UKGovernmentBEIS
- 32 skills
- 0 followers
- 733 repo stars
- last month last updated
- ▌ Secret Code · ukgovernmentbeis bundleRetrieve a secret code by reading a bundled asset file and executing a companion script. Use when the user asks to reveal, decode, or look up the secret code from this skill's assets.
- ▌ Update Test Cases · ukgovernmentbeis bundleUse when: updating test cases in General_TestCases.csv, syncing test cases from spec files, adding new test cases to CSV, documenting automated tests, checking for duplicate test cases, updating test case results or status. Maintains Documentation/Test Cases/General_TestCases.csv in sync with Playwright .spec.ts test files. Use for: 'update test cases', 'sync test cases', 'add test case to CSV', 'document this test', 'record test cases from this file'.
- ▌ Scientific Debug · ukgovernmentbeisUse this skill whenever the user asks to debug something, fix a bug, troubleshoot an issue, or mentions "scientific debugging". Any debugging request should use this skill.
- ▌ Running Hibayes · ukgovernmentbeisUse whenever the user wants to run, configure, extend, or debug a HiBayES analysis — hierarchical Bayesian statistical modelling of Inspect AI eval results (or any tabular eval data). Covers the five-stage pipeline (load → process → model → check → communicate), the YAML config surface, the CLI (`hibayes-full`, `hibayes-load`, `hibayes-process`, `hibayes-model`, `hibayes-comm`), the component registries (extractors, processors, models, checkers, communicators), and the AnalysisState output layout. Triggers on "analyse these eval scores with hibayes", "is model X actually better than Y", "fit a hierarchical model to my eval results", "add a custom extractor/processor/model", installing or setting up hibayes, watching a run's TUI, or any config.yaml editing for hibayes.
- ▌ Hibayes Statistical Workflow · ukgovernmentbeis bundleUse whenever making STATISTICAL decisions in a HiBayES analysis: choosing a model/likelihood, setting or justifying priors, interpreting prior/posterior predictive checks, diagnosing bad MCMC fits (divergences, R-hat, low ESS, BFMI), comparing models with WAIC/LOO, or writing up results. Encodes the principled Bayesian workflow applied to AI-eval data, and carries a plain-language concepts reference for explaining each step to the user. Triggers on "which model should I use", "are these priors OK", "the fit has divergences", "is the difference between models real", "how do I report this", "what does R-hat/elpd/partial pooling mean", "is this significant", or reviewing any hibayes config's model/check sections.
- ▌ Inspect AI · ukgovernmentbeisAnalyze Inspect AI evaluation logs, understand EvalLog structure, extract samples, events, and scoring data using dataframes
- ▌ Inspect Scout · ukgovernmentbeisAnalyze AI agent transcripts using Inspect Scout scanners, grep patterns, and LLM-based analysis
- ▌ Create Eval · ukgovernmentbeisRedirect to the inspect-evals-template for creating new evaluations. New evals are no longer created in this repository — they live in standalone repos. Use when user asks to create/implement/build a new evaluation.
- ▌ Write An Adr · ukgovernmentbeis bundleWrite an Architectural Decision Record (ADR) to document a significant design choice. Use when user asks to write/create/document an ADR, or to record an architectural decision.
- ▌ Read Eval Logs · ukgovernmentbeisView and analyse Inspect evaluation log files using the Python API. Trigger whenever you need to look at a .eval file yourself without using pre-written scripts.
- ▌ Prepare Release · ukgovernmentbeisPrepare a new release of inspect_evals by creating a release branch, collecting changelog fragments, and opening a PR. Use when user asks to cut/prepare/create a new release or version bump.
- ▌ Build Repo Context · ukgovernmentbeisCrawl repository PRs, issues, and review comments to distill institutional knowledge into a shared knowledge base. Run periodically by "context agents" to maintain agent_artefacts/repo_context/REPO_CONTEXT.md. Trigger only on specific request.
- ▌ Investigate Dataset · ukgovernmentbeis bundleInvestigate datasets from HuggingFace, CSV, or JSON files to understand their structure, fields, and data quality. Trigger whenever you need to explore or inspect a dataset yourself without using pre-written scripts.
- ▌ Security Audit Eval · ukgovernmentbeisAudit a third-party Inspect AI evaluation for security risks before running it locally. Decide whether the eval is safe by checking for malicious host-side code, externally-fetched files that aren't quality-controlled, sandbox-breakout instructions, weak sandbox configuration, supply-chain hazards, credential exposure, resource exhaustion, and provenance signals. Use when the user asks to audit / vet / security-review an eval repo (GitHub URL or local path), or asks "is it safe to run X". Do NOT use for assessing whether an eval *measures what it claims* (use eval-validity-review) or for general code-quality review (use eval-quality-workflow / code-quality-review-all).
- ▌ Code Quality Fix All · ukgovernmentbeisFix code quality issues identified in a code quality review stored in agent_artefacts/code_quality/<topic>/. Systematically addresses issues found by the code-quality-review-all skill for ANY code quality topic, with validation and testing at each step. Use when user asks to fix issues from a code quality review, or asks to fix issues from agent_artefacts/code_quality/<topic>.
- ▌ Ensure Test Coverage · ukgovernmentbeis bundleEnsure test coverage for a single evaluation - both reviewing existing tests and creating missing ones. Analyzes testable components, checks tests against repository conventions, reports coverage gaps, and creates or improves tests. Use when user asks to check/review/create/add/ensure tests for an eval. Use whenever you are asked to review an evaluation that contains tests, or whenever you need to write a suite of tests. Do NOT use for fixing a specific failing CI test (use ci-maintenance-workflow instead).
