leave-management – skill Khác cho agent AI
Sổ đăng ký nghỉ phép: yêu cầu, loại nghỉ, nhân viên và phòng ban, quản lý và người phê duyệt, ngày bắt đầu và kết thúc, số ngày xin nghỉ, số dư phép, ghi chú bàn giao và trạng thái. Dùng để theo dõi nghỉ phép.
Cài skill leave-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/leave-management-cc4b6.tgz | tar xz -C ~/.claude/skills
Gọi trong Claude Code: /leave-management – rồi mô tả công việc bạn muốn làm.
Codex
mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/leave-management-cc4b6.tgz | tar xz -C ~/.codex/skills
Gọi trong Codex: $leave-management – rồi mô tả công việc bạn muốn làm.
Hermes Agent
mkdir -p ~/.hermes/skills && curl -fsSL https://skill.dn1nguoi.com/z/leave-management-cc4b6.tgz | tar xz -C ~/.hermes/skills
Gọi trong Hermes Agent: /leave-management – rồi mô tả công việc bạn muốn làm.
DeepSeek
mkdir -p ~/.deepcode/skills && curl -fsSL https://skill.dn1nguoi.com/z/leave-management-cc4b6.tgz | tar xz -C ~/.deepcode/skills
Gọi trong DeepSeek: /leave-management – rồi mô tả công việc bạn muốn làm.
Nội dung SKILL.md
Nội dung SKILL.md gốc bằng tiếng Anh.
Leave Management
What it is: Leave tracking.
Overview
Works out the smallest useful Leave 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: Starter stage. Table code: n/a.
When to Use This Skill
- leave tracker
- leave management system
- vacation tracker
- absence register
Also use it when the user says "leave tracking", 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 many people need leave tracking?
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.
- Scope - How many people? / Who applies for leave? / Full time or part time?
- Rules - Which leave types? / Who approves? / Track balances or days?
- Process - Notice needed? / Handover required? / Carry over allowed?
- Current process - How do you track leave today? / Sheet, app or nothing? / What breaks?
- Outcome - What do you need? / Approvals, balances 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: leave-management
intent: null # setup | advice | review | fix | build | convert | export
scale: null # Starter | Growth | Scale, only if the answer changes it
areas:
"Scope": null
"Rules": 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: Keep leave in the tool people already use and add the missing approval and balance steps, not a new system.
Why this one: Leave records go stale when balances and requests live apart. One place for both, with an approval state, keeps them consistent.
Workflow: Request → Manager approval → Calendar entry → Balance update → Report
Treat balances as optional dated snapshots from the approved leave system, not authoritative entitlements stored independently on each request. Define calendar, holidays, working pattern and partial-day units before counting days; end date must not precede start date. Collect only the minimum reason needed; exclude diagnoses and keep emergency contact information in a separately restricted directory rather than routine calendar exports.
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.
