performance-management – skill Lập trình cho agent AI
Sổ đánh giá hiệu suất: loại đánh giá, kỳ đánh giá, nhân viên và người đánh giá, điểm KPI, OKR và hành vi, xếp loại tổng thể, cờ PIP và thăng chức, kế hoạch phát triển. Dùng cho đánh giá hiệu suất.
Cài skill performance-management bằng một lệnh
Chọn công cụ bạn đang dùng, copy lệnh và dán vào terminal. Skill sẽ nằm trong thư mục skills của công cụ đó và sẵn sàng dùng ở phiên làm việc tiếp theo.
Claude Code
mkdir -p ~/.claude/skills && curl -fsSL https://skill.dn1nguoi.com/z/performance-management-bfeca.tgz | tar xz -C ~/.claude/skills
Gọi trong Claude Code: /performance-management – rồi mô tả công việc bạn muốn làm.
Codex
mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/performance-management-bfeca.tgz | tar xz -C ~/.codex/skills
Gọi trong Codex: $performance-management – rồi mô tả công việc bạn muốn làm.
Hermes Agent
mkdir -p ~/.hermes/skills && curl -fsSL https://skill.dn1nguoi.com/z/performance-management-bfeca.tgz | tar xz -C ~/.hermes/skills
Gọi trong Hermes Agent: /performance-management – rồi mô tả công việc bạn muốn làm.
DeepSeek
mkdir -p ~/.deepcode/skills && curl -fsSL https://skill.dn1nguoi.com/z/performance-management-bfeca.tgz | tar xz -C ~/.deepcode/skills
Gọi trong DeepSeek: /performance-management – rồi mô tả công việc bạn muốn làm.
Nội dung SKILL.md
Nội dung SKILL.md gốc bằng tiếng Anh.
Performance Management
What it is: Structured reviews.
Overview
Works out the smallest useful Performance Management setup for the business in front of it, then
builds it only when asked. The default output is a short recommendation, not a
spreadsheet. Artifacts - CSV, SQL DDL, JSON Schema, Notion mapping - are produced on
request, from one field list so they cannot drift apart.
Layer: Layer 4: Manage. Fits: Growth stage. Table code: n/a.
When to Use This Skill
- performance review
- appraisal template
- performance review cycle
- employee review tracker
Also use it when the user says "structured reviews", or describes the same process happening in a
spreadsheet, a document or someone inboxes.
Do not use it for: payroll calculation, tax filing, or legal advice. This skill produces
empty templates only - it never holds or processes real employee or customer data.
How It Works
Follow the shared execution contract. The module-specific rules below define only domain fields, decisions, calculations, and safety constraints.
Step 1 - Identify intent
Read the request and pick the intent before asking anything.
- "set up" or "build" or "create" -> the user wants artifacts; go to Step 2.
- "our process is ..." or "it is in a sheet" -> the user wants to move an existing process; capture it, then Step 2.
- "is this right" or "review" or "audit" -> the user wants a check, not a build; answer from what they share.
- "how do I ..." -> advice question; answer directly and offer the build only if it helps.
Ask only if this is the highest-value missing fact; otherwise proceed without an opener:
> Q: How often do you review people?
Step 2 - Ask only what is missing
Skip anything the user already answered, in any earlier message. Ask the rest one at a
time, and stop as soon as the remaining answers would not change the output.
- Cycle - How often? / Probation too? / Who reviews whom?
- Content - Ratings or scores? / Goals plus feedback? / Development plan?
- Process - Who signs off? / Shared with the person? / Appeals?
- Current process - How do you review now? / Forms or documents? / Where stored?
- Outcome - What do you need? / Forms, records or reporting?
Never invent an answer. If the user does not know, record it as unknown and carry on.
Step 3 - Hold the internal context
Hold the answers in this shape. It stays internal - it is not shown to the user unless
they ask, and it never carries a value the user did not give.
module: performance-management
intent: null # setup | advice | review | fix | build | convert | export
scale: null # Starter | Growth | Scale, only if the answer changes it
areas:
"Cycle": null
"Content": null
"Process": null
"Current process": null
"Outcome": null
requested_outputs: [] # csv | sql | json | notion | xlsx - requested formats only
confirmed_facts: [] # only what the user actually said
open_questions: [] # the unanswered ones, in the order worth askingStep 4 - Recommend the smallest workflow
If an artifact was requested, build it after resolving essential missing facts. Otherwise give a short recommendation and offer the relevant artifact.
Recommended approach: Build the review form around goals and behaviours already tracked elsewhere, and store the record per cycle.
Why this one: Reviews become paperwork when the review duplicates data you already track. Reference the KPI and OKR records instead of re-entering them.
Workflow: Review cycle → Self input → Manager review → Discussion → Record and actions
Step 5 - Build only on request
Once the user asks for it, derive the fields from the confirmed context and emit the
requested artifacts. For machine-readable text, keep prose outside the data; for files,
provide a usable link. Report material validation failures or limitations separately.
**A selected Notion output is rendered by notion-manual-import, so route the
Notion step there.** When the user selects Notion, hand that step to
@notion-manual-import: it holds the CSV, the property
mapping, the import steps and the verification checklist, and it renders the Field
Reference below instead of defining a table of its own. Do not restate the mapping
here and do not improvise the import steps. Manual CSV and mapping outputs need no
connection. For requested workspace changes, follow the shared contract: verify actual
tool access and the target before writing. A user saying "connected" is not tool evidence.
Never ask for a Notion password or token.
For an Excel-compatible CSV, use UTF-8 with a byte order mark so Excel opens the
text correctly. A CSV is not an .xlsx workbook; create .xlsx only when the user
requests a workbook.
