alumni-re-hire-tracker – skill Dữ liệu & Khoa học cho agent AI
Sổ đăng ký cựu nhân viên và tái tuyển dụng: vị trí cũ, ngày làm việc cuối cùng, điều kiện tái tuyển, nơi làm việc hiện tại và ngày tái kết nối, xuất dạng CSV, SQL, JSON Schema hoặc Notion theo yêu cầu. Dùng cho việc liên hệ cựu nhân viên.
Cài skill alumni-re-hire-tracker 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/alumni-re-hire-tracker-d623f.tgz | tar xz -C ~/.claude/skills
Gọi trong Claude Code: /alumni-re-hire-tracker – rồi mô tả công việc bạn muốn làm.
Codex
mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/alumni-re-hire-tracker-d623f.tgz | tar xz -C ~/.codex/skills
Gọi trong Codex: $alumni-re-hire-tracker – rồi mô tả công việc bạn muốn làm.
Hermes Agent
mkdir -p ~/.hermes/skills && curl -fsSL https://skill.dn1nguoi.com/z/alumni-re-hire-tracker-d623f.tgz | tar xz -C ~/.hermes/skills
Gọi trong Hermes Agent: /alumni-re-hire-tracker – rồi mô tả công việc bạn muốn làm.
DeepSeek
mkdir -p ~/.deepcode/skills && curl -fsSL https://skill.dn1nguoi.com/z/alumni-re-hire-tracker-d623f.tgz | tar xz -C ~/.deepcode/skills
Gọi trong DeepSeek: /alumni-re-hire-tracker – rồi mô tả công việc bạn muốn làm.
Nội dung SKILL.md
Nội dung SKILL.md gốc bằng tiếng Anh.
Alumni & Re-hire Tracker
What it is: Former employees.
Overview
Works out the smallest useful Alumni & Re-hire Tracker 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 10: Exit. Fits: Scale stage. Table code: n/a.
When to Use This Skill
- alumni tracker
- rehire tracker
- former employee register
- past employee list
Also use it when the user says "former employees", 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 have left the company?
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.
- Alumni - How many ex-employees? / How long ago? / Any warm contacts?
- Fit - Why would you re-hire? / Roles they held? / Skills worth recording?
- Reach - How do you stay in touch? / Any consent on file? / How often to check in?
- Current process - Is anything recorded? / LinkedIn or a sheet? / What gets missed?
- Outcome - What do you need? / An alumni register, a re-hire view or both?
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: alumni-re-hire-tracker
intent: null # setup | advice | review | fix | build | convert | export
scale: null # Starter | Growth | Scale, only if the answer changes it
areas:
"Alumni": null
"Fit": null
"Reach": 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 a small alumni record with the exit date, the role held and one line on why they left, and revisit it only when a role opens.
Why this one: Alumni records are only worth maintaining if something triggers a revisit. Tie it to open roles instead of a standing newsletter.
Workflow: Departure recorded → Details kept → Re-hire considered when a role opens → Rejoined or contacted
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.