Leave Request,Annual Leave Balance,Approver,Days Requested,Department,Emergency Contact,Employee Name,End Date,Handover Notes,Leave ID,Leave Type,Manager,Notes,Reason,Sick Leave Balance,Start Date,Status
2026-02-10 to 2026-02-12,14,Sneha Iyer,3,Delivery,Anil Sharma,Aarav Sharma,2026-02-12,Client handover to Rohit Verma,,Annual,Sneha Iyer,Approved by the reporting manager; handover agreed with the team.,Family commitment,8,2026-02-10,TakenCREATE TABLE leave_management (
leave_request VARCHAR(255),
annual_leave_balance NUMERIC,
approver VARCHAR(255),
days_requested NUMERIC NOT NULL,
department VARCHAR(255),
emergency_contact VARCHAR(255),
employee_name VARCHAR(255),
end_date DATE NOT NULL,
handover_notes TEXT,
leave_id SERIAL PRIMARY KEY,
leave_type VARCHAR(100) NOT NULL,
manager VARCHAR(255),
notes TEXT,
reason VARCHAR(255),
sick_leave_balance NUMERIC,
start_date DATE NOT NULL,
status VARCHAR(100) NOT NULL,
created_at TIMESTAMP DEFAULT NOW(),
updated_at TIMESTAMP DEFAULT NOW()
);
CREATE INDEX idx_leave_management_status ON leave_management (status);{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "Leave Management",
"type": "object",
"additionalProperties": false,
"properties": {
"Leave Request": { "type": "string" },
"Annual Leave Balance": { "type": "number" },
"Approver": { "type": "string" },
"Days Requested": { "type": "number" },
"Department": { "type": "string" },
"Emergency Contact": { "type": "string" },
"Employee Name": { "type": "string" },
"End Date": { "type": "string", "format": "date" },
"Handover Notes": { "type": "string" },
"Leave ID": { "type": "integer" },
"Leave Type": { "type": "string" },
"Manager": { "type": "string" },
"Notes": { "type": "string" },
"Reason": { "type": "string" },
"Sick Leave Balance": { "type": "number" },
"Start Date": { "type": "string", "format": "date" },
"Status": { "type": "string" }
},
"required": [
"Days Requested",
"End Date",
"Leave Type",
"Start Date",
"Status"
]
}| CSV column | Notion property | Set after import |
|---|---|---|
| Leave Request | Title | Use as the database title |
| Annual Leave Balance | Number | Convert to Number |
| Approver | Text | Leave as Text |
| Days Requested | Number | Convert to Number |
| Department | Text | Leave as Text |
| Emergency Contact | Text | Leave as Text |
| Employee Name | Text | Leave as Text |
| End Date | Date | Convert to Date |
| Handover Notes | Text | Leave as Text |
| Leave ID | Text (preserve source ID) | Keep imported IDs as Text; optionally add a separate Unique ID property |
| Leave Type | Select (add options after import) | Convert to Select, add options: "Annual", "Sick", "Casual", "Unpaid", "Maternity", "Paternity", "Comp Off" |
| Manager | Text | Leave as Text |
| Notes | Text | Leave as Text |
| Reason | Text | Leave as Text |
| Sick Leave Balance | Number | Convert to Number |
| Start Date | Date | Convert to Date |
| Status | Select (add options after import) | Convert to Select, add options: "Pending", "Approved", "Declined", "Cancelled", "Taken" |The rows above are documentation examples only. Emit empty templates unless the user explicitly requests examples. Money stays currency, dates stay date,
and anything pointing at another table stays relation.
Field Reference
| # | Field | Type | SQL | JSON Schema | Notion | CSV example |
|---:|---|---|---|---|---|---|
| 1 | Leave Request | text | VARCHAR(255) | string | Text
… (nội dung đầy đủ có trong gói tải về)
Skill liên quan
- ledger-tasks-yylo – Dùng quản lý tác vụ YYLO Ledger: tạo, liệt kê, tìm kiếm, lấy, đánh dấu, cập nhật, lưu…
- leiloeiro-edital – Phân tích và kiểm toán edital (thông báo) đấu giá tư pháp và ngoài tư pháp. Rủi ro ẩn…
- leiloeiro-ia – Chuyên gia đấu giá tư pháp và ngoài tư pháp bất động sản. Phân tích pháp lý, thẩm định…
- leiloeiro-juridico – Phân tích pháp lý đấu giá: vô hiệu, bem de família, alienação fiduciária, CPC arts…
- leiloeiro-mercado – Phân tích thị trường bất động sản cho đấu giá. Thanh khoản, mức chiết khấu điển hình…
- lesson-generator – Tạo các sản phẩm khóa học nhiều bài, gọn nhẹ và độc lập, có điều hướng bài học, mục…
- lightning-channel-factories – Tài liệu kỹ thuật về channel factory của Lightning Network, kênh đa bên, kiến trúc LSP…
- lightning-factory-explainer – Giải thích channel factory của Bitcoin Lightning và giao thức SuperScalar — onboarding…