-advisor` —— 高管沟通/薪酬上下文;`data-storyteller` —— 把绩效证据组织成可信叙事。
- combines_with:`data-storyteller` —— 校准文档与晋升案例的故事化表达。
- 同源 anthropics/knowledge-work-plugins 的 human-resources 插件下其余人力资源类技能。

---

采编自 anthropics/knowledge-work-plugins(Apache-2.0 许可证)。

Attribution

findscripterfindscripter
View sourceSee grades on GitHubMore from findscripter →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →