NVIDIA/SkillEvaluatorPublic

Multi-tier framework for evaluating AI agent skills and plugins with quality gates, security scanning, harness compatibility checks, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior. Ships reusable CI templates that bring every check to any repository.

AI summary: Multi‑tier framework that validates AI agent skills and quantifies their effect on task performance

Stars
4K
+315 today
Forks
534
Watchers
8
Open issues
7
Open PRs
10
Contributors
~33
Commits
600
Branches
37
Views (30d)
4

PythonApache-2.0Created Jun 24, 2026Last push 1d agoLatest release v0.9.0+1.4K stars this week+1.4K this month

Quick answers

What is SkillEvaluator?
Multi‑tier framework that validates AI agent skills and quantifies their effect on task performance
What does SkillEvaluator do?
SkillEvaluator addresses the lack of systematic quality and impact assessment for AI agent skills defined by the Agent Skills specification. It implements a three‑tier pipeline—static validation, semantic deduplication, and live agent evaluation—each optional and runnable via a single CLI. Tier 1 runs safety and format checks using SkillSpector, Gitleaks, and optional Semgrep without requiring an LLM. Tier 2 computes embedding‑based overlap to detect redundant guidance across a catalog of skills. Tier 3 executes the skill in a sandboxed agent (Harbor) and measures performance changes, optionally using NVIDIA Build LLMs for rubric scoring. The framework produces deterministic JSON or CLI reports and can be integrated in CI or invoked programmatically.
Who is SkillEvaluator for?
SkillEvaluator is aimed at AI agent developers, skill marketplace curators, and CI engineers who need automated quality and impact testing of Agent Skills. Users should be comfortable with Python, command‑line tools, and optionally have access to NVIDIA Build API keys for LLM‑backed rubrics.
How do I get started with SkillEvaluator?
pip install skillevaluator
How popular is SkillEvaluator on GitHub?
NVIDIA/SkillEvaluator has 4,015 stars and 534 forks on GitHub, and gained 1,413 stars in the last 7 days.
What license does SkillEvaluator use?
NVIDIA/SkillEvaluator is released under the Apache-2.0 license.

Star history

since Nov 16, 2026
02K4KNov 2026Nov 2026Nov 2026Nov 2026
4K stars as of Nov 19, 2026. Measured daily since Nov 16, 2026; GitHub no longer exposes earlier star timestamps.

Update history

2 recorded
  • Nov 19, 2026Description changed from "Multi-tier framework for evaluating AI agent skills and plugins with quality gates, semantic overlap detection, syntheti" to "Multi-tier framework for evaluating AI agent skills and plugins with quality gates, security scanning, harness compatibi".
  • Nov 16, 2026Description changed from "Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation" to "Multi-tier framework for evaluating AI agent skills and plugins with quality gates, semantic overlap detection, syntheti".

