177 skills · sorted by relevance
Establishes CPU/GPU baselines before resource-intensive operations. Use before builds, training runs, or any task that pins cores or GPUs for over a minute.
The English summary is being prepared. Showing the original description.
Optimize DSPy programs with dspy.GEPA — a reflective/evolutionary optimizer to consider against task-specific baselines within an authorized evaluation budget. Use when the user says optimize, compile, GEPA, reflective optimization, or "make this program better" and a DSPy program + metric + trainset exist.
The English summary is being prepared. Showing the original description.
Design reproducible evaluations for AI agents with representative task sets, explicit rubrics, appropriate graders, baselines, regression gates, and failure analysis. Use when defining agent quality, comparing prompts or models, validating a release, measuring tool-use reliability, investigating regressions, or deciding whether an agent is ready for production.
The English summary is being prepared. Showing the original description.
Think and work like an expert Machine Learning Engineer. Use when a task calls for Machine Learning Engineer judgment. Reasons from decision-policy framing, Google's Rules of ML, point-in-time data, and prefill/decode inference physics through GBDT/PyTorch baselines, vLLM/SGLang/KServe serving with FP8/AWQ quantization, hybrid-retrieval RAG, RAGAS and human-validated LLM judges, OpenTelemetry GenAI tracing, and post-Omnibus EU AI Act obligations while treating train-serve skew, temporal leakage, prompt injection, LLM nondeterminism, and degenerate feedback loops as first-class failure modes.
The English summary is being prepared. Showing the original description.
Think and work like an expert Conservation Biologist. Use when a task calls for Conservation Biologist judgment. Reasons from IUCN Red List A–E and Green Status recovery metrics, PVA/Ne, occupancy and distance sampling (unmarked, msocc, RMark), prioritizr/Marxan SCP, Conservation Evidence and ROSES synthesis, counterfactual impact evaluation, METT/SMART PAME, and eDNA false-positive models while treating pseudoreplication, GBIF effort bias, offset baselines, and Red List≠priority conflation as first-class failure modes.
The English summary is being prepared. Showing the original description.
Think and work like an expert Computer Graphics Researcher. Use when a task calls for Computer Graphics Researcher judgment. Reasons from the rendering equation, Monte Carlo bias/variance, sampling theory, and BSDF energy conservation through pbrt-v4/Mitsuba 3 references, MIS/ReSTIR/path guiding, DXR 1.2 real-time stacks, 3DGS and NerfBaselines protocols, FLIP/ColorVideoVDP evaluation, OpenUSD/MaterialX/OpenPBR interchange, and ACES 2/OCIO color while treating unconverged references, unequal-time comparisons, denoiser and temporal-reuse bias, scene- vs display-referred color errors, and white-furnace energy failures as first-class failure modes.
The English summary is being prepared. Showing the original description.
Think and work like an expert Computer Vision Scientist. Use when a task calls for Computer Vision Scientist judgment. Reasons from image formation, projective geometry (pinhole intrinsics and extrinsics, epipolar/PnP/bundle adjustment, similarity-scale ambiguity), and COCO/LVIS AP mechanics through DINOv3/SigLIP 2 foundation baselines, RF-DETR/YOLO26/SAM 3 models, COLMAP 4/GLOMAP and VGGT geometry, pycocotools/TrackEval/BOP evaluation, and CVPR reporting and EU AI Act limits while treating train–test and pretraining leakage, AP evaluation-setting gaming, preprocessing mismatches (EXIF, BGR, aliased resizing), label noise, and camera-convention and scale errors as first-class failure modes.
The English summary is being prepared. Showing the original description.
Think and work like an expert Climatologist. Use when a task calls for Climatologist judgment. Characterizes climate via WMO CLINO baselines (1991–2020 vs 1961–1990), ETCCDI indices, and teleconnection modes; bridges ERA5 climatology to CMIP6/ScenarioMIP SSP deltas (xsdba/QDM), optimal-fingerprint attribution, AR6 ERF/ECS/TCR, and proxy reconstructions (CPS/EIV, PAGES2k, MXD divergence)—distinct from weather forecasting and generic physical-climate narration.
The English summary is being prepared. Showing the original description.
Proteina-Complexa flow-based protein backbone generation with fold-conditioned sampling guidance. Use this skill when: (1) Generating de novo protein backbones with hierarchical fold conditioning, (2) Exploring long-chain backbone generation beyond standard diffusion baselines, (3) Using NVIDIA Proteina-style flow matching workflows for controllable backbone design, (4) Comparing flow-based backbone generation against RFdiffusion or BoltzGen, (5) Prototyping fold-guided backbone campaigns before sequence design. This skill is based on the public NVIDIA Digital Bio Proteina project and uses "Proteina-Complexa" as the BioClaw-facing skill label. For sequence design after backbone generation, use proteinmpnn or solublempnn. For QC thresholds, use protein-design-qc.
The English summary is being prepared. Showing the original description.
Implement visual regression testing with Playwright screenshots, Chromatic, Percy, and Argos CI. Covers baseline management, diff threshold tuning, dynamic content masking, responsive viewport testing, and review/approval workflows. Use when: "visual test," "screenshot," "visual regression," "pixel diff," "snapshot diff," "update baselines," "Chromatic," "percy snapshot," "argos screenshot." Not for: bulk baseline regeneration after a redesign broke many tests — use selector-drift-recovery; cross-browser rendering matrices — use cross-browser-testing; general Playwright test structure — use playwright-automation. Related: playwright-automation, ci-cd-integration, cross-browser-testing.