Alumni Name,Former Department,Former Job Title,Last Working Day,Rehire Eligible,Personal Email,LinkedIn,Current Company,Last Contact,Re-engage Date,Notes,Alumni ID
Example Person,Delivery,Delivery Manager,2026-03-31,TRUE,[email protected],https://example.com/in/example-person,Example Company,2026-01-20,2026-07-01,"Reached out in February; interested in returning once the current notice period ends.",CREATE TABLE alumni_re_hire_tracker (
alumni_name VARCHAR(255),
former_department VARCHAR(255),
former_job_title VARCHAR(255),
last_working_day DATE NOT NULL,
rehire_eligible BOOLEAN NOT NULL,
personal_email VARCHAR(255),
linkedin TEXT,
current_company VARCHAR(255),
last_contact DATE,
re_engage_date DATE,
notes TEXT,
alumni_id SERIAL PRIMARY KEY,
created_at TIMESTAMP DEFAULT NOW(),
updated_at TIMESTAMP DEFAULT NOW()
);{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "Alumni & Re-hire Tracker",
"type": "object",
"additionalProperties": false,
"properties": {
"Alumni Name": { "type": "string" },
"Former Department": { "type": "string" },
"Former Job Title": { "type": "string" },
"Last Working Day": { "type": "string", "format": "date" },
"Rehire Eligible": { "type": "boolean" },
"Personal Email": { "type": "string", "format": "email" },
"LinkedIn": { "type": "string", "format": "uri" },
"Current Company": { "type": "string" },
"Last Contact": { "type": ["string", "null"], "format": "date" },
"Re-engage Date": { "type": ["string", "null"], "format": "date" },
"Notes": { "type": "string" },
"Alumni ID": { "type": "integer" }
},
"required": [
"Last Working Day",
"Rehire Eligible"
]
}| CSV column | Notion property | Set after import |
|---|---|---|
| Alumni Name | Title | Use as the database title |
| Former Department | Text | Leave as Text |
| Former Job Title | Text | Leave as Text |
| Last Working Day | Date | Convert to Date |
| Rehire Eligible | Checkbox | Convert to Checkbox |
| Personal Email | Email | Convert to Email |
| LinkedIn | URL | Convert to URL |
| Current Company | Text | Leave as Text |
| Last Contact | Date | Convert to Date |
| Re-engage Date | Date | Convert to Date |
| Notes | Text | Leave as Text |
| Alumni ID | Text (preserve source ID) | Keep imported IDs as Text; optionally add a separate Unique ID property |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 | Alumni Name | text | VARCHAR(255) | string | Text | Example Person |
| 2 | Former Department | text | VARCHAR(255) | string | Text | Delivery |
| 3 | Former Job Title | text | VARCHAR(255) | string | Text | Delivery Manager |
| 4 | Last Working Day | date | DATE | string, format: date | Date | 2026-03-31 |
| 5 | Rehire Eligible | checkbox | BOOLEAN | boolean | Checkbox | TRUE |
| 6 | Personal Email | email | VARCHAR(255) | string, format: email | Email | [email protected] |
| 7 | LinkedIn | url | TEXT | string, format: uri | URL | https://example.com/in/example-person |
| 8 | Current Company | text | VARCHAR(255) | string | Text | Example Company |
| 9 | Last Contact | date | DATE | string, format: date | Date | 2026-01-20 |
| 10 | Re-engage Date | date | DATE | string, format: date | Date | 2026-07-01 |
| 11 | Notes | long_text | TEXT | string | Text | Reached out in February; interested in returning once the current notice period ends. |
| 12 | Alumni ID | id | SERIAL PRIMARY KEY | integer | Text (preserve source ID) | (blank) |
Select Options
_No Select fields._
Relations
Link fields: none
… (nội dung đầy đủ có trong gói tải về)
Skill liên quan
- data-storytelling – Biến dữ liệu thành câu chuyện thuyết phục bằng trực quan hóa, bối cảnh và cấu trúc có…
- database-migration – Thực hiện migration cơ sở dữ liệu trên nhiều ORM và nền tảng, với chiến lược…
- notion-research-documentation – Nghiên cứu trên Notion và tổng hợp thành tài liệu có cấu trúc. Dùng khi thu thập thông…
- chroma – Cơ sở dữ liệu embedding cho RAG và tìm kiếm ngữ nghĩa.
- observability-and-instrumentation – Gắn công cụ đo lường (instrumentation) vào code để hành vi production có thể quan sát và…
- depmap – Truy xuất và phân tích dữ liệu bản phát hành Cancer Dependency Map (DepMap), gồm hiệu…
- dataset-curation – Chuẩn bị, định dạng và kiểm tra dataset cho supervised fine-tuning và huấn luyện theo sở…
- dbt-transformation-patterns – Thành thạo dbt (data build tool) cho analytics engineering với tổ chức model, kiểm thử…