buddy-program-manager – Other skill for AI agents
Buddy programme register: new hire, assigned buddy, department, start and end dates, check-ins planned and done, and feedback score. Use for onboarding buddy schemes.
Install the buddy-program-manager skill with one command
Pick the tool you use, copy the command and paste it in your terminal. The skill lands in that tool's skills folder and is ready in your next session.
Claude Code
mkdir -p ~/.claude/skills && curl -fsSL https://skill.dn1nguoi.com/z/buddy-program-manager-6e62d.tgz | tar xz -C ~/.claude/skills
Call it in Claude Code: /buddy-program-manager – then describe the task you want done.
Codex
mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/buddy-program-manager-6e62d.tgz | tar xz -C ~/.codex/skills
Call it in Codex: $buddy-program-manager – then describe the task you want done.
Hermes Agent
mkdir -p ~/.hermes/skills && curl -fsSL https://skill.dn1nguoi.com/z/buddy-program-manager-6e62d.tgz | tar xz -C ~/.hermes/skills
Call it in Hermes Agent: /buddy-program-manager – then describe the task you want done.
DeepSeek
mkdir -p ~/.deepcode/skills && curl -fsSL https://skill.dn1nguoi.com/z/buddy-program-manager-6e62d.tgz | tar xz -C ~/.deepcode/skills
Call it in DeepSeek: /buddy-program-manager – then describe the task you want done.
SKILL.md content
Buddy Program Manager
What it is: Peer support.
Overview
Works out the smallest useful Buddy Program Manager 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 3: Onboard. Fits: Scale stage. Table code: n/a.
When to Use This Skill
- buddy program
- new hire buddy
- peer onboarding tracker
- onboarding buddy manager
Also use it when the user says "peer support", 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 new joiners do you onboard a month?
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.
- Volume - New joiners per month? / One buddy each? / Same team or cross-team?
- Programme - How long? / Check-in cadence? / Feedback captured?
- People - Who can be a buddy? / Time allocated? / Recognition for buddies?
- Current process - Anything informal today? / How is it tracked? / What fails?
- Outcome - What do you need? / Matching, check-ins or feedback?
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: buddy-program-manager
intent: null # setup | advice | review | fix | build | convert | export
scale: null # Starter | Growth | Scale, only if the answer changes it
areas:
"Volume": null
"Programme": null
"People": 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: Match buddies by department and timezone, then track a small number of check-ins. Do not build a scoring system for it.
Why this one: Buddy programmes fail on load, not on matching. Three check-ins over 30 days is an illustrative starting cadence; adapt it to participant needs and measured programme feedback.
Workflow: New joiner → Buddy match → Check-ins → Feedback → Buddy recognition
Feedback Score is optional and must stay blank until voluntary feedback exists; define its scale and purpose before use. It is not a performance ranking. Check-in counts are nonnegative whole events; counts and snapshots do not replace the dated event log described below. Distinguish planned end from actual close, and validate date order.
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.
Buddy Pair,New Hire,Buddy,Department,Start Date,End Date,Check-ins Planned,Check-ins Done,Feedback Score,Status,Notes,Buddy ID
Example New Hire + Example Buddy,Example New Hire,Example Buddy,Delivery,2026-01-05,2026-12-19,6,3,4,Active,First-week check-in done; the buddy asked for a narrower first assignment.,CREATE TABLE buddy_program_manager (
buddy_pair VARCHAR(255),
new_hire VARCHAR(255), -- relation -> target record
buddy VARCHAR(255), -- relation -> target record
department VARCHAR(255),
start_date DATE NOT NULL,
end_date DATE NOT NULL,
check_ins_planned NUMERIC NOT NULL,
check_ins_done NUMERIC NOT NULL,
feedback_score NUMERIC,
status VARCHAR(100) NOT NULL,
notes TEXT,
buddy_id SERIAL PRIMARY KEY,
created_at TIMESTAMP DEFAULT NOW(),
updated_at TIMESTAMP DEFAULT NOW()
);
CREATE INDEX idx_buddy_program_manager_status ON buddy_program_manager (status);{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "Buddy Program Manager",
"type": "object",
"additionalProperties": false,
"properties": {
"Buddy Pair": { "type": "string" },
"New Hire": { "type": "string" },
"Buddy": { "type": "string" },
"Department": { "type": "string" },
"Start Date": { "type": "string", "format": "date" },
"End Date": { "type": "string", "format": "date" },
"Check-ins Planned": { "type": "number" },
"Check-ins Done": { "type": "number" },
"Feedback Score": { "type": "number" },
"Status": { "type": "string" },
"Notes": { "type": "string" },
"Buddy ID": { "type": "integer" }
},
"required": [
"Start Date",
"End Date",
"Check-ins Planned",
"Check-ins Done",
"Status"
]
}| CSV column | Notion property | Set after import |
|---|---|---|
| Buddy Pair | Title | Use as the database title |
| New Hire | Relation (link to the target database) | Convert to Relation, link to the target database |
| Buddy | Relation (link to the target database) | Convert to Relation, link to the target database |
| Department | Text | Leave as Text |
| Start Date | Date | Convert to Date |
| End Date | Date | Convert to Date |
| Check-ins Planned | Number | Convert to Number |
| Check-ins Done | Number | Convert to Number |
| Feedback Score | Number | Convert to Number |
| Status | Select (add options after import) | Convert to Select, add options: "Not Started", "Active", "Paused", "Completed" |
| Notes | Text | Leave as Text |
| Buddy 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 | Buddy Pair | text | VARCHAR(255) | string | Text | Example New Hire + Example Buddy |
| 2 | New Hire | relation | VARCHAR(255) | string | Relation (link to the target database) | Example New Hire |
| 3 | Buddy | relation | VARCHAR(255) | string | Relation (link to the target database) | Example Buddy |
| 4 | Department | text | VARCHAR(255) | string | Text | Delivery |
| 5 | Start Date | date | DATE | string, format: date | Date | 2026-01-05 |
| 6 | End Date | date | DATE | string, format: date | Date | 2026-12-19 |
| 7 | Check-ins Planned | number | NUMERIC | number | Number | 6 |
| 8 | Check-ins Done | number | NUMERIC | number | Number | `3
… (full content is in the download package)
Related skills
- budget-cash-flow – Budget against actual by department, category and period, with budget and actual…
- obsidian – Read, search, create, and edit notes in the Obsidian vault.
- busabase – Use when managing Busabase workspace records, knowledge, apps, or skills through…
- one-three-one-rule – 1-3-1 decision briefs: problem, three options, one pick.
- busybox-on-windows – How to use a Win32 build of BusyBox to run many of the standard UNIX command line tools…
- c4-container – Expert C4 Container-level documentation specialist.
- c4-context – Expert C4 Context-level documentation specialist. Creates high-level system context…
- candidate-talent-pool – Candidate and prospect pool: contact details, experience, skills, consent status and…