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-23: 0 commits2025-11-24: 0 commits2025-11-25: 0 commits2025-11-26: 0 commits2025-11-27: 0 commits2025-11-28: 0 commits2025-11-29: 0 commits2025-11-30: 0 commits2025-12-01: 0 commits2025-12-02: 0 commits2025-12-03: 0 commits2025-12-04: 0 commits2025-12-05: 0 commits2025-12-06: 0 commits2025-12-07: 0 commits2025-12-08: 0 commits2025-12-09: 0 commits2025-12-10: 0 commits2025-12-11: 0 commits2025-12-12: 0 commits2025-12-13: 0 commits2025-12-14: 0 commits2025-12-15: 0 commits2025-12-16: 0 commits2025-12-17: 0 commits2025-12-18: 0 commits2025-12-19: 0 commits2025-12-20: 0 commits2025-12-21: 0 commits2025-12-22: 0 commits2025-12-23: 0 commits2025-12-24: 0 commits2025-12-25: 0 commits2025-12-26: 0 commits2025-12-27: 0 commits2025-12-28: 0 commits2025-12-29: 0 commits2025-12-30: 0 commits2025-12-31: 0 commits2026-01-01: 0 commits2026-01-02: 0 commits2026-01-03: 0 commits2026-01-04: 0 commits2026-01-05: 0 commits2026-01-06: 0 commits2026-01-07: 0 commits2026-01-08: 0 commits2026-01-09: 0 commits2026-01-10: 0 commits2026-01-11: 0 commits2026-01-12: 0 commits2026-01-13: 0 commits2026-01-14: 0 commits2026-01-15: 0 commits2026-01-16: 0 commits2026-01-17: 0 commits2026-01-18: 0 commits2026-01-19: 0 commits2026-01-20: 0 commits2026-01-21: 0 commits2026-01-22: 0 commits2026-01-23: 0 commits2026-01-24: 0 commits2026-01-25: 0 commits2026-01-26: 0 commits2026-01-27: 0 commits2026-01-28: 0 commits2026-01-29: 0 commits2026-01-30: 0 commits2026-01-31: 0 commits2026-02-01: 0 commits2026-02-02: 0 commits2026-02-03: 0 commits2026-02-04: 0 commits2026-02-05: 0 commits2026-02-06: 0 commits2026-02-07: 0 commits2026-02-08: 0 commits2026-02-09: 0 commits2026-02-10: 0 commits2026-02-11: 0 commits2026-02-12: 0 commits2026-02-13: 0 commits2026-02-14: 0 commits2026-02-15: 0 commits2026-02-16: 0 commits2026-02-17: 0 commits2026-02-18: 0 commits2026-02-19: 0 commits2026-02-20: 0 commits2026-02-21: 0 commits2026-02-22: 0 commits2026-02-23: 0 commits2026-02-24: 0 commits2026-02-25: 0 commits2026-02-26: 0 commits2026-02-27: 0 commits2026-02-28: 0 commits2026-03-01: 0 commits2026-03-02: 0 commits2026-03-03: 0 commits2026-03-04: 0 commits2026-03-05: 0 commits2026-03-06: 0 commits2026-03-07: 0 commits2026-03-08: 0 commits2026-03-09: 0 commits2026-03-10: 0 commits2026-03-11: 0 commits2026-03-12: 0 commits2026-03-13: 0 commits2026-03-14: 0 commits2026-03-15: 0 commits2026-03-16: 0 commits2026-03-17: 0 commits2026-03-18: 0 commits2026-03-19: 0 commits2026-03-20: 0 commits2026-03-21: 0 commits2026-03-22: 0 commits2026-03-23: 0 commits2026-03-24: 0 commits2026-03-25: 0 commits2026-03-26: 0 commits2026-03-27: 0 commits2026-03-28: 0 commits2026-03-29: 0 commits2026-03-30: 0 commits2026-03-31: 0 commits2026-04-01: 0 commits2026-04-02: 0 commits2026-04-03: 0 commits2026-04-04: 0 commits2026-04-05: 0 commits2026-04-06: 0 commits2026-04-07: 0 commits2026-04-08: 0 commits2026-04-09: 0 commits2026-04-10: 0 commits2026-04-11: 0 commits2026-04-12: 0 commits2026-04-13: 0 commits2026-04-14: 0 commits2026-04-15: 0 commits2026-04-16: 0 commits2026-04-17: 0 commits2026-04-18: 0 commits2026-04-19: 0 commits2026-04-20: 0 commits2026-04-21: 0 commits2026-04-22: 0 commits2026-04-23: 0 commits2026-04-24: 0 commits2026-04-25: 0 commits2026-04-26: 0 commits2026-04-27: 0 commits2026-04-28: 0 commits2026-04-29: 0 commits2026-04-30: 0 commits2026-05-01: 0 commits2026-05-02: 0 commits2026-05-03: 0 commits2026-05-04: 0 commits2026-05-05: 0 commits2026-05-06: 0 commits2026-05-07: 0 commits2026-05-08: 0 commits2026-05-09: 0 commits2026-05-10: 0 commits2026-05-11: 0 commits2026-05-12: 0 commits2026-05-13: 0 commits2026-05-14: 0 commits2026-05-15: 0 commits2026-05-16: 0 commits2026-05-17: 0 commits2026-05-18: 0 commits2026-05-19: 0 commits2026-05-20: 0 commits2026-05-21: 0 commits2026-05-22: 0 commits2026-05-23: 0 commits2026-05-24: 