Results for “eval”

Evaluate learning progress, identify blockers, and adjust the learning plan

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

Improve agent reliability over time — diagnose why agents fail and fix the setup. Triggers on: agent keeps failing, same mistake again, agent not improving, make agent smarter, agent quality plateau, agents ignore skills, agent skips tests, fix agent behavior, agent unreliable, improve agent setup, self-improving harness, agents worse over time, tune agent instructions, agent going in circles, agent ignores AGENTS.md, repeated agent errors. Requires harness v0 and eval harness. AUTO-ROUTED from harness-engineering on symptoms. Not first setup — harness-generation first.

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

Seed minimal agent harness v0 — manifest, eval checks stub, governance. AUTO-INVOKED after project-setup or retroactive-project-setup when docs/harness/manifest.json is missing. Also triggers on: generate harness, scaffold agents, agent bootstrap, first time agents in this repo, new project agent setup, set up agent harness, agent onboarding files, missing agent configuration, agent instructions setup, make agents read project rules, agent reliability setup, agents not configured. Pairs with project-setup. Evolution is harness-evolution.

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

Pick the right business-model canvas (Lean Canvas, Business Model Canvas, or Value Proposition Canvas) for the stage and fill it with specifics — one segment, one primary canvas, top-3 assumptions, no fluff in the moat or channel boxes. Load when the user asks to fill a business model canvas, lean canvas, value proposition canvas, model this business, map the business model, says "fill the BMC", "make a Lean Canvas", "Value Proposition Canvas for this", "model this idea", "what's the business model", "design the business model". Sub-skill of `venture-exploration`. Hard-bans "everyone" segments, generic channels ("SEO/social/content/ads"), and "unfair advantage = AI/data/network effects" with no concrete asset. Does NOT score viability — for that use `idea-evaluation`.

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

Instrument a shipped product's AI agents with tracing and observability so you can see what they did, why outputs happened, and what each run cost. Plain-language primer plus free-tier-first backend selection (Langfuse, Phoenix, LangSmith, Braintrust) and OpenTelemetry/OpenInference instrumentation. Load when the user asks to add observability, add tracing, instrument my agents, see what my agent is doing in production, set up Langfuse or Phoenix or LangSmith, debug why my agent gave a bad answer, or track LLM cost per request. Also fires when agent-system-architecture or setup-evaluation requires an observability plan for an agent-chain product. NOT for tracing the coding agent itself — that is run-trace. Precondition for runtime-learning-loop.

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

Review a built frontend against its chosen direction, catch drift back to generic AI defaults, enforce state coverage, ethical patterns, UX heuristics, and polish, and check contrast with APCA (not the legacy WCAG ratio). Produces specific, prioritized fixes — never vibes-based feedback. Works with pasted screenshots or Playwright MCP automated capture. Load when the user asks to review a UI, audit a design, check if a frontend looks generic or vibecoded, evaluate visual quality or polish, says "review this UI", "is this design good", "audit my frontend", "does this feel like [product]", "design QA", or when frontend-design routes here. Sub-skill of frontend-design.

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

Use this skill when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews covering methodology assessment, contribution evaluation, literature positioning, and constructive feedback generation. Trigger on queries involving paper URLs, uploaded PDFs, arXiv links, or requests like "review this paper", "analyze this research", "summarize this study", or "write a peer review".

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

X-ray any AI model's behavioral patterns — refusal boundaries, hallucination tendencies, reasoning style, formatting defaults. No API key needed.

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

High-level SDK for Azure AI Foundry projects with agents, connections, deployments, and evaluations.

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

Azure AI Projects SDK for Java. High-level SDK for Azure AI Foundry project management including connections, datasets, indexes, and evaluations.

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

Azure AI Projects SDK for .NET. High-level client for Azure AI Foundry projects including agents, connections, datasets, deployments, evaluations, and indexes.

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

Find and evaluate influencers for brand partnerships, verify authenticity, and track collaboration performance across Instagram, Facebook, YouTube, and TikTok.

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

Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.

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

A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks.

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

Segment single cells from multiplexed IMC/MIBI tissue images using Mesmer/DeepCell, Cellpose, or ilastik+CellProfiler, covering whole-cell vs nuclear segmentation, the summed-membrane-channel decision, nuclear-expansion bias, lateral spillover, resolution-floor parameters, and downstream-proxy evaluation. Use when delineating cells after preprocessing, choosing a segmentation model, building a cell mask for quantification, diagnosing impossible double-positive populations, or troubleshooting over/under-segmentation.

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

Evaluates genome assembly quality across the three orthogonal axes - contiguity (QUAST auN/NG50/NGx, not bare N50), completeness (BUSCO/compleasm gene-space plus Merqury k-mer completeness), and correctness (reference-free Merqury QV, Inspector/CRAQ structural errors, asmgene false-duplication/collapse). Covers why N50 is the most-gamed metric, why QV measured on the polishing reads is circular, distinguishing uncollapsed haplotigs from real WGD, and the EBP/VGP 6.C.Q40 standard. Use when judging whether an assembly is good enough to annotate or publish, comparing assemblers, diagnosing a fragmented or duplicated assembly, or assessing a phased diploid assembly.