- ▌ Eval Report Workflow · ukgovernmentbeis bundleCreate an evaluation report for a README by selecting models, estimating costs, running evaluations, and formatting results tables. Use when user asks to make/create/generate an evaluation report. Trigger when the user asks you to run the "Make An Evaluation Report" workflow.
- ▌ Eval Validity Review · ukgovernmentbeisReview a single evaluation's validity — whether its claims hold up, whether its name is accurate, whether samples can be both succeeded and failed at, and whether scoring measures ground truth. Use when user asks to check validity of an eval, or as part of the Master Checklist workflow. Do NOT use for code quality or test coverage (use eval-quality-workflow or ensure-test-coverage instead).
- ▌ Eval Quality Workflow · ukgovernmentbeisFix or review a single evaluation against all EVALUATION_CHECKLIST.md standards. Use "fix" mode to refactor an eval into compliance, or "review" mode to assess compliance without making changes. Use when user asks to fix, review, or check an evaluation's quality. Trigger when the user asks you to run the "Fix An Evaluation" or "Review An Evaluation" workflow. Do NOT use for reviewing ALL evals against a single code quality standard (use code-quality-review-all instead).
- ▌ Verify Scoring Change · ukgovernmentbeisUse when reviewing, verifying, or triaging a PR or proposed fix that changes a scorer, a metric, an answer-extraction or verdict-parsing path, or code that consumes a grader model's output. Also use when asked whether a scoring fix is safe to merge or whether reported numbers will move. Do NOT use for reviewing a whole evaluation against every standard (eval-quality-workflow) or for general PR review (ci-maintenance-workflow).
- ▌ Generate Asset Actions · ukgovernmentbeisGenerate asset-actions.yaml from ASSETS.yaml by classifying assets into priority tiers. Use when the user asks to regenerate, update, or refresh the asset actions.
- ▌ CI Maintenance Workflow · ukgovernmentbeisCI and GitHub Actions maintenance workflows — fix a failing test from a CI URL, fix a failing smoke test, add @pytest.mark.slow markers to slow tests, or review a PR against agent-checkable standards. Use when user asks to fix a failing test, fix a smoke test, mark slow tests, or review a PR. Trigger when the user asks you to run the "Write a PR For A Failing Test", "Fix A Failing Smoke Test", "Mark Slow Tests", or "Review PR According to Agent-Checkable Standards" workflow.
- ▌ Code Quality Review All · ukgovernmentbeis bundleReview all evaluations in the repository against a single code quality standard. Checks ALL evals against ONE standard for periodic quality reviews. Use when user asks to review/audit/check all evaluations for a specific topic or standard. Do NOT use for reviewing a single eval (use eval-quality-workflow instead) or for test coverage (use ensure-test-coverage instead).
- ▌ Check Trajectories Workflow · ukgovernmentbeisUse Inspect Scout to analyze agent trajectories from evaluation log files. Runs default and custom scanners to detect external failures, formatting issues, reward hacking, and ethical refusals. Use when user asks to check/analyze agent trajectories. Trigger when the user asks you to run the "Check Agent Trajectories" workflow.
- ▌ Prepare Submission Workflow · ukgovernmentbeisPrepare an evaluation for PR submission as an entry to the register. Use when user asks to prepare an eval for submission or finalize a PR. Trigger when the user asks you to run the "Prepare Evaluation For Submission" workflow.
- ▌ Disk Usage · ukgovernmentbeis bundleAnalyze disk space usage, filesystem mounts, and storage allocation on Linux systems. Identifies large files and directories, checks partition usage, and reports inode consumption. Use when the user asks about disk full errors, free space, storage usage, du/df output, finding large files, or checking which directories consume the most space.
- ▌ System Info · ukgovernmentbeis bundleRetrieve detailed Linux system information including OS distribution, kernel version, CPU model and core count, memory usage, and uptime. Use when the user asks about system specs, hardware details, RAM, processor info, kernel version, or needs a host inventory summary.
- ▌ Network Info · ukgovernmentbeis bundleGather network configuration and connectivity details on Linux including interfaces, IP addresses, routing tables, DNS settings, and listening ports. Use when the user asks about IP configuration, network interfaces, connection issues, DNS resolution, open ports, routing, or network troubleshooting.
- ▌ Release Sandbox Tools · ukgovernmentbeisLand a PR that requires new inspect-sandbox-tools injectable binaries to be built and published. Use when asked to land/merge a PR that changed code under src/inspect_sandbox_tools/ (typically its slow-tool-tests-release check fails on missing published binaries), or when asked to build/validate/upload sandbox tools binaries.
- ▌ CI Perf · ukgovernmentbeis bundleAssess and improve CI performance for pull requests in this repo. Use whenever the user asks about CI speed, slow CI, how long checks take, queue/runner wait, slow or duplicate tests, CI cost, or asks to run the recurring CI performance report (/ci-perf). Also use when asked to make PR feedback faster or to review workflow efficiency.
- ▌ Slow Tests · ukgovernmentbeisRun the gated test classes that plain `pytest` skips (slow Docker/sandbox tests, live model-provider API tests, flaky tests, trio variants). Use when asked to run slow, live, api, or trio tests, when debugging one, or when a change touches model providers, sandbox or tool code, agents, or async plumbing and needs its gated coverage run.
- ▌ Land TS Mono · ukgovernmentbeisLand a PR that requires a coordinated ts-mono submodule change. Use when the check-schema-and-types CI job fails, when a Python model change requires regenerating the OpenAPI spec / TypeScript types, or when any change touches the ts-mono submodule and needs to be landed.