0 commits2026-05-25: 0 commits2026-05-26: 0 commits2026-05-27: 0 commits2026-05-28: 0 commits2026-05-29: 0 commits2026-05-30: 0 commits2026-05-31: 0 commits2026-06-01: 0 commits2026-06-02: 0 commits2026-06-03: 0 commits2026-06-04: 0 commits2026-06-05: 0 commits2026-06-06: 0 commits2026-06-07: 0 commits2026-06-08: 0 commits2026-06-09: 0 commits2026-06-10: 0 commits2026-06-11: 0 commits2026-06-12: 0 commits2026-06-13: 0 commits2026-06-14: 0 commits2026-06-15: 0 commits2026-06-16: 0 commits2026-06-17: 0 commits2026-06-18: 0 commits2026-06-19: 0 commits2026-06-20: 0 commits2026-06-21: 0 commits2026-06-22: 0 commits2026-06-23: 0 commits2026-06-24: 0 commits2026-06-25: 0 commits2026-06-26: 0 commits2026-06-27: 0 commits2026-06-28: 0 commits2026-06-29: 0 commits2026-06-30: 0 commits2026-07-01: 0 commits2026-07-02: 0 commits2026-07-03: 0 commits2026-07-04: 0 commits2026-07-05: 0 commits2026-07-06: 0 commits2026-07-07: 0 commits2026-07-08: 0 commits2026-07-09: 0 commits2026-07-10: 0 commits2026-07-11: 0 commits2026-07-12: 0 commits2026-07-13: 0 commits2026-07-14: 0 commits2026-07-15: 0 commits2026-07-16: 0 commits2026-07-17: 0 commits2026-07-18: 0 commits2026-07-19: 0 commits2026-07-20: 0 commits2026-07-21: 0 commits2026-07-22: 0 commits2026-07-23: 0 commits2026-07-24: 0 commits2026-07-25: 1 commit2026-07-26: 1 commit2026-07-27: 0 commits2026-07-28: 0 commits2026-07-29: 0 commits2026-07-30: 0 commits2026-07-31: 2 commits2026-08-01: 0 commits2026-08-02: 0 commits2026-08-03: 0 commits2026-08-04: 11 commits2026-08-05: 3 commits2026-08-06: 14 commits2026-08-07: 0 commits2026-08-08: 0 commits2026-08-09: 0 commits2026-08-10: 0 commits2026-08-11: 0 commits2026-08-12: 8 commits2026-08-13: 0 commits2026-08-14: 1 commit2026-08-15: 0 commits2026-08-16: 0 commits2026-08-17: 0 commits2026-08-18: 5 commits2026-08-19: 2 commits2026-08-20: 8 commits2026-08-21: 3 commits2026-08-22: 0 commits2026-08-23: 0 commits2026-08-24: 2 commits2026-08-25: 4 commits2026-08-26: 1 commit2026-08-27: 1 commit2026-08-28: 3 commits2026-08-29: 0 commits2026-08-30: 3 commits2026-08-31: 2 commits2026-09-01: 3 commits2026-09-02: 0 commits2026-09-03: 2 commits2026-09-04: 0 commits2026-09-05: 0 commits2026-09-06: 0 commits2026-09-07: 0 commits2026-09-08: 3 commits2026-09-09: 0 commits2026-09-10: 1 commit2026-09-11: 1 commit2026-09-12: 1 commit2026-09-13: 1 commit2026-09-14: 0 commits2026-09-15: 2 commits2026-09-16: 2 commits2026-09-17: 4 commits2026-09-18: 0 commits2026-09-19: 0 commits2026-09-20: 3 commits2026-09-21: 0 commits2026-09-22: 0 commits2026-09-23: 1 commit2026-09-24: 1 commit2026-09-25: 2 commits2026-09-26: 4 commits2026-09-27: 0 commits2026-09-28: 2 commits2026-09-29: 0 commits2026-09-30: 8 commits2026-10-01: 1 commit2026-10-02: 1 commit2026-10-03: 0 commits2026-10-04: 2 commits2026-10-05: 4 commits2026-10-06: 3 commits2026-10-07: 0 commits2026-10-08: 2 commits2026-10-09: 3 commits2026-10-10: 1 commit2026-10-11: 1 commit2026-10-12: 1 commit2026-10-13: 5 commits2026-10-14: 3 commits2026-10-15: 1 commit2026-10-16: 5 commits2026-10-17: 0 commits2026-10-18: 2 commits2026-10-19: 6 commits2026-10-20: 3 commits2026-10-21: 4 commits2026-10-22: 2 commits2026-10-23: 0 commits2026-10-24: 0 commits2026-10-25: 2 commits2026-10-26: 1 commit2026-10-27: 1 commit2026-10-28: 6 commits2026-10-29: 20 commits2026-10-30: 8 commits2026-10-31: 0 commits2026-11-01: 7 commits2026-11-02: 24 commits2026-11-03: 12 commits2026-11-04: 8 commits2026-11-05: 26 commits2026-11-06: 14 commits2026-11-07: 1 commit2026-11-08: 1 commit2026-11-09: 25 commits2026-11-10: 20 commits2026-11-11: 2 commits2026-11-12: 31 commits2026-11-13: 82 commits2026-11-14: 42 commits2026-11-15: 9 commits2026-11-16: 53 commits2026-11-17: 0 commits2026-11-18: 0 commits2026-11-19: 0 commits2026-11-20: 0 commits2026-11-21: 0 commits
561 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Rising fast

