Department of Business, Energy and Industrial Strategy
Official@ukgovernmentbeis · United Kingdom
Technical infrastructure for Linux system diagnostics, evaluation log auditing, and dataset schema validation within enterprise environments.
Agent Skills by Department of Business, Energy and Industrial Strategy
Showing 24 vetted skills indexed across 2 GitHub repositories.
UKGovernmentBEISeval-report-workflow
Generates reproducible LLM evaluation reports with model selection, cost estimation, and results tables.
UKGovernmentBEISgenerate-asset-actions
Classify external assets into priority tiers and generate asset-actions.yaml from ASSETS.yaml.
UKGovernmentBEIScheck-trajectories-workflow
Analyzes agent trajectories from evaluation logs using Inspect Scout scanners.
UKGovernmentBEISbuild-repo-context
Distills GitHub PRs, issues, and review comments into a repository knowledge base.
UKGovernmentBEISensure-test-coverage
Review and create pytest test coverage for Inspect AI evaluations.
UKGovernmentBEISeval-quality-workflow
Fix or review a single Inspect AI evaluation against EVALUATION_CHECKLIST.md standards.
UKGovernmentBEISeval-validity-review
Review an Inspect AI evaluation's claims, naming, dataset, and scoring validity.
UKGovernmentBEISci-maintenance-workflow
Diagnose and fix failing CI tests, smoke tests, and slow test markers in GitHub Actions workflows.
UKGovernmentBEISprepare-release
Prepares an inspect_evals release by collecting changelog fragments and opening a draft PR.
UKGovernmentBEISprepare-submission-workflow
Prepares an evaluation for register submission by generating eval.yaml and validating it.
UKGovernmentBEISwrite-an-adr
Write Architectural Decision Records documenting significant design choices in a numbered adr directory.
UKGovernmentBEIScreate-eval
Redirects users to the inspect-evals-template repository for creating new evaluations.
UKGovernmentBEISsecurity-audit-eval
Audit third-party Inspect AI evaluations for security risks before running them locally.
UKGovernmentBEISrelease-sandbox-tools
Builds, validates, and publishes inspect-sandbox-tools binaries to S3 for PR landing.
UKGovernmentBEISland-ts-mono
Coordinates cross-repo PR landing for ts-mono submodule changes in inspect_ai.
UKGovernmentBEISci-perf
Analyze GitHub Actions CI timing data and prepare ranked performance fixes for pull requests.
UKGovernmentBEISread-eval-logs
List, dump, convert, and view Inspect evaluation logs via Python APIs and CLI.
UKGovernmentBEIScode-quality-review-all
Audit evaluations under src/inspect_evals and generate results.json and SUMMARY.md.
UKGovernmentBEISinvestigate-dataset
Inspect HuggingFace, CSV, and JSON datasets for schema and quality.
UKGovernmentBEIScode-quality-fix-all
Plan, validate, and apply code quality fixes from results.json on a dedicated branch.
UKGovernmentBEISsecret-code
Read assets/secret.txt and execute scripts/reveal.sh to print the secret code.
UKGovernmentBEISdisk-usage
Analyze disk space usage and filesystem information on Linux systems.
UKGovernmentBEISnetwork-info
Collect Linux network configuration and connectivity data via netinfo.sh.
UKGovernmentBEISsystem-info
Gather Linux OS, kernel, CPU, memory, and uptime details from standard files.
Frequently Asked Questions About Department of Business, Energy and Industrial Strategy
FAQPage SchemaWhat specific tasks can be performed using these system diagnostic capabilities?▼
These capabilities enable granular analysis of Linux disk usage, network connectivity, and hardware telemetry. Users can extract kernel, CPU, and memory metrics directly from system files to monitor infrastructure health and connectivity status across distributed environments.
Which personas benefit most from these evaluation and code quality functions?▼
System administrators, site reliability engineers, and data quality analysts benefit from these functions. The suite is designed for technical professionals responsible for maintaining Linux server stability, auditing evaluation logs, and ensuring data schema compliance within complex development environments.
What are the prerequisites for executing these diagnostic and audit functions?▼
Execution requires a Linux-based environment with standard shell access and read permissions for system files. For evaluation and dataset tasks, users must have access to the target repository structure, specifically the src/inspect_evals directory and relevant data files in CSV, JSON, or HuggingFace formats.