651 skills · sorted by relevance
Use TensorBoard to visualize training loss and accuracy, compare experiments, and inspect model structure. Guides logging for PyTorch and TensorFlow, including weight distributions and performance profiling to investigate training problems and processing bottlenecks.
Run concurrent Omnigent conversations with real hosts and runners while replacing the LLM with a zero-latency mock. Read the generated report to explain response-time distributions, throughput, and failures, helping assess Omnigent's own processing overhead.
Build MCP servers that connect AI assistants to external services and data. This skill guides tool design, input validation, error handling, testing, and distribution, with implementation examples for TypeScript and Python.
Use three adaptive questions to identify where product growth is stuck. The skill recommends a path through new customer segments, geographies, distribution channels, or products, then suggests a low-cost first experiment and a common trap to watch for.
Build or review quality control workflows for single-cell and single-nucleus RNA sequencing data. Select filters from observed data, detect doublets, assign cell types, and create UMAP plots that summarize cell relationships, while recording analysis decisions and outputs.
Diagnose macOS app launch and trust failures by inspecting code signatures, app permissions, and Gatekeeper checks. Identify the failure category and get a minimal validation or repair sequence that distinguishes local development issues from distribution requirements.
Design a content marketing system that connects posts, videos, and newsletters to sales opportunities. It helps analyze successful content, adapt one core piece for multiple platforms, plan follow-up conversations, and measure which content contributes to deals.
Clean Excel data and group records with similar numerical features. Produce a combined view of indicator trends, value distributions, category shares, and grouped data, then export the charts as an image and cleaned records as Excel.
Assess numeric Excel columns using IQR, a measure of the middle half of values, to flag outliers. Summarize counts and limits, create box plots, and examine distribution shape to inform data cleaning.
Analyze Excel data using custom categories, count distributions, and compare groups with charts. Score text using its length, technical terms, numbers, and selected complex concepts, then visualize difficulty levels and the relationship between text length and scores.
Classify existing tests with standard tags for success cases, errors, boundaries, and other behaviors. Get a per-test mapping and distribution summary, or apply tags using supported framework syntax and verify compilation and test discovery.
Analyze datasets in R or Python, from exploring distributions and missing values to fitting regressions. Produce tables and figures for publication, save scripts and model results, and review the analysis for common problems.
Build and evaluate Bayesian models with PyMC and ArviZ, from choosing initial assumptions to checking predictions. The workflow covers sampling diagnostics, model comparison, and reports that explain results with uncertainty intervals.
Use when the user asks to run a full empirical / causal analysis in Python — by default in the style of an applied economics paper (AER / QJE / JPE / ReStud / AEJ) with DID / RD / IV / SCM / DML / matching, written-out estimating equation + identifying assumption, Table 1 / Table 2 / event-study figure / robustness gauntlet — OR in epidemiology / public health style (target-trial emulation, IPTW + g-formula + TMLE triplet, Mendelian randomization, KM/AFT survival, E-value sensitivity, STROBE/TRIPOD reporting) — OR in ML causal inference style (DML, S/T/X/R/DR meta-learners, causal forest, Dragonnet/TARNet/CEVAE, BCF, CATE distribution, policy learning, conformal causal, fairness audit, causal discovery) — OR in distributional / gap-decomposition style (Oaxaca–Blinder `sp.oaxaca`, Kitagawa `sp.kitagawa_decompose`, DiNardo–Fortin–Lemieux `sp.dfl_decompose`, Gelbach `sp.gelbach`, Fairlie `sp.fairlie`, RIF / FFL `sp.rif_decomposition`, all reachable through the `sp.decompose` dispatcher). Also covers exporting multi-column regression tables to Word / Excel / LaTeX (Stata outreg2 / esttab / R modelsummary equivalent) and bundling an entire replication appendix into one .docx / .xlsx / .tex file. Triggers on keywords "StatsPAI", "statspai", "AER empirical analysis", "applied micro pipeline", "Table 1 balance", "event study", "first-stage F", "Oster bound", "honest_did", "spec_curve", "callaway_santanna", "dragonnet", "text as treatment", "outreg2 in Python", "regression table to Word/Excel", "sp.regtable", "sp.collect", "sp.paper_tables", "sp.feols", "summary_col", "modelsummary", "AER style table", "QJE style table", "epidemiology pipeline", "target trial emulation", "g-formula", "IPTW", "TMLE", "Mendelian randomization", "STROBE", "TRIPOD", "公共健康", "流行病学", "DML", "double machine learning", "causal forest", "meta-learner", "CATE", "conformal causal", "policy learning", "因果机器学习", "ML causal", "decomposition", "Oaxaca-Blinder", "Kitagawa", "DiNardo-Fortin-Lemieux", "DFL", "Gelbach", "RIF decomposition", "wage gap decomposition", "sp.decompose", "sp.oaxaca".
The English summary is being prepared. Showing the original description.