    +1,413 stars this week

  • Very active

    561 commits in 52 weeks

  • Well documented

    High community health score

  • Permissive license

    Apache-2.0

  • Continuous integration

    Automated checks passing

  • Repeat trending

    4 trending appearances

What SkillEvaluator does

SkillEvaluator addresses the lack of systematic quality and impact assessment for AI agent skills defined by the Agent Skills specification. It implements a three‑tier pipeline—static validation, semantic deduplication, and live agent evaluation—each optional and runnable via a single CLI. Tier 1 runs safety and format checks using SkillSpector, Gitleaks, and optional Semgrep without requiring an LLM. Tier 2 computes embedding‑based overlap to detect redundant guidance across a catalog of skills. Tier 3 executes the skill in a sandboxed agent (Harbor) and measures performance changes, optionally using NVIDIA Build LLMs for rubric scoring. The framework produces deterministic JSON or CLI reports and can be integrated in CI or invoked programmatically.

SkillEvaluator is aimed at AI agent developers, skill marketplace curators, and CI engineers who need automated quality and impact testing of Agent Skills. Users should be comfortable with Python, command‑line tools, and optionally have access to NVIDIA Build API keys for LLM‑backed rubrics.

  • Tier‑1 validation: Performs safety, format, and harness compatibility checks with SkillSpector and Gitleaks without an LLM.
  • Tier‑2 deduplication: Uses embedding models to detect semantic overlap between a skill and a catalog, flagging redundant guidance.
  • Tier‑3 live evaluation: Runs the skill in a sandboxed agent environment and reports impact on task success metrics.
  • CLI integration: Single command interface supports pip, uv, and CI workflows, producing JSON and human‑readable outputs.
  • Provider flexibility: Works keyless or with NVIDIA Build, allowing LLM‑backed rubric scoring via environment variables.

Where teams use it

CI quality gate for skill repositories

Teams can add `skillevaluator ci init` to their GitHub pipelines to automatically reject skills that fail static safety or format checks before merge.

Skill marketplace curation

Marketplace operators run the full three‑tier pipeline to ensure submitted skills are non‑redundant and demonstrably improve agent performance, providing a quantitative grade.

Research benchmarking of agent capabilities

Researchers generate synthetic evaluation datasets with `tier3 create-eval-dataset` and compare how different skill sets affect benchmark tasks.

Secure plugin development

Developers of agent plugins use Tier 1 scans to catch insecure code patterns and missing license headers early in the development cycle.

Custom agent integration

Deployers add the skill to Claude Code or Codex via `npx skills add` and let the agent query SkillEvaluator to decide whether to use the skill at runtime.

Getting started: pip install skillevaluator

README

main branch

SkillEvaluator

SkillEvaluator wordmark

License Python PyPI Documentation Paper NVIDIA Developer Blog

📺 Livestream: Ask the Experts: Evaluating Agent Skills

SkillEvaluator checks AI agent skills and measures their effect on task results: start with quality checks, then compare runs with and without a skill.

Agent skills are folders of instructions and supporting files defined by the Agent Skills specification. SkillEvaluator is part of the NVIDIA Verified Skills pipeline.

Get started

Three ways in, one CLI, same results.

1. Run the CLI directly 2. Add it to your repo via CI 3. Wire it to your agent

Install with pip:

pip install skillevaluator
Or install with uv
uv tool install \
  skillevaluator

Then check your skill, no API key:

skillevaluator validate \
  ./my-skill --tiers 1

Other tiers: installation guide.

Run this in your GitHub repository. It opens a setup PR:

skillevaluator ci init

GitLab and details: repository guide.

Add the skill to Claude Code, Codex or another agent:

npx skills add \
  NVIDIA/SkillEvaluator

Then ask: "Is my skill any good?" It runs the CLI from step 1. See the agent guide.

Quickstart

Both paths use bundled text-analyzer.

Start here Requires First result
Run without an LLM Git and uv A deterministic quality score and findings
Use NVIDIA Build Git, uv, and a Build API key Model-backed rubric scores and feedback

Install uv and Git, then get the example:

git clone --depth 1 https://github.com/NVIDIA/SkillEvaluator.git
cd SkillEvaluator

uv provisions Python 3.13 and dependencies. For standalone installation, see Installation.

Run without an LLM

uv run --python 3.13 skillevaluator quality-check \
  src/skillevaluator/tier3/reference_skills/text-analyzer \
  -r cli -r json -o reports/first-quality

No API key, scanner, GPU or Docker is needed. The example scores 88.8/100 (B), exits 0 and saves reports/first-quality/skillevaluator-quality.json. The passing threshold defaults to 70.

This checks static quality; publication evidence stays INCOMPLETE. Security needs scanners; agent impact needs live evaluation. Replace the example path with your skill directory. See the keyless walkthrough.

Use NVIDIA Build

Eligible NVIDIA Developer Program members can use NVIDIA-hosted endpoints for free prototyping, subject to access terms and rate limits.

  1. Sign in at build.nvidia.com and complete enrollment.
  2. Open a model page, select Get API Key, and generate your key.
  3. Set the provider and key in the same terminal, then run the rubric check:
export SKILL_EVAL_LLM_PROVIDER=nv_build
export NVIDIA_API_KEY='nvapi-...'
uv run --python 3.13 --extra llm skillevaluator rubric-eval \
  src/skillevaluator/tier3/reference_skills/text-analyzer \
  -r cli -r json -o reports/first-build

The command sends skill documentation to the model and saves feedback in reports/first-build/skillevaluator-rubric.json. No agent runtime or Docker is needed. Completed evaluations can still fail rubric thresholds.

The same key supports Tier 2 embeddings and supported Tier 3 agents. See the Build walkthrough or provider configuration.

Three-tier overview

SkillEvaluator three-tier pipeline: Skill → Tier 1 Validation → Tier 2 Deduplication → Tier 3 Live Evaluation → Reports

Each tier is independent. Add its extra to your command:

Tier Question Example after setup Additional setup
Tier 1: Validation Is the skill safe, well-formed and harness-compatible? uv run skillevaluator tier1 ./my-skill --no-llm External scanners for full static coverage; a provider and model clients enable LLM checks
Tier 2: Deduplication Does guidance repeat or overlap? uv run --extra tier2 skillevaluator tier2 ./my-skill Embeddings and chat; add --catalog ./skill-catalog.json for inter-skill comparison
Tier 3: Live Evaluation Does the skill help the agent? uv run --extra tier3 skillevaluator tier3 ./my-skill Provider access, a supported agent, and a running sandbox (Docker by default)

Tier 1 fetches pinned, verified SkillSpector and Gitleaks releases when they are missing; Semgrep is optional. See scanners. --no-llm does not remove scanner requirements; a scanner that cannot run is INCOMPLETE and exits nonzero. SkillSpector provides specialized skill security scanning; Harbor, the open-source agent evaluation framework, powers sandboxed agent runs.

