> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/skills/skillevaluator/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/skills/skillevaluator/_mcp/server.

# Quickstart

> Install SkillEvaluator and get your first skill evaluation result in about two minutes — no API key required.

Get your first evaluation result in about two minutes, with no API key. This page walks you from install to a scored skill, then adds a provider key to unlock the LLM-backed checks.

## Evaluate your first skill

### Install

One command installs the CLI with every Python feature. [uv](https://docs.astral.sh/uv/) provisions Python 3.13 automatically:

```bash title="Install with uv"
uv tool install --python 3.13 "skillevaluator[all] @ git+https://github.com/NVIDIA/SkillEvaluator.git"
```

Confirm the install:

```bash title="Verify"
skillevaluator --version
```

You should see `skillevaluator, version 0.1.0` (or newer).

If the shell can't find `skillevaluator`, run `uv tool update-shell` and open a new terminal — uv installs tools to `~/.local/bin`, which may not be on your PATH yet.

### Run the keyless quality check

Point SkillEvaluator at any skill directory (a folder with a `SKILL.md`):

```bash title="No API key required"
skillevaluator quality-check ./my-skill
```

You get a deterministic quality score from 0–100 and an A–F grade; the check passes at 70 (a C) or above by default.

### Run the complete offline Tier 1 validation

`validate` runs the full static and security check suite. The `[all]` install
above includes the Python scanners, but complete evidence also requires the
separate Semgrep, SkillSpector, and Gitleaks executables. Install all three,
and pass `--no-dedup` to skip the Tier 2 pass that needs an embeddings key:

```bash title="Complete offline Tier 1"
brew install semgrep gitleaks   # macOS
uv tool install git+https://github.com/NVIDIA/SkillSpector.git
skillevaluator validate ./my-skill --no-dedup
```

On other platforms, follow [Installation: System tools](/skills/skillevaluator/installation#system-tools)
for the Semgrep, SkillSpector, and Gitleaks setup. The terminal shows a
compact pipeline view, and HTML and JSON reports land in `reports/` — pass
`-r cli` explicitly for terminal-only output, or `--verbose` for the full
per-check detail stream. The command exits `0` only when every check passes
and every required scanner returns complete evidence. A failed check or
missing scanner evidence leaves the result `INCOMPLETE` and exits `1`. See
[Gate Your CI](/skills/skillevaluator/ci-integration) for the full recipe.

### Add an LLM provider

LLM-backed features — rubric judging, deeper security analysis, and Tier 2 deduplication — use whichever provider you configure. A free [NVIDIA API Catalog](https://build.nvidia.com/) key covers both LLM judging and embeddings with one variable:

```bash title="Configure a provider"
export SKILL_EVAL_LLM_PROVIDER=nv_build
export NVIDIA_API_KEY='nvapi-...'
```

If `SKILL_EVAL_LLM_PROVIDER` is unset and exactly one of `NVIDIA_API_KEY`, `OPENAI_API_KEY`, or `ANTHROPIC_API_KEY` is present, that provider is auto-selected; with more than one key set, you must name the provider explicitly. OpenAI, Anthropic, Bedrock, OpenAI-compatible endpoints, and fully local servers all work; see [Providers & Credentials](/skills/skillevaluator/configuration).

### Check for redundancy

With a provider configured, find repeated guidance inside your skill, or compare every skill in a collection for overlap:

```bash title="Tier 2 deduplication"
skillevaluator context-optimization-check ./my-skill   # inside one skill
skillevaluator similarity-check ./skills               # across a collection
```

Cross-skill matches are classified by similarity, from `EXACT_DUPLICATE` down to `LOOSELY_RELATED`; intra-skill duplicate findings include a suggested fix. See [Tier 2: Deduplication](/skills/skillevaluator/tier2-deduplication).

## Where to go next

| Your goal                            | Command            | Guide                                                                   | What success looks like                                                  |
| ------------------------------------ | ------------------ | ----------------------------------------------------------------------- | ------------------------------------------------------------------------ |
| Gate skill quality and security      | `validate`         | [Tier 1: Validation](/skills/skillevaluator/tier1-validation)           | Exit code `0`, no CRITICAL findings                                      |
| Find overlapping or duplicate skills | `similarity-check` | [Tier 2: Deduplication](/skills/skillevaluator/tier2-deduplication)     | No `EXACT_DUPLICATE` or `HIGH_SIMILARITY` findings                       |
| Prove the skill helps a real agent   | `tier3 evaluate`   | [Tier 3: Live Evaluation](/skills/skillevaluator/tier3-live-evaluation) | Positive Skill Lift across the five dimensions                           |
| Run all three tiers in one shot      | `validate --full`  | [Tier 3: Live Evaluation](/skills/skillevaluator/tier3-live-evaluation) | Exit code `0` plus an auto-generated dataset and advisory Tier 3 results |
| Block bad skills at merge time       | `validate` in CI   | [Gate Your CI](/skills/skillevaluator/ci-integration)                   | A red check on failing PRs                                               |
| Look up every flag and default       | —                  | [CLI Reference](/skills/skillevaluator/cli-reference)                   | —                                                                        |

## What each tier needs

Every tier is an independent entry point — nothing requires running the earlier tiers first.

| Tier                         | CLI only                                                  | Provider key                                                     | External scanners                                                  | Docker + agent CLI                                             |
| ---------------------------- | --------------------------------------------------------- | ---------------------------------------------------------------- | ------------------------------------------------------------------ | -------------------------------------------------------------- |
| **Tier 1** — validation      | All deterministic checks                                  | Only `rubric-eval` and the optional `--llm`/`--llm-verify` flags | Semgrep, SkillSpector, and Gitleaks for a complete security result | —                                                              |
| **Tier 2** — deduplication   | —                                                         | Embeddings; intra-skill analysis also needs a chat LLM           | —                                                                  | —                                                              |
| **Tier 3** — live evaluation | Keyless dataset templates (`--no-llm`) and report viewing | LLM dataset generation and grading                               | —                                                                  | Live runs need a sandbox plus the agent CLI and its credential |

Ready for the deeper install options — extras, pip, source, Docker? Head to [Installation](/skills/skillevaluator/installation).