The English summary is being prepared. Showing the original description.
Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent (HP-WEAK-BASELINE); 'outperforms' is asserted over overlapping error bars or with no variance/seeds (HP-SIG-OVERLAP); and a cross-row 'improves over baseline by X%' is arithmetically wrong (HP-DELTA-ERROR, cross-row form only). A versioned per-domain baseline profile + a live leaderboard/recency search are assembled by the EXECUTOR as structured facts; a fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per dimension) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Works at L0 (stated comparisons) and deepens at L2 (configs/result files). A completeness question it cannot settle internally becomes needs_external_check, never a guessed missing baseline. Emits baseline-comparison-audit.findings.json; computes NO verdict. Detect-only. Triggers: "baseline audit", "missing baselines", "is the comparison fair", "weak baseline", "baseline 误报", "SOTA earned?".
The English summary is being prepared. Showing the original description.
Verify authorized feature, fix, and refactor work with scoped obligations, regression-first fixes, behavioral checks, characterization baselines, coverage, and lint.
The English summary is being prepared. Showing the original description.
SEO drift monitoring: capture baselines of SEO-critical elements, detect changes, and track regressions over time. Git for SEO — baseline, diff, and track changes to your on-page SEO. Use when user says "SEO drift", "baseline", "track changes", "did anything break", "SEO regression", "compare SEO", "before and after", "monitor SEO changes", or "deployment check".
The English summary is being prepared. Showing the original description.
Use when training, tuning, comparing or evaluating a model — choosing the cross-validation scheme, baselines, tuning inside CV, thresholds and calibration, per-slice metrics, feature importance and error analysis
The English summary is being prepared. Showing the original description.
Tests a real web user flow with a browser by asserting semantic behavior, network and loading states, keyboard access, responsive layouts, and stable visual evidence. Use for browser bugs, end-to-end UI behavior, responsive or accessibility checks, and screenshot baselines. Not for static source review without a browser or for backend-only tests.
The English summary is being prepared. Showing the original description.
Designs and runs reproducible evaluations for AI agents, prompts, tools, skills, and model-backed workflows using realistic datasets, isolated baselines, objective assertions, rubric grading, trajectory analysis, cost/latency tracking, and regression comparison. Use when measuring agent quality, optimizing skill triggering, comparing prompts or models, or gating an AI feature release. Not for ordinary deterministic unit tests.
The English summary is being prepared. Showing the original description.
Designs and executes compatibility-preserving migrations across APIs, schemas, frameworks, dependencies, protocols, storage, and infrastructure with baselines, coexistence, staged cutover, rollback or forward-fix paths, and explicit removal criteria. Use for deprecations, upgrades, data moves, contract changes, and replacing live implementations. Not for a local refactor with no external state or compatibility boundary.
The English summary is being prepared. Showing the original description.
A/B test CLAUDE.md instruction changes against eval benchmarks. Capture baselines, test variants, compare results.
The English summary is being prepared. Showing the original description.
Use this skill when a company starts a compliance programme and needs to know how far it is from a framework, and asks "run a gap analysis", "how ready are we for the audit", "baseline us against the framework", "what do we have and what is missing", "readiness assessment before we hire an auditor" or "how long until we can certify". Baselines what exists against the chosen framework from documents and records, rates each item by evidence rather than opinion, sizes every gap by effort and audit risk, and writes a gap register plus a prioritised summary with the long-lead items first.
The English summary is being prepared. Showing the original description.
Monitor, cap, and recover from context accumulation in agentic systems. Covers per-cycle cost tracking, context window auditing, budget caps with enforcement policies, emergency pruning when approaching limits, and progressive disclosure integration to minimize token spend on routing. Use when running long-lived agent loops (heartbeats, polling, autonomous workflows), when context windows are growing unpredictably between cycles, when API costs spike beyond expected baselines, when designing new agentic workflows that need cost guardrails from the start, or when post-mortem analysis reveals a cost incident caused by context accumulation.
The English summary is being prepared. Showing the original description.
Create or evolve an implementation-agnostic website design system from existing-site evidence, verified brand inputs, and an optional Visual Reference Brief. Use to establish visual and restrained-motion baselines, extract an existing site's rendered system for style-preserving extensions, validate one selected baseline with a compact Design Board, or update shared rules before page/module design. Do not conduct cross-industry reference research, map Elementor settings, create page layouts, design modules, or implement production code.
The English summary is being prepared. Showing the original description.
Visual regression testing — screenshot baselines, determinism, diff review, baseline custody and CI wiring. Load when adding, reviewing or debugging tests that compare a rendered subject against an approved image.
The English summary is being prepared. Showing the original description.
Use when setting up visual regression testing with Playwright - toHaveScreenshot baselines, masking dynamic content, handling animations, full-page and element screenshots, cross-browser runs, CI integration, VUDA MCP tooling, or debugging flaky visual diffs
The English summary is being prepared. Showing the original description.
Use when setting up or reviewing Storybook component documentation, design-system presentation, isolated component state previews, stories, addons, decorators, MDX docs, component-state interaction checks, visual baselines, or Chromatic. For real-browser cross-page journeys or broader coverage planning, choose the matching testing workflow first; Chinese triggers include Storybook, component documentation, Design System, visual regression.
The English summary is being prepared. Showing the original description.