Tier 2 reports when inter-skill comparison did not run. Tier 3 autopilot reuses sources or creates one skill-grounded case with limited coverage. See tier guides.

Run the combined pipeline

After setting up the provider, scanners, and agent sandbox, run all three tiers:

uv run --python 3.13 --extra all skillevaluator doctor --env-mode docker
uv run --python 3.13 --extra all skillevaluator validate ./my-skill

doctor checks readiness, not inference success. validate runs all tiers with autopilot for skills. Use --tiers 1,2 to skip live evaluation or --tiers 1 for static checks. --no-autopilot requires an existing source. Other artifact types retain their applicable stages.

Tier 1 gates validate. Tier 2 gates unless --no-block-on-dedup is set; Tier 3 gates only with --block-on-agent-eval. Model and managed-sandbox usage can incur charges; see runtime and cost.

Standalone generation needs substantive evals/EVAL.md guidance, a --prompt file with task requests and outcomes, or matching retained traces. --force below replaces the autopilot starter; --refine refines it. Explicit --grounding skill permits skill-only starters. Review cases; templates omit unauthored negatives.

uv run --python 3.13 --extra tier3 skillevaluator tier3 create-eval-dataset ./my-skill --full --prompt eval-guidance.md --force

Run from a source checkout

Use uv run --python 3.13 with the relevant extra. See Installation for extras and standalone upgrades.

Research and citation

Resources: paper, PDF, DOI, BibTeX, and the NVIDIA Developer blog. Cite the paper and record the SkillEvaluator release or commit; see CITATION.cff.

Documentation

See the documentation for setup, tier guides, reports, CI integration, CLI reference, and performance dashboard.

Installation and third-party software

Follow the installation guide to choose the full installation or a smaller per-tier setup.

This project will download and install additional third-party open source software projects. Review the license terms of these open source projects before use.

Contributing

Read CONTRIBUTING.md and run:

make lint && make test && make build

See project governance and the Code of Conduct.

Support

Support level: Experimental. Community-supported, best-effort, with no SLA or NVIDIA enterprise support entitlement. Report bugs and feature requests through GitHub Issues; see SUPPORT.md.

Security

Report suspected vulnerabilities using the private process in SECURITY.md. Do not disclose security issues in a public GitHub issue.

Releases

Release changes are recorded in CHANGELOG.md and GitHub Releases.

License

Apache License 2.0 — see LICENSE, NOTICE, and THIRD_PARTY_NOTICES.md.

Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.

View on GitHub

Recent activity

commits and pull requests

Releases and announcements

11 total
  1. SkillEvaluator 0.9.0v0.9.0Nov 13, 202682 downloads

    # SkillEvaluator 0.9.0 SkillEvaluator 0.9.0 expands how you build evaluation datasets, compare skill versions, and understand why an agent passed or failed. It adds controls for evaluation budgets, reusable baselines, and clearer evidence across terminal, HTML, JSON, Markdown, and benchmark reports. For PyPI users upgrading from 0.7.2, this release also includes the changes shipped in the GitHub-only 0.8.0 release. ## Highlights - **Build and review better evaluation datasets.** Declare deterministic checks for script execution, workspace files, and final responses. Generate datasets grounded in skill instructions, author intent, or traces; import production traces as redacted review candidates; and promote expectations only after explicit human review. Preview legacy dataset migrations before writing a new file. - **Track skill improvements over time.** Compare retained skill versions with `--compare-to` and `compare-versions`, browse run history, and reuse a compatible no-skill baseline with `--reuse-baseline`. Version comparisons remain separate from Skill Lift against a no-skill baseline. - **Control evaluation spending.** Set token, judge-call, attempt, and priced-cost bud

  2. SkillEvaluator v0.8.0v0.8.0Nov 6, 202688 downloads

    # SkillEvaluator 0.8.0 Tier 3 now computes every score from judge verdicts, grades accuracy on the outcome alone, and explains failing scores in the HTML report. A new `tier3 feedback` chat answers questions about a completed run, and opt-in policies control which models a judge may fall back to. Reports give every finding stable IDs. Tier 1 accepts audited SkillSpector baselines and evidence-bound PII waivers. This release also ships a rebuilt Tier 1 scanner image and CI bundle. ```bash pip install --upgrade skillevaluator skillevaluator ci init ``` [PyPI package](https://pypi.org/project/skillevaluator/0.8.0/) · [CLI onboarding guide](https://docs.nvidia.com/skills/skillevaluator/cli-onboarding) · [Ready-to-use CI templates](https://github.com/NVIDIA/SkillEvaluator/tree/v0.8.0/ci/bundles/0.8.0) ## Before you upgrade - **The shared validation policy is now `default`** ([#334](https://github.com/NVIDIA/SkillEvaluator/pull/334)). The shared OSS policy for public and private repositories was called `external`. `--profile external`, `--external`, and `SKILLEVALUATOR_PROFILE=external` still work, with the same rules. Report policy metadata and the policy digest change

