发现 Skills
为真实工作流程挑选经过整理的 Skill,连接、安装并开始使用。
flow-next-opencode-sync
Manually trigger plan-sync to update downstream task specs after implementation drift. Use when code changes outpace specs.
flow-next-opencode-work
Execute a Flow epic or task systematically with git setup, task tracking, quality checks, and commit workflow. Use when implementing a plan or working through a spec. Triggers on /flow-next:work with Flow IDs (fn-1, fn-1.2).
flow-next-deps
Show epic dependency graph and execution order. Use when asking 'what's blocking what', 'execution order', 'dependency graph', 'what order should epics run', 'critical path', 'which epics can run in parallel'.
flow-next-export-context
Export RepoPrompt context for external LLM review (ChatGPT, Claude web, etc.). Use when you want to review code or plans with an external model. Triggers on /flow-next:export-context.
starrocks-docs
Look up StarRocks query profile metrics and tuning documentation. Use when you need to understand what a metric means or how to optimize query performance.
hecras_explore_gui
Explores the HEC-RAS GUI to document menus, dialogs, controls, and workflows using win32com automation with screenshot capture. Use when needing to discover menu structure, document dialog controls, capture screenshots for documentation, or explore unfamiliar GUI elements in HEC-RAS. Triggers: explore GUI, screenshot, capture dialog, document menu, HEC-RAS interface, discover controls, GUI automation, menu exploration, dialog documentation, visual documentation.
bio-bedgraph-handling
Create, manipulate, and convert bedGraph files for genome browser visualization. Covers bedGraph format, conversion to/from bigWig, normalization, and signal processing. Use when handling coverage and signal tracks from ChIP-seq, ATAC-seq, or RNA-seq.
bio-format-conversion
Convert between sequence file formats (FASTA, FASTQ, GenBank, EMBL) using Biopython Bio.SeqIO. Use when changing file formats or preparing data for different tools.
bio-restriction-fragment-analysis
Analyze restriction digest fragments using Biopython's Bio.Restriction. Predict fragment sizes, obtain fragment sequences, simulate gel electrophoresis patterns, and perform double digests. Use this when analyzing restriction digest fragment patterns.
bio-long-read-sequencing-nanopore-methylation
Calls DNA methylation from Oxford Nanopore sequencing data using signal-level analysis. Use when detecting 5mC or 6mA modifications directly from nanopore reads without bisulfite conversion.
bio-genome-assembly-scaffolding
Scaffold contigs into chromosome-level assemblies using Hi-C data with YaHS, 3D-DNA, SALSA2, and validate with BUSCO and contact maps. Use when scaffolding contigs to chromosome-level assemblies.
bio-chipseq-super-enhancