Index of every page on this site: llms.txt
All skills
microsoft avatar

/name-generator

@7bf7acb
Run it yourself

Generate approved person names for examples, demos, quests, tests, docs, and sample data. Use when a task needs fictional person names, customer names, employee names, patient names, student names, instructor names, or other human names.

Use this Skill: https://skilld.dev/gh/microsoft/ontology-playground/name-generator

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈63 tokens for metadata: the name and description. ≈773 when used: this file.

Description uses 3.2% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈254 characters, or 3.2%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Name Generator Skill

Goal

Generate person names for this repository from the approved local name fixture:

data/reference/FNF-2026-06-01-01002-0268.csv

Do not invent person names. Every person name used in examples, sample data, quests, tests, demos, docs, or generated ontology content must come from the CSV FullName column.

Source File

CSV columns:

FirstName,LastName,FullName,FirstNameNative,LastNameNative,FullNameNative,Gender,Language

Use FullName by default. Use FullNameNative only when the user explicitly asks for native-script names or locale-specific display text.

Workflow

1. Decide how many names are needed

Identify the role and quantity from the task, for example:

  • sample customers
  • employees or managers
  • patients or clinicians
  • students or instructors
  • reviewers, approvers, assignees, or contributors

If the task does not specify quantity, use the minimum number needed for the example or test.

2. Read names from the CSV

Use the CSV fixture as the only source. A quick shell-friendly way to inspect the first approved names is:

awk -F, 'NR > 1 { print $3 }' data/reference/FNF-2026-06-01-01002-0268.csv | head

For random sampling:

awk -F, 'NR > 1 { print rand() "\t" $3 }' data/reference/FNF-2026-06-01-01002-0268.csv | sort -n | cut -f2- | head -n 5

If names with commas or quotes are ever added to the CSV, use a proper CSV parser instead of field splitting.

3. Fit names to the scenario

  • Choose distinct names for distinct entities.
  • Keep the selected names stable within a scenario so queries, expected results, docs, and sample instances stay consistent.
  • Do not alter spellings unless the surrounding file has a strict ASCII-only convention. If ASCII is required, choose names from the CSV that are already ASCII-compatible.
  • Email addresses and IDs may be generic (customer001@example.com) and do not need to use the person's name.

4. Update all dependent examples

When replacing a name in code or content, update every coupled surface:

  • sample instances
  • query prompts and curated query matches
  • expected test strings
  • rendered docs or generated content source files
  • catalogue examples or learning materials

Regenerate compiled artifacts when source content changes:

npm run catalogue:build
npm run learn:build

Validation

Before finishing a name-generation or name-replacement task:

  1. Verify each selected name appears in the CSV FullName column.
  2. Search for removed placeholder names to ensure no stale references remain.
  3. Run focused tests for touched code paths.
  4. Run npm run build when generated catalogue or learning output changes.

Done Criteria

  • All person names used by the task come from data/reference/FNF-2026-06-01-01002-0268.csv.
  • No invented placeholder names remain in the touched examples.
  • Related prompts, sample data, expected results, and tests are consistent.
  • Relevant tests or build commands have passed, or any skipped validation is clearly reported.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts4mo3 checks · Risk SAFE
  • Gen Agent Trust Hub4mo

    This skill provides a mechanism for generating approved person names from a local fixture file. While it involves local file access and shell command execution, these actions are scoped to the project environment and are used for the intended purpose of maintaining documentation and test data consistency.

  • Socket4mo

    No alerts

  • Snyk4mo

    Risk: LOW · No issues

Signed by skilld at 7bf7acb. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Activeupdated 6 months ago

README badge

README badge for microsoft/ontology-playground/name-generator