  3. SkillEvaluator v0.7.2v0.7.2Nov 4, 202637 downloads

    # SkillEvaluator 0.7.2 Add hosted reports to an existing GitHub skill-checks workflow while keeping its shared component, folders, thresholds, and triggers. A centrally maintained component such as `@v3` can now update its pinned evaluator without requiring an edit in every consumer repository. Each report retains the signed evaluator identity and resolved workflow revisions. ```bash pip install --upgrade skillevaluator skillevaluator ci init ``` [PyPI package](https://pypi.org/project/skillevaluator/0.7.2/) · [CLI onboarding guide](https://docs.nvidia.com/skills/skillevaluator/cli-onboarding) · [Ready-to-use CI templates](https://github.com/NVIDIA/SkillEvaluator/tree/v0.7.2/ci/bundles/0.7.2) ## GitHub onboarding and reporting - Preserve an existing supported scan workflow while adding hosted HTML and one updated PR comment. Direct evaluator calls and shared-component calls are supported. - Verify the shared component's identity permission before changing repository settings. Existing Actions restrictions, unrelated Pages sites, and deployment approvals remain protected. - Reuse an administrator-configured private Pages site in eligible GitHub Enterprise Cloud organization rep

  4. SkillEvaluator v0.7.1v0.7.1Nov 3, 202634 downloads

    SkillEvaluator 0.7.1 packages guided GitHub onboarding, improves CI report feedback, and includes scanner and evaluation runtime fixes. ## Highlights - Set up repository checks with `skillevaluator ci init`; use `ci status` to inspect setup and `ci demo` to open an optional test PR. - Check changed skills with Tier 1 quality checks and SkillSpector security scanning. Optional GitHub feedback includes hosted HTML reports and one updated PR comment. - Improve scanner setup, local agent installation, Tier 3 progress and results, and provider readiness checks. See the changes below. ## Python package **[SkillEvaluator 0.7.1 on PyPI](https://pypi.org/project/skillevaluator/0.7.1/)** · [NVIDIA Python package index](https://pypi.nvidia.com/skillevaluator/) Requires Python 3.12, 3.13 or 3.14. Install or upgrade: ```bash pip install --upgrade skillevaluator ``` Both the wheel and source distribution are published on PyPI and NVIDIA's index. Package files and SHA-256 checksums are attached below. ## CI integration From your cloned GitHub repository, run: ```bash skillevaluator ci init ``` The wizard prepares a setup PR for review. Automatic setup requires an existing GitHub CLI lo

  5. SkillEvaluator v0.7.00.7.0Nov 2, 202618 downloads

    # SkillEvaluator 0.7.0 SkillEvaluator 0.7.0 adds Python 3.14 support alongside Python 3.12 and 3.13, reusable Tier 1 CI integration, configurable quality policies, and clearer evaluation reports. ## Highlights - Python 3.14 support, with full-suite CI and built-package installation checks across Python 3.12, 3.13, and 3.14. - Reusable GitHub Actions and GitLab CI checks, parallel skill scanning, and configurable quality headings and thresholds. - Verdict-led HTML reports, case-first Tier 3 summaries, matching-judge comparisons, and actionable recommendations in `what_to_fix.json`. - More precise Tier 2 completeness reporting, Tier 3 timeout/recovery and local-mode fixes, and an optional `--max-cases` limit for exploratory runs. - SkillSpector 2.13.3 installation and CI pins, preserved NVIDIA Build model-registry handling, and validated LLM provenance in JSON/HTML reports. - Refreshed locked runtime and dashboard dependencies. The Python package's dependency ranges are unchanged. ## Python package **PyPI publication: published and verified.** Both the wheel and source distribution are available on PyPI and NVIDIA’s Python package index. Their downloaded SHA-256 hashes match the

