hr-skills: Command for Claude Code

.claude/commands/new-skill.md

new-skill is a command for Claude Code from tuanductran/hr-skills. It costs 19 tokens per session (3,094 once invoked), scanned A, original, MIT.

A command for scaffolding a new hr- skill package with a SKILL.md file, content, and examples directories. Scaffolding means creating the initial folder and file structure from templates.

In plain words
What is it for?
Use it to start a new kebab-case skill whose name begins with hr-, create its standard files and folders, and prepare an example scenario.
Why use it?
It removes repetitive setup work and enforces the required naming and package layout for new skills.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is tuanductran/hr-skills's own configuration. It tells Claude Code how to work on hr-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything hr-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tuanductran/hr-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tuanductran/hr-skills/main/.claude/commands/new-skill.md
Clone the repo
git clone --depth 1 https://github.com/tuanductran/hr-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for new-skill

README.md
[![agentmods](https://agentmods.dev/badge/commands/tuanductran/hr-skills/new-skill/github.svg)](https://agentmods.dev/commands/tuanductran/hr-skills/new-skill)
Your own site
<a href="https://agentmods.dev/commands/tuanductran/hr-skills/new-skill"><img src="https://agentmods.dev/badge/commands/tuanductran/hr-skills/new-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for new-skill

Your own site · 80×15
<a href="https://agentmods.dev/commands/tuanductran/hr-skills/new-skill"><img src="https://agentmods.dev/badge/commands/tuanductran/hr-skills/new-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,094 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.03094
Opus 5 $0.00010 $0.01547
Sonnet 5 $0.00004 $0.00619
Haiku 4.5 $0.00002 $0.00309

Measured 10d ago against content hash 1ad78edbd604, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

new-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/new-skill.md · 475 lines

How it starts

The opening of the file, as written. The whole thing — 475 lines — stays where its author put it; the contents beside it link to each section on GitHub.

New skill

Ask the user for the skill name. It must start with hr- and use kebab-case only (for example hr-retention, hr-interviewing). If the name does not follow this format, prompt again.

Once you have a valid name, derive these values:

  • <full-name> — the full name the user provided (e.g. hr-retention)
  • <short-name> — the part after hr- (e.g. retention), used as the filename for the content doc (no hr- prefix)
  • <Title Case> — a human-readable title derived from <short-name> (e.g. Retention)

Then:

  1. Create the directory skills/<full-name>/
  2. Create skills/<full-name>/SKILL.md using the SKILL.md template below — replace every <full-name>, <short-name>, <Title Case>, and <placeholder> with appropriate content based on the skill name the user provided
  3. Create the directory skills/<full-name>/content/
  4. Create skills/<full-name>/content/<short-name>.md using the content template below
  5. Create the directory skills/<full-name>/examples/
  6. Ask the user for one realistic scenario name to scaffold the example around (e.g. "designing a retention plan for a startup"), derive <scenario-slug> from it in kebab-case, and create skills/<full-name>/examples/<scenario-slug>.md using the example template below
  7. Make sure the content file's "Example Workflow" section links to ../examples/<scenario-slug>.md and the example file may reference the content file via ../content/<short-name>.md if relevant
  8. Tell the user: "Skill scaffolded with SKILL.md, content/<short-name>.md, and examples/<scenario-slug>.md. Now edit the files to add real content, then run bun run sync followed by bun run validate."

Directory structure produced

skills/<full-name>/
├── SKILL.md
├── content/
│   └── <short-name>.md
└── examples/
    └── <scenario-slug>.md

SKILL.md template

Use this exact template for skills/<full-name>/SKILL.md (canonical source: .github/skill-template.md):

Read the full file on GitHub · 475 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 475 lines · 19 tokens per session scan A 1ad78edbd604

Subscribe to this mod's changes

new-skill is a command published in the GitHub repository tuanductran/hr-skills (56 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 3,094 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.