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

Query UniProt's REST API (post-2022 endpoint at rest.uniprot.org) for protein sequences, annotations, GO terms, cross-references, ID mappings, and proteomes. Use when fetching UniProtKB entries, navigating the JSON schema, choosing between UniProtKB/UniRef/UniParc/Proteomes resources, deciding stream vs search endpoint for batch retrieval, running ID-mapping jobs with the async pattern, handling isoform suffixes, or filtering reviewed Swiss-Prot vs auto-annotated TrEMBL. Encodes the legacy URL migration (2022), the new JSON schema layout, and bulk-pull patterns.

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

Aligns and QCs methylated-RNA-immunoprecipitation (MeRIP / m6A-seq) IP and input libraries using STAR or HISAT2 splice-aware mapping, samtools sort/index, IP/input matched-pair tracking, antibody-lot metadata recording, replicate concordance via deepTools multiBamSummary + plotCorrelation, IP enrichment QC via plotFingerprint and per-transcript IP/input ratio distributions, library-complexity saturation curves via PreSeq c_curve / lc_extrap, and the explicit do-NOT-deduplicate convention for standard non-UMI MeRIP. Use when preparing paired IP and input BAM files for exomePeak2 / MeTPeak / MACS3 peak calling, evaluating MeRIP replicate concordance and IP enrichment, deciding whether to deduplicate (standard MeRIP typically NOT — see Tips), choosing genome-vs-transcriptome alignment for downstream peak vs m6Anet workflows, recording antibody clone and lot metadata for downstream cross-batch reconciliation, detecting failed IPs via saturation curves and IP/input distribution shape, or generating IP-over-Input bigWig tracks for downstream visualisation.

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

Infer gene regulatory networks from bulk or general expression data with mutual-information (ARACNe) and tree-ensemble (GENIE3, GRNBoost2) methods, and infer transcription-factor protein activity from regulons with VIPER and msVIPER. Covers the activity-not-edges paradigm, the undirected-association caveat, the DREAM5 wisdom-of-crowds and method-complementarity result, AUPRC-over-AUROC evaluation, and gold-standard incompleteness. Use when inferring a regulatory network from a bulk expression matrix, finding master regulators, or scoring TF activity from a signature. For single-cell motif-pruned regulons see scenic-regulons; for co-expression modules see coexpression-networks.

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

Query the Ensembl REST API for gene/transcript/protein lookup, sequence retrieval, comparative genomics (Compara), variant effect prediction (VEP), regulatory features, and cross-species ortholog/paralog calls. Use when pulling Ensembl-native data (Ensembl Gene IDs, version-pinned releases, archive endpoints for reproducibility), gene/transcript/exon structure with stable IDs, or VEP for variant annotation. Encodes the 15 req/sec rate limit, archive (e110.rest.ensembl.org) for reproducibility, Ensembl divisions (vertebrates / plants / fungi / metazoa / bacteria), and the symbol-vs-ID stability problem.

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

Download genome assemblies, gene records, and ortholog data from NCBI using the modern Datasets v2 CLI (replaces assembly_summary.txt scraping and many EFetch workflows). Use when bulk-pulling genome assemblies, gene metadata across species, ortholog sets, or BLAST databases; when E-utilities are too slow for genome-scale work; or when automatic checksum verification, parallel download, and clean accession-driven retrieval are required. Encodes the JSON-lines output format, dataformat conversion, --dehydrated for cloud workflows, and when Datasets is/isn't the right tool.

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

Quality control for pooled CRISPR screens covering library representation, Gini index, log-skew, replicate Pearson and Spearman concordance, essentialome precision-recall AUC against CEGv2 (Hart 2017), Cas9 cut-toxicity diagnostics, copy-number amplicon detection (Aguirre 2016 / Munoz 2016), bottleneck propagation through plasmid pool, infection, selection, and endpoint stages, MOI verification, and DepMap-style screen-quality scoring. Use when assessing screen quality before hit calling, deciding whether to repeat or rescue a screen, diagnosing low-confidence hits, choosing between MAGeCK / BAGEL2 / Chronos based on quality grade, picking a normalization strategy from QC signatures, or evaluating whether an in-vivo screen retained adequate library complexity.

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

Build publication-quality figures in R with ggplot2 using the grammar of graphics (data + aesthetics + geometries + scales + facets + themes) with CVD-safe palettes, cairo_pdf TrueType embedding, programmatic aes via tidy evaluation, and the theme_classic publication baseline. Use when producing static figures in R for papers, presentations, or reports.

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

Predict RBP binding from RNA sequence using deep learning models (RBPNet sequence-to-signal, RNAProt RNN, GraphProt2 GCN with structure, DeepCLIP, DeepRiPe multi-modal CNN) for variant-effect prediction, in silico binding-site discovery, model interpretation, and transfer learning from CLIP and RBNS datasets. Use when computational prediction of RBP binding from sequence is needed, evaluating variant effects on binding without further wet-lab experiments, comparing model performance, or training a custom model on ENCODE eCLIP data.

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