Code frequency

additions and deletions
+151.7K-151.7KWeek of 2026-07-19: +644 linesWeek of 2026-07-19: -53 linesWeek of 2026-07-26: +128,588 linesWeek of 2026-07-26: -2,258 linesWeek of 2026-08-02: +21,448 linesWeek of 2026-08-02: -2,326 linesWeek of 2026-08-09: +191 linesWeek of 2026-08-09: -59 linesWeek of 2026-08-16: +14,722 linesWeek of 2026-08-16: -2,225 linesWeek of 2026-08-23: +64,052 linesWeek of 2026-08-23: -5,997 linesWeek of 2026-08-30: +4,999 linesWeek of 2026-08-30: -327 linesWeek of 2026-09-06: +5,174 linesWeek of 2026-09-06: -237 linesWeek of 2026-09-13: +5,256 linesWeek of 2026-09-13: -175 linesWeek of 2026-09-20: +7,485 linesWeek of 2026-09-20: -1,451 linesWeek of 2026-09-27: +21,318 linesWeek of 2026-09-27: -1,188 linesWeek of 2026-10-04: +21,240 linesWeek of 2026-10-04: -4,425 linesWeek of 2026-10-11: +17,731 linesWeek of 2026-10-11: -2,749 linesWeek of 2026-10-18: +7,921 linesWeek of 2026-10-18: -908 linesWeek of 2026-10-25: +79,775 linesWeek of 2026-10-25: -15,133 linesWeek of 2026-11-01: +96,754 linesWeek of 2026-11-01: -4,848 linesWeek of 2026-11-08: +151,718 linesWeek of 2026-11-08: -5,945 linesWeek of 2026-11-15: +5,187 linesWeek of 2026-11-15: -615 linesJul 19, 2026Nov 15, 2026
+654.2K lines added, -50.9K removed over the last year.

