Results for “compare”

Investigate AI observability evaluations of both types — `hog` (deterministic code-based) and `llm_judge` (LLM-prompt-based). Find existing evaluations, inspect their configuration, run them against specific generations, query individual pass/fail results, and generate AI-powered summaries of patterns across many runs. Use when the user asks to debug why an evaluation is failing, surface common failure modes, compare results across filters, dry-run a Hog evaluator, prototype a new LLM-judge prompt, or manage the evaluation lifecycle (create, update, enable/disable, delete).

The English summary is being prepared. Showing the original description.

Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".

The English summary is being prepared. Showing the original description.

Create a PostHog endpoint with the right shape on the first try — covers query kind choice, name conventions, what to expose as variables (HogQL code_name vs insight breakdown), data_freshness_seconds, and whether to materialise on day one. Use when the user says "create an endpoint", "expose this query as an API", "turn this insight into an endpoint", or asks for help structuring a new endpoint. Steers away from common mistakes: materialising a query with cohort breakdowns or compare mode, inline-only variables on a materialised endpoint, unbounded date ranges, ambiguous names.

The English summary is being prepared. Showing the original description.

Investigate AI observability clusters — understand usage patterns in AI/LLM traffic, compare cluster behavior, compute cost/latency metrics, and drill into individual traces within clusters.

The English summary is being prepared. Showing the original description.

Diagnoses CI and pull-request pipeline health for a GitHub repo using the engineering analytics MCP tools — pull-requests (PR list with CI status), workflow-health (per-workflow CI trends), and pr-lifecycle (a single PR's timeline). Use when asked whether CI is getting faster or slower, which GitHub Actions workflow is the slow or flaky long-pole, how long PRs take from open to merge, how an author's merge time compares to the cohort, which open PRs have failing or pending CI, or where a specific pull request is stuck. Triggers on "engineering analytics", "is CI getting slower", "slow workflow", "flaky CI", "time to merge", "cycle time", "PR throughput", "failing checks", "where is PR <n> stuck", "CI long pole", "what's holding up this PR".

The English summary is being prepared. Showing the original description.

Analyze session replay patterns across experiment variants to understand user behavior differences. Use when the user wants to see how users interact with different experiment variants, identify usability issues, compare behavior patterns between control and test groups, or get qualitative insights to complement quantitative experiment results.

The English summary is being prepared. Showing the original description.

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit

The English summary is being prepared. Showing the original description.

Dose-response / concentration-response curve fitting — IC50, EC50, Hill slope, Emax/Emin efficacy, and relative potency from paired concentration vs response data (enzyme/cell assays, drug screening, agonist/antagonist pharmacology). Fits the 4-parameter logistic (Hill sigmoidal) model. Use when you have concentrations + responses and need a potency value, to compare two compounds' potency, or to judge curve quality. NOT for image-derived dose-response (use tooluniverse-image-analysis) and NOT for survival/regression (use tooluniverse-statistical-modeling).

The English summary is being prepared. Showing the original description.

Find commercial sources for chemical compounds — PubChem/ChEMBL identity resolution then vendor catalog search across ZINC, Enamine, eMolecules, Mcule. Compares pricing, availability, and identifies purchasable analogs when an exact compound is not in stock. Use for chemical procurement, virtual library curation, and 'where can I buy X' questions for synthesis planning.

The English summary is being prepared. Showing the original description.

Performs alchemical free-energy calculations including relative binding free energy (RBFE / FEP+) and absolute binding free energy (ABFE) via OpenFE, FEP+, GROMACS, AMBER pmemd, and OpenMM with explicit lambda window scheduling, soft-core potentials, REST2 enhanced sampling, MBAR/BAR analysis, and cycle closure validation. Compares ML alternatives (Boltz-2 affinity, DeepDock). Use when ranking analogs by binding affinity beyond docking accuracy, performing prospective lead optimization, or validating SAR predictions.

The English summary is being prepared. Showing the original description.

Standardizes molecular structures using ChEMBL chembl_structure_pipeline and RDKit rdMolStandardize covering sanitization, salt/solvent stripping, neutralization, tautomer canonicalization, stereochemistry standardization, mixture handling, and isotope normalization. Explicitly compares ChEMBL pipeline, canSARchem, and PubChem standardization choices. Use when preparing libraries for QSAR training, joining datasets across sources, deduplicating compound collections, or building canonical compound registries.

The English summary is being prepared. Showing the original description.

Design charts, metrics, and data tables that help users interpret and compare data. Use when the user asks to visualize data, choose chart types, improve dashboard analytics, or make data presentation accessible. Dashboard navigation and shell layout alone belong to add-ui or arrange.

The English summary is being prepared. Showing the original description.

Create or redesign React and Tailwind sections, pages, flows, shells, and components. Use when the user wants new UI or a redesign. Implement one requested or selected direction directly, or generate distinct alternatives when the user asks to compare options.

The English summary is being prepared. Showing the original description.

Search academic literature and generate, validate, or compare Knows paper sidecars. Use for claim/evidence analysis and literature synthesis.

The English summary is being prepared. Showing the original description.

Reads and summarises ScenarioRunner output — the criteria pass/fail tables from --output/--file, the machine-readable --json and --junit result files, and the criteria JSON written alongside a --record recording — and runs the metrics module (metrics_manager.py) to compute custom measurements over a recorded run offline, without the simulator. Use when the user asks "did the scenario pass", "why did it fail", "summarise these results", "compare these runs", or wants distance/speed/lane metrics from a recording.

