candidate-talent-pool – Other skill for AI agents

Candidate Talent Pool

What it is: Prospect database.

Overview

Works out the smallest useful Candidate Talent Pool 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 2: Acquire. Fits: Growth stage. Table code: n/a.

When to Use This Skill

• talent pool database
• candidate tracker
• recruiter pipeline spreadsheet
• keep candidates warm

Also use it when the user says "prospect database", 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: Which roles do you hire for?

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.

• Roles - Which roles? / How many open? / Any hard-to-fill roles?
• Pipeline - How do you find people now? / Referrals or inbound? / Keep rejects warm?
• Pool - How long to keep? / Contact allowed? / Consent to re-engage?
• Current process - Where do CVs sit now? / Spreadsheet or inbox? / How many in the pool?
• Outcome - What do you need? / A pool, a tracker or alerts?

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: candidate-talent-pool
intent: null            # setup | advice | review | fix | build | convert | export
scale: null             # Starter | Growth | Scale, only if the answer changes it
areas:
  "Roles": null
  "Pipeline": null
  "Pool": 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 asking

Step 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 warm pool with consent and a re-engage date. It is a contact list with a purpose, not a resume archive.

Why this one: Previous applicants may be a relevant source when retention and re-contact are appropriate. Consent and a re-engage date are what make it reusable.

Workflow: Candidate added → Consent → Re-engage date → Reminder → Reopen role

Re-engagement gate: a candidate may carry a Re-engage Date only when Consent Status is Granted. If consent was never recorded, leave Re-engage Date empty, set Consent Status to Not recorded, and tell the user how many candidates are blocked on it. Do not infer consent from a role being open, from the candidate replying once, or from their CV being on file. Declined is final: never re-contact, and never quietly reset it to Not recorded to make a re-engagement list longer.

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.

Candidate Name,Candidate ID,Department,Email,Experience (Years),Last Contact,LinkedIn URL,Notes,Phone,Consent Status,Consent Date,Re-engage Date,Referred By,Skills,Source,Status,Target Role
Example Person,,Delivery,[email protected],6,2026-01-20,https://example.com/in/example-person,Went cold in February after a counter-offer; worth re-approaching in six months.,+91 98xxxxxx21,Granted,2026-01-05,2026-07-01,Example Referrer,"Python, SQL, Stakeholder Management",Referral,Active,Delivery Manager

CREATE TABLE candidate_talent_pool (
  candidate_name VARCHAR(255),
  candidate_id SERIAL PRIMARY KEY,
  department VARCHAR(255),
  email VARCHAR(255),
  experience_years NUMERIC CHECK (experience_years >= 0),
  last_contact DATE,
  linkedin_url TEXT,
  notes TEXT,
  phone VARCHAR(255),
  consent_status VARCHAR(100) NOT NULL,
  consent_date DATE,
  re_engage_date DATE,
  referred_by VARCHAR(255),
  skills VARCHAR(255),
  source VARCHAR(255),
  status VARCHAR(100) NOT NULL,
  target_role VARCHAR(255),
  created_at TIMESTAMP DEFAULT NOW(),
  updated_at TIMESTAMP DEFAULT NOW(),
  -- Conservative workflow gate; not a determination of legal basis.
  CHECK (consent_status IN ('Not recorded', 'Granted', 'Declined')),
  CHECK (consent_status = 'Granted' OR re_engage_date IS NULL),
  CHECK (consent_status <> 'Granted' OR consent_date IS NOT NULL)
);

CREATE INDEX idx_candidate_talent_pool_status ON candidate_talent_pool (status);
CREATE INDEX idx_candidate_talent_pool_re_engage_date ON candidate_talent_pool (re_engage_date);

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "Candidate Talent Pool",
  "type": "object",
  "additionalProperties": false,
  "properties": {
      "Candidate Name": { "type": "string" },
      "Candidate ID": { "type": "integer" },
      "Department": { "type": "string" },
      "Email": { "type": "string", "format": "email" },
      "Experience (Years)": { "type": ["number", "null"], "minimum": 0 },
      "Last Contact": { "type": ["string", "null"], "format": "date" },
      "LinkedIn URL": { "type": "string", "format": "uri" },
      "Notes": { "type": "string" },
      "Phone": { "type": "string" },
      "Consent Status": { "enum": ["Not recorded", "Granted", "Declined"] },
      "Consent Date": { "type": ["string", "null"], "format": "date" },
      "Re-engage Date": { "type": ["string", "null"], "format": "date" },
      "Referred By": { "type": "string" },
      "Skills": { "type": "string" },
      "Source": { "type": "string" },
      "Status": { "type": "string" },
      "Target Role": { "type": "string" }
  },
  "allOf": [
    {"if": {"properties": {"Consent Status": {"const": "Granted"}}, "required": ["Consent Status"]}, "then": {"required": ["Consent Date"], "properties": {"Consent Date": {"type": "string", "format": "date"}}}, "else": {"properties": {"Re-engage Date": {"type": "null"}}}}
  ],
  "required": [
      "Consent Status",
      "Status"
  ]
}

| CSV column | Notion property | Set after import |
|---|---|---|
| Candidate Name | Title | Use as the database title |
| Candidate ID | Text (preserve source ID) | Keep imported IDs as Text; optionally add a separate Unique ID property |
| Department | Text | Leave as Text |
| Email | Email | Convert to Email |
| Experience (Years) | Number | Convert to Number |
| Last Contact | Date | Convert to Date |
| LinkedIn URL | URL | Convert to URL |
| Notes | Text | Leave as Text |
| Phone | Text | Leave as Text |
| Consent Status | Select (add options after import) | Conv

… (full content is in the download package)