Commits per week

last 52 weeks
2030Week of 2025-11-23: 0 commitsWeek of 2025-11-30: 0 commitsWeek of 2025-12-07: 0 commitsWeek of 2025-12-14: 0 commitsWeek of 2025-12-21: 0 commitsWeek of 2025-12-28: 0 commitsWeek of 2026-01-04: 0 commitsWeek of 2026-01-11: 0 commitsWeek of 2026-01-18: 0 commitsWeek of 2026-01-25: 0 commitsWeek of 2026-02-01: 0 commitsWeek of 2026-02-08: 0 commitsWeek of 2026-02-15: 0 commitsWeek of 2026-02-22: 0 commitsWeek of 2026-03-01: 0 commitsWeek of 2026-03-08: 0 commitsWeek of 2026-03-15: 0 commitsWeek of 2026-03-22: 0 commitsWeek of 2026-03-29: 0 commitsWeek of 2026-04-05: 0 commitsWeek of 2026-04-12: 0 commitsWeek of 2026-04-19: 0 commitsWeek of 2026-04-26: 0 commitsWeek of 2026-05-03: 0 commitsWeek of 2026-05-10: 0 commitsWeek of 2026-05-17: 0 commitsWeek of 2026-05-24: 0 commitsWeek of 2026-05-31: 0 commitsWeek of 2026-06-07: 0 commitsWeek of 2026-06-14: 0 commitsWeek of 2026-06-21: 0 commitsWeek of 2026-06-28: 0 commitsWeek of 2026-07-05: 0 commitsWeek of 2026-07-12: 0 commitsWeek of 2026-07-19: 1 commitsWeek of 2026-07-26: 3 commitsWeek of 2026-08-02: 28 commitsWeek of 2026-08-09: 9 commitsWeek of 2026-08-16: 18 commitsWeek of 2026-08-23: 11 commitsWeek of 2026-08-30: 10 commitsWeek of 2026-09-06: 6 commitsWeek of 2026-09-13: 9 commitsWeek of 2026-09-20: 11 commitsWeek of 2026-09-27: 12 commitsWeek of 2026-10-04: 15 commitsWeek of 2026-10-11: 16 commitsWeek of 2026-10-18: 17 commitsWeek of 2026-10-25: 38 commitsWeek of 2026-11-01: 92 commitsWeek of 2026-11-08: 203 commitsWeek of 2026-11-15: 62 commitsNov 23, 2025Nov 15, 2026
561 commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 0 commitsSun 1:00 — 0 commitsSun 2:00 — 0 commitsSun 3:00 — 2 commitsSun 4:00 — 2 commitsSun 5:00 — 1 commitsSun 6:00 — 0 commitsSun 7:00 — 0 commitsSun 8:00 — 1 commitsSun 9:00 — 0 commitsSun 10:00 — 0 commitsSun 11:00 — 0 commitsSun 12:00 — 1 commitsSun 13:00 — 1 commitsSun 14:00 — 2 commitsSun 15:00 — 1 commitsSun 16:00 — 1 commitsSun 17:00 — 1 commitsSun 18:00 — 1 commitsSun 19:00 — 1 commitsSun 20:00 — 0 commitsSun 21:00 — 5 commitsSun 22:00 — 2 commitsSun 23:00 — 10 commitsMon 0:00 — 7 commitsMon 1:00 — 7 commitsMon 2:00 — 12 commitsMon 3:00 — 13 commitsMon 4:00 — 13 commitsMon 5:00 — 5 commitsMon 6:00 — 2 commitsMon 7:00 — 1 commitsMon 8:00 — 0 commitsMon 9:00 — 1 commitsMon 10:00 — 3 commitsMon 11:00 — 6 commitsMon 12:00 — 8 commitsMon 13:00 — 6 commitsMon 14:00 — 6 commitsMon 15:00 — 2 commitsMon 16:00 — 2 commitsMon 17:00 — 1 commitsMon 18:00 — 1 commitsMon 19:00 — 6 commitsMon 20:00 — 9 commitsMon 21:00 — 3 commitsMon 22:00 — 2 commitsMon 23:00 — 4 commitsTue 0:00 — 4 commitsTue 1:00 — 5 commitsTue 2:00 — 5 commitsTue 3:00 — 4 commitsTue 4:00 — 2 commitsTue 5:00 — 2 commitsTue 6:00 — 2 commitsTue 7:00 — 3 commitsTue 8:00 — 1 commitsTue 9:00 — 3 commitsTue 10:00 — 4 commitsTue 11:00 — 4 commitsTue 12:00 — 10 commitsTue 13:00 — 1 commitsTue 14:00 — 0 commitsTue 15:00 — 6 commitsTue 16:00 — 4 commitsTue 17:00 — 2 commitsTue 18:00 — 1 commitsTue 19:00 — 3 commitsTue 20:00 — 2 commitsTue 21:00 — 2 commitsTue 22:00 — 2 commitsTue 23:00 — 0 commitsWed 0:00 — 2 commitsWed 1:00 — 3 commitsWed 2:00 — 4 commitsWed 3:00 — 2 commitsWed 4:00 — 2 commitsWed 5:00 — 2 commitsWed 6:00 — 1 commitsWed 7:00 — 0 commitsWed 8:00 — 1 commitsWed 9:00 — 3 commitsWed 10:00 — 4 commitsWed 11:00 — 6 commitsWed 12:00 — 2 commitsWed 13:00 — 1 commitsWed 14:00 — 0 commitsWed 15:00 — 6 commitsWed 16:00 — 3 commitsWed 17:00 — 2 commitsWed 18:00 — 0 commitsWed 19:00 — 1 commitsWed 20:00 — 1 commitsWed 21:00 — 0 commitsWed 22:00 — 1 commitsWed 23:00 — 1 commitsThu 0:00 — 2 commitsThu 1:00 — 1 commitsThu 2:00 — 7 commitsThu 3:00 — 0 commitsThu 4:00 — 0 commitsThu 5:00 — 0 commitsThu 6:00 — 1 commitsThu 7:00 — 2 commitsThu 8:00 — 4 commitsThu 9:00 — 6 commitsThu 10:00 — 15 commitsThu 11:00 — 8 commitsThu 12:00 — 6 commitsThu 13:00 — 16 commitsThu 14:00 — 13 commitsThu 15:00 — 2 commitsThu 16:00 — 9 commitsThu 17:00 — 6 commitsThu 18:00 — 1 commitsThu 19:00 — 4 commitsThu 20:00 — 0 commitsThu 21:00 — 1 commitsThu 22:00 — 8 commitsThu 23:00 — 2 commitsFri 0:00 — 12 commitsFri 1:00 — 10 commitsFri 2:00 — 8 commitsFri 3:00 — 3 commitsFri 4:00 — 5 commitsFri 5:00 — 2 commitsFri 6:00 — 3 commitsFri 7:00 — 4 commitsFri 8:00 — 3 commitsFri 9:00 — 11 commitsFri 10:00 — 8 commitsFri 11:00 — 12 commitsFri 12:00 — 5 commitsFri 13:00 — 5 commitsFri 14:00 — 6 commitsFri 15:00 — 3 commitsFri 16:00 — 4 commitsFri 17:00 — 3 commitsFri 18:00 — 7 commitsFri 19:00 — 3 commitsFri 20:00 — 5 commitsFri 21:00 — 0 commitsFri 22:00 — 2 commitsFri 23:00 — 1 commitsSat 0:00 — 0 commitsSat 1:00 — 0 commitsSat 2:00 — 0 commitsSat 3:00 — 0 commitsSat 4:00 — 0 commitsSat 5:00 — 0 commitsSat 6:00 — 1 commitsSat 7:00 — 0 commitsSat 8:00 — 0 commitsSat 9:00 — 5 commitsSat 10:00 — 1 commitsSat 11:00 — 2 commitsSat 12:00 — 1 commitsSat 13:00 — 1 commitsSat 14:00 — 0 commitsSat 15:00 — 0 commitsSat 16:00 — 0 commitsSat 17:00 — 0 commitsSat 18:00 — 0 commitsSat 19:00 — 3 commitsSat 20:00 — 19 commitsSat 21:00 — 12 commitsSat 22:00 — 1 commitsSat 23:00 — 4 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.
DateListRankStars gained
Nov 19, 2026daily#5+869
Nov 18, 2026daily#5+869
Nov 17, 2026daily#9+953
Nov 16, 2026daily#9+953
  • public-apis/public-apis

    A collective list of free APIs

    500.5K stars · Python

  • morluto/rea

    Reverse engineer anything with agents, from app behavior down to native binaries.

    471.6K stars · TypeScript

  • donnemartin/system-design-primer

    Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

    378.7K stars · Python

  • obra/superpowers

    An agentic skills framework & software development methodology that works.

    322.9K stars · Shell

  • affaan-m/ECC

    The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

    307.9K stars · JavaScript

  • practical-tutorials/project-based-learning

    Curated list of project-based tutorials

    290.1K stars · Python