A CSV carries no types, so after it, name the columns
that need a number, date or currency format applied.
Review Title,Areas for Improvement,Behaviour Score,Department,Development Plan,Due Date,Employee Name,Increment Recommended,KPI Score,Notes,OKR Score,Overall Rating,PIP Required,Promotion Eligible,Rating Label,Review Date,Review ID,Review Period,Review Type,Reviewer,Status,Strengths
Q1 review - Example Employee,Delegation,4,Delivery,Lead one workstream,2026-04-15,Example Employee,FALSE,82,Synthetic quarterly review; manager draft awaiting calibration.,0.7,4 - Exceeds Expectations,FALSE,FALSE,Strong,2026-04-15,,Q1 2026,Quarterly,Example Reviewer,Manager Review,Reliable under pressureCREATE TABLE performance_management (
review_title VARCHAR(255),
areas_for_improvement VARCHAR(255),
behaviour_score NUMERIC,
department VARCHAR(255),
development_plan VARCHAR(255),
due_date DATE NOT NULL,
employee_name VARCHAR(255),
increment_recommended BOOLEAN,
kpi_score NUMERIC,
notes TEXT,
okr_score NUMERIC,
overall_rating VARCHAR(100),
pip_required BOOLEAN,
promotion_eligible BOOLEAN,
rating_label VARCHAR(255),
review_date DATE,
review_id SERIAL PRIMARY KEY,
review_period VARCHAR(255),
review_type VARCHAR(100) NOT NULL,
reviewer VARCHAR(255),
status VARCHAR(100) NOT NULL,
strengths VARCHAR(255),
created_at TIMESTAMP DEFAULT NOW(),
updated_at TIMESTAMP DEFAULT NOW()
);
CREATE INDEX idx_performance_management_status ON performance_management (status);{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "Performance Management",
"type": "object",
"additionalProperties": false,
"properties": {
"Review Title": { "type": "string" },
"Areas for Improvement": { "type": "string" },
"Behaviour Score": { "type": "number" },
"Department": { "type": "string" },
"Development Plan": { "type": "string" },
"Due Date": { "type": "string", "format": "date" },
"Employee Name": { "type": "string" },
"Increment Recommended": { "type": "boolean" },
"KPI Score": { "type": "number" },
"Notes": { "type": "string" },
"OKR Score": { "type": "number" },
"Overall Rating": { "type": "string" },
"PIP Required": { "type": "boolean" },
"Promotion Eligible": { "type": "boolean" },
"Rating Label": { "type": "string" },
"Review Date": { "type": "string", "format": "date" },
"Review ID": { "type": "integer" },
"Review Period": { "type": "string" },
"Review Type": { "type": "string" },
"Reviewer": { "type": "string" },
"Status": { "type": "string" },
"Strengths": { "type": "string" }
},
"required": [
"Due Date",
"Review Type",
"Status"
]
}| CSV column | Notion property | Set after import |
|---|---|---|
| Review Title | Title | Use as the database title |
| Areas for Improvement | Text | Leave as Text |
| Behaviour Score | Number | Convert to Number |
| Department | Text | Leave as Text |
| Development Plan | Text | Leave as Text |
| Due Date | Date | Convert to Date |
| Employee Name | Text | Leave as Text |
| Increment Recommended | Checkbox | Convert to Checkbox |
| KPI Score | Number | Convert to Number |
| Notes | Text | Leave as Text |
| OKR Score | Number | Convert to Number |
| Overall Rating | Select (add options after import) | Convert to Select, add options: "1 - Needs Improvement", "2 - Developing", "3 - Meets Expectations", "4 - Exceeds Expectations", "5 - Outstanding" |
| PIP Required | Checkbox | Convert to Checkbox |
| Promotion Eligible | Checkbox | Convert to Checkbox |
| Rating Label | Text | Leave as Text |
| Review Date | Date | Convert to Date |
| Review ID | Text (preserve source ID) | Keep imported IDs as Text; optionally add a separate Unique ID property |
| Review Period | Text | Leave as Text |
| Review Type | Select (add options after import) | Convert to Select, add options: "Probation", "Quarterly", "Half Yearly", "Annual", "Mid Term" |
| Reviewer | Text | Leave as Text |
| Status | Select (add options after import) | Convert to Select, add options: "Not Started", "Self Rev… (nội dung đầy đủ có trong gói tải về)
Skill liên quan
- performance-optimizer – Xác định và sửa nút thắt hiệu năng trong mã nguồn, cơ sở dữ liệu và API. Đo trước và sau…
- performance-testing-review-ai-review – Rà soát các thay đổi mã nhạy cảm về hiệu năng với mốc chuẩn tái lập được, chỉ số khối…
- performance-testing-review-multi-agent-review – Rà soát một diff mã đã xác định từ góc nhìn đúng đắn, phân quyền và hiệu năng liên quan…
- permission-manager – Quản lý quyền của opencode: rà soát danh sách luôn cho phép, đề xuất lệnh chỉ đọc an…
- phase-gated-debugging – Dùng khi gỡ lỗi bất kỳ lỗi nào. Áp dụng quy trình 5 pha, chặn chỉnh sửa code cho đến khi…
- php – Hướng dẫn super-code theo từng ngôn ngữ dành cho php.
- pi-delegate – Giao việc viết code cho CLI Pi coding agent (`pi`) chỉ khi người dùng yêu cầu rõ ràng…
- placecall – Thực hiện cuộc gọi đi thật tới doanh nghiệp tại Mỹ qua PlaceCall API: đặt lịch, hỏi…