发现 Skills

Use when you have a spec or requirements for a multi-step task, before touching code

Red team engagement planning is the foundational phase that defines scope, objectives, rules of engagement (ROE), threat model selection, and operational timelines before any offensive testing begins.

Use when legacy prompts or older framework flows reference `product-manager` and you need the modern runtime to resolve that capability cleanly.

Control the Chrome browser using 71 MCP tools — screenshots, clicks, form filling, downloads, network capture, TTS, history, cookies, and emulation. Use when working with browser automation.

Generate a complete MCP server implementation optimized for Copilot Studio integration, with proper schema constraints and streamable HTTP support

Automatically censor profanity in messages by replacing with asterisks

Expertise in LLVM-based code obfuscation techniques including Obfuscator-LLVM (OLLVM), control-flow flattening, string and constant encryption, instruction virtualization, and anti-analysis methods. Use this skill when working on code protection, anti-reverse engineering, or implementing custom obfuscation passes.

Fetches comments and reviews from the current GitHub Pull Request and formats them as Markdown.

Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check deployment status, verify serving endpoints, or clean up resources by undeploying models and deleting endpoints. Use when asked to deploy models on Agent Platform, list available Model Garden models, check if a model is deployable, query deployment cost, troubleshoot deployment errors (like quota limits), or undeploy/clean up endpoints. Also use when copying and deploying a 1P Tuned Model. Don't use for public Vertex AI deployments (use the `vertex-deploy` skill) or for running model evaluations (use the `agent-platform-eval` skill).

Validate alignment quality with insert size distribution, proper pairing rates, GC bias, strand balance, and other post-alignment metrics. Use when verifying alignment data quality before variant calling or quantification.

Generate consensus FASTA sequences by applying VCF variants to a reference using bcftools consensus. Use when creating sample-specific reference sequences or reconstructing haplotypes.

Exports publication-ready figures in various formats with proper resolution, sizing, and typography. Use when preparing figures for journal submission, creating vector graphics for presentations, or ensuring consistent figure styling across analyses.

Calculate linkage disequilibrium statistics (r², D'), perform LD pruning for population structure analysis, identify haplotype blocks, and visualize LD patterns using PLINK, scikit-allel, and LDBlockShow. Use when calculating LD or pruning variants.

MAGeCK (Model-based Analysis of Genome-wide CRISPR-Cas9 Knockout) for pooled CRISPR screen analysis. Covers count normalization, gene ranking, and pathway analysis. Use when identifying essential genes, drug targets, or resistance mechanisms from dropout or enrichment screens.

Annotate ChIP-seq peaks to genomic features and nearest genes. Classify peaks as promoter, exon, intron, or intergenic using ChIPseeker (R), HOMER annotatePeaks.pl (CLI), or Python (pandas/pyranges). Supports pre-built annotation databases and custom GTF files. Handles promoter definition, feature priority, category collapsing, and signed distance-to-TSS. Use when assigning genomic context to ChIP-seq peaks or linking peaks to target genes.

Quality control, filtering, and normalization for single-cell RNA-seq using Seurat (R) and Scanpy (Python). Use for calculating QC metrics, filtering cells and genes, normalizing counts, identifying highly variable genes, and scaling data. Use when filtering, normalizing, and selecting features in single-cell data.

Protein grouping and inference from peptide identifications. Use when resolving protein ambiguity from shared peptides. Handles protein groups and protein-level FDR control using parsimony and probabilistic approaches.

Python population genetics with scikit-allel. Read VCF files, compute allele frequencies, calculate diversity statistics, perform PCA, and run selection scans using GenotypeArray and HaplotypeArray data structures. Use when analyzing population genetics in Python.

Analyze time-series RNA-seq data using limma voom with splines, maSigPro, and ImpulseDE2. Identify genes with dynamic expression patterns. Use when analyzing time-series or longitudinal expression data.

Create portable bioinformatics pipelines with Workflow Description Language (WDL) using Cromwell or miniwdl execution engines. Use when running GATK best practices pipelines, working with Terra/AnVIL platforms, or building workflows for cloud execution on Google Cloud or AWS.

Codebase structure and organization audit across 13 dimensions (SA1-SA13): directory consistency, naming conventions, folder depth, colocation, barrel exports, separation of concerns, file size distribution, dead code, complexity distribution, duplication, root organization, documentation, hotspots. Tool-driven with CodeSift primary and CLI fallbacks (cloc, knip, dep-cruiser, jscpd, eslint, git mining). Flags: full (default), [path], --naming, --size, --dead-code, --duplication, --hotspots, --quick, --fix.

You are the compliance auditor for `/legal compliance <url>`. You scan a website for compliance gaps across multiple regulatory frameworks and produce a scored compliance audit report with specific findings, evidence links, and prioritized remediation recommendations.

GROWI main application (apps/app) specific commands and scripts. Auto-invoked when working in apps/app.

Control OpenCode directly via the Agent Client Protocol (ACP). Start sessions, send prompts, resume conversations, and manage OpenCode updates.