The English summary is being prepared. Showing the original description.

Read a Japanese job posting closely and report what it actually states: base pay separated from fixed overtime allowance, the range converted to an hourly basis, required versus preferred requirements, and the terms left ambiguous. Use when a user wants a 求人票 or job description examined before applying, wants two postings compared on the same basis, or wants questions prepared about pay and working conditions; do not use to judge whether the user will be hired, to infer duties the posting does not state, or to evaluate the employer's reputation.

The English summary is being prepared. Showing the original description.

Prepare the internal case for hosting an Otameshi Tenshoku trial: total what it costs the company with candidate pay, staff hours and platform or incidental fees kept apart, compare it with the budget, state what remains if no hire follows, and lay out the risks, stop conditions, decision owners and deadlines. Use when a hiring manager needs approval or budget from a decision maker, a recruiter has to explain the plan to the team that will host, or a small-business owner wants to see the full cost including their own time before posting; do not use to design the work (trial-work-design), to write the listing (trial-listing-draft), to predict whether a hire will follow, to state platform fees, agency fees or market rates from memory, or to submit the request or post the listing on the user's behalf.

The English summary is being prepared. Showing the original description.

Check the working conditions of a Japanese job offer item by item against the conditions an employer states in writing, compare the offer letter or 労働条件通知書 with the job posting and what was said in interviews, and separate what is confirmed in writing from what is still only verbal. Use when a user has received an offer, a working-conditions notice, or an employment contract and wants to know what is missing, what conflicts with earlier statements, and what to confirm before the acceptance deadline; do not use to rule on whether the terms are lawful, to decide whether to accept or decline, or to contact the employer on the user's behalf.

The English summary is being prepared. Showing the original description.

Debrief a finished Otameshi Tenshoku trial from the employer's side: set the observed facts against the completion criteria agreed before the start, keep expectations added afterwards, second-hand or off-the-job observations and the company's own late or missing support apart, settle the hours actually worked separately from any evaluation, and draft feedback to the candidate that states facts, support gaps and what happens next without promising a hire or continuation the company has not decided. Use when a hiring manager, recruiter or small-business owner wants to review a trial, decide what to tell the candidate, or work out the settlement after a shortfall; do not use to judge the candidate's aptitude or predict a hire, to cut pay or demand unpaid rework because of dissatisfaction, to compare candidates, or to send the feedback, pay, or update records on the user's behalf.

The English summary is being prepared. Showing the original description.

Help a user talk through whether to change jobs, stay, or change something in their current work, starting from uncertainty, distress, a vague sense of stagnation, an offer in hand, a counter-offer from the current employer, or pressure from family or colleagues. Clarify what matters, separate deadlines that order the next steps from the decision itself, compare conditional options, and agree on a small next step and a time to revisit it. Use when someone asks whether they should quit, wonders whether leaving is just running away, has second thoughts after receiving an offer or being asked to stay, feels stuck because others say it would be a waste, wants to leave soon after joining, or wants advice before deciding to start a job search; do not make the final stay-or-leave decision, evaluate offer terms, plan the resignation, or predict hiring outcomes.

The English summary is being prepared. Showing the original description.

Audit a browser fingerprint for internal contradictions with the liarjs CLI - canvas, WebGL, WebGL2, WebGPU, audio, 220 fonts, WebRTC and timezone probes, scored against the TLS/HTTP/ASN view of the same request. Use when asked to run a browser fingerprint test, see what a fingerprint looks like, check canvas or WebGL fingerprint stability, compare a spoofed profile against a real browser, or find out whether a browser profile is self-consistent.

The English summary is being prepared. Showing the original description.

Work on album artwork — reading an image's dimensions, and embedding a folder's cover file into the tags of its tracks. Use this whenever a task touches `services/artwork.py`, the cover half of `services/tags.py`, or `scripts/embed_covers.py` / `embed_covers_cron.sh`. Covers why Lyrion shows the embedded artwork and never the folder file, how covers are compared, why images are never re-encoded, and what embedding costs in rewritten files.

The English summary is being prepared. Showing the original description.

Reads, queries, and writes bigWig indexed binary signal tracks (coverage, fold-change, conservation, methylation-rate) with pyBigWig (Python) and the UCSC Kent tools (bedGraphToBigWig, bigWigToBedGraph, bigWigInfo, bigWigSummary, bigWigAverageOverBed) and deepTools (multiBigwigSummary, computeMatrix, bigwigCompare). Covers the central trap that a wide query returns a precomputed zoom-level summary (by default the mean, which annihilates narrow peaks) not per-base data, when exact=True/values() is mandatory, the NaN-not-zero gap-handling fork, choosing mean vs max vs sum vs coverage by biological question, and the sorted-bedGraph plus chrom.sizes build requirement. Use when extracting signal at regions, computing mean signal per gene/peak, building a browser track from bedGraph, comparing tracks, or building TSS/gene-body metaprofiles.

The English summary is being prepared. Showing the original description.

Compare cell-type composition and spatial features across conditions in IMC/MIBI cohorts with the patient as the experimental unit, covering pseudoreplication, per-patient aggregation, mixed models, compositional (Dirichlet/scCODA) differential abundance, diffcyt, per-image-to-patient spatial differential testing (SpaceANOVA), batch covariates, and FDR. Use when testing whether a cell type or spatial niche differs between groups, avoiding cell-level pseudoreplication, choosing a differential-abundance method, or correctly powering an IMC cohort comparison.

The English summary is being prepared. Showing the original description.