agentleFS
rubiconrubicon/ai-skills/skills/secret-santa-generator/SKILL.md

secret-santa-generator

Skill1 starsChanged 3 months agoMITView on GitHub

Generate Secret Santa assignment lists from participant names and optional exclusion pairs. Use when the user asks to organize a Secret Santa, assign recipients, resolve duplicate names, or validate exclusion constraints.

The file

Show its rules and text

We split this skill into the rules it gives an agent

21 rules. About 0 are common, 21 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈21

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user:

    line 16
  2. Distinctive:

    Every person gives to exactly one other person.

    line 52
  3. Distinctive:

    Every person receives from exactly one other person.

    line 53
  4. Distinctive:

    No one is assigned to themselves.

    line 54
  5. Distinctive:

    Never silently remove duplicate names.

    line 57
  6. Distinctive:

    If fewer than two valid participants remain after cleanup, explain why and ask the user to revise.

    line 58
  7. Distinctive:

    If exclusions make a valid assignment impossible, explain why and suggest removing one or more exclusion pairs.

    line 59
  8. Distinctive:

    If a name appears more than once:

    line 63
  9. Distinctive:

    Stop before generating assignments.

    line 64
  10. Distinctive:

    Ask whether the duplicate is accidental or refers to different people.

    line 66
  11. Distinctive:

    If it is intentional, ask for a designator so the names can be distinguished.

    line 67
  12. Distinctive:

    Verify that no self-assignments or exclusion violations exist.

    line 77
  13. Distinctive:

    If the assignment is invalid, retry with a different shuffle.

    line 78
  14. Distinctive:

    If repeated retries fail, explain that the constraints are impossible and ask the user to revise the exclusions or participants.

    line 79
  15. Distinctive:

    If the user wants it, also provide the results as:

    line 97
  16. Distinctive:

    Before presenting results, confirm:

    line 103
  17. Distinctive:

    Every participant appears exactly once as a giver

    line 104
  18. Distinctive:

    Every participant appears exactly once as a recipient

    line 105
  19. Distinctive:

    No one is assigned to themselves

    line 106
  20. Distinctive:

    No exclusion rule is violated

    line 107
  21. Distinctive:

    If validation fails, do not present the result as final.

    line 109

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Secret Santa Generator

Generate a randomized Secret Santa assignment list from participant names and optional exclusion rules.

When To Use

Use this skill when the user:

  • Wants to organize or run a Secret Santa
  • Needs a randomized giver-to-recipient assignment list
  • Has exclusion pairs that must not be matched
  • Wants duplicate names resolved before assignments are generated
  • Wants results as plain text, CSV, or JSON

Inputs

Accept participant names in any mix of these formats:

  • One name per line
  • Comma-separated
  • Semicolon-separated
  • Pipe-separated
  • Tab-separated
  • Space-separated

Accept exclusions in any of these formats:

  • EXCLUDE: Mum & Dad, Alice & Bob
  • EXCLUDE: followed by one pair per line
  • Flexible spacing around delimiters

Within an exclusion pair, the names may be separated by:

  • &
  • |
  • +
  • /
  • and
  • vs
  • -
  • ,

Trim leading and trailing whitespace from every name.

Rules

  • Every person gives to exactly one other person.
  • Every person receives from exactly one other person.
  • No one is assigned to themselves.
  • Exclusions are symmetric. If A cannot give to B, then B cannot give to A.
  • Ignore blank entries.
  • Never silently remove duplicate names.
  • If fewer than two valid participants remain after cleanup, explain why and ask the user to revise.
  • If exclusions make a valid assignment impossible, explain why and suggest removing one or more exclusion pairs.

Duplicate Names

If a name appears more than once:

  • Stop before generating assignments.
  • Tell the user which name is duplicated and how many times it appears.
  • Ask whether the duplicate is accidental or refers to different people.
  • If it is intentional, ask for a designator so the names can be distinguished.
  • Confirm the resolved names before continuing.

Assignment Workflow

  1. Normalize and deduplicate the input.
  2. Parse exclusions.
  3. Validate that at least two participants remain.
  4. Randomly shuffle the participant list.
  5. Assign each person the next person in the shuffled list, wrapping around at the end.
  6. Verify that no self-assignments or exclusion violations exist.
  7. If the assignment is invalid, retry with a different shuffle.
  8. If repeated retries fail, explain that the constraints are impossible and ask the user to revise the exclusions or participants.

Output Format

Present results clearly and consistently.

Recommended plain-text format:

  • Alice -> Charlie
  • Bob -> Diana
  • Charlie -> Alice
  • Diana -> Bob

Then include a short summary:

  • Participant count
  • Pairing count
  • Exclusion count
  • Validation status

If the user wants it, also provide the results as:

  • CSV
  • JSON

Safety And Validation

Before presenting results, confirm:

  • Every participant appears exactly once as a giver
  • Every participant appears exactly once as a recipient
  • No one is assigned to themselves
  • No exclusion rule is violated

If validation fails, do not present the result as final.

Examples

User: "Set up a Secret Santa for Alice, Bob, Carol, and Dave. Bob and Carol are married, so don't pair them." Result: A valid randomized assignment that respects the exclusion rule.

User: "Run a Secret Santa for our 12-person team, list attached." Result: Parse the names, validate the set, and generate assignments.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.