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or get distribution stats.
The English summary is being prepared. Showing the original description.
Detects market top probability using O'Neil Distribution Days, Minervini Leading Stock Deterioration, and Monty Defensive Sector Rotation. Generates a 0-100 composite score with risk zone classification. Use when user asks about market top risk, distribution days, defensive rotation, leadership breakdown, or whether to reduce equity exposure. Focuses on 2-8 week tactical timing signals for 10-20% corrections.
The English summary is being prepared. Showing the original description.
Detect IBD-style Distribution Days for QQQ/SPY (close down at least 0.2% on higher volume), track 25-session expiration and 5% invalidation, count d5/d15/d25 clusters, classify market risk (NORMAL/CAUTION/HIGH/SEVERE), and emit TQQQ/QQQ exposure recommendations. Use after market close, before TQQQ exposure changes, or as input to FTD/market-state frameworks. Does not execute trades.
The English summary is being prepared. Showing the original description.
Write and distribute launch and publicity content across LinkedIn, X/Twitter, Instagram, Discord, Medium, Substack, and YouTube. Produces per-platform copy that does not read as AI-written (no em dashes, no "thrilled to announce", no engagement-bait), plus the exact image/video specs and character limits each platform wants. Use this skill whenever the user wants to announce, launch, publicize, promote, cross-post, or share anything - a product, a feature, an open-source release, a research paper, a blog post, a demo video, a milestone, a job opening, or a conference talk. Trigger it on phrases like "post this on LinkedIn", "write a launch tweet", "announce this", "share this in Discord", "turn this into a thread", "what should I post", "write a Medium article about", "help me with distribution", "draft a YouTube description", "make this sound less like AI", or "de-slop this post". Also use it when the user has just finished shipping something and asks how to get it in front of people.
The English summary is being prepared. Showing the original description.
Optimize workload distribution across workers, processes, or nodes for efficient parallel execution. Use when asked to balance work distribution, improve parallel efficiency, reduce stragglers, implement load balancing, or optimize task scheduling. Covers static/dynamic partitioning, work stealing, and adaptive load balancing strategies.
The English summary is being prepared. Showing the original description.
Analyzes code files and reports statistics including line counts, file counts by extension, and total size. Use this skill whenever the user wants to understand the composition of a codebase - asking about "how many lines of code", "what file types exist", "code distribution", or needing a quick audit of project size and structure. Make sure to invoke this skill when users mention analyzing codebases, counting lines, checking file distributions, or auditing code.
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, 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), choosing genome-vs-transcriptome alignment for downstream peak vs m6Anet workflows, recording antibody clone and lot metadata for cross-batch reconciliation, detecting failed IPs via saturation curves and IP/input distribution shape, or generating IP-over-Input bigWig tracks for visualisation.
The English summary is being prepared. Showing the original description.
Visualises RNA-modification data with transcript-feature metagene plots (Guitar GuitarPlot; MetaPlotR; deepTools computeMatrix scale-regions), peak-centred heatmaps (ComplexHeatmap; deepTools plotHeatmap), IP-vs-input paired browser tracks (log2 IP/input bigWig via deepTools bamCompare; pyGenomeTracks; Gviz; IGV/UCSC track hubs), DRACH sequence-logo plots (ggseqlogo; MEME), feature-distribution stacked bars, and volcano/MA plots for differential modification. Establishes stop-codon enrichment in the metagene plot as the biological QC anchor for any MeRIP dataset (Dominissini 2012; Meyer 2012). Use when producing the canonical metagene plot with stop-codon enrichment as a QC anchor, building paired IP/input genome-browser tracks at single-locus resolution, plotting peak-centred heatmaps clustered by condition, summarising peak distribution across transcript features, generating DRACH motif logos as sanity checks, rendering volcano plots of differential m6A, or reproducing the stop-codon enrichment plot.
The English summary is being prepared. Showing the original description.
Plot per-gene mutation distributions on a protein-domain map (lollipop / needle plots) showing mutation position, recurrence count, and variant classification with maftools, g3-lollipop, trackViewer, and ProteinPaint. Use when visualizing recurrent mutation hotspots on a single gene's protein, marking domain boundaries from UniProt/Pfam, comparing missense vs truncating distributions, or contrasting two cohorts on the same lollipop.
The English summary is being prepared. Showing the original description.
Comprehensive quality control for CLIP-seq libraries (eCLIP, iCLIP, iCLIP2, PAR-CLIP) covering library complexity (preseq), FRiP, IDR replicate reproducibility, read-distribution metagene, SMInput vs IgG control rationale, rRNA / snoRNA contamination, fragment-length distribution, and ENCODE-compliance thresholds. Use when assessing whether a CLIP library passed, deciding lenient vs stringent peak thresholds, comparing replicates with IDR rescue and self-consistency ratios, or distinguishing failed IP from over-amplified library.
The English summary is being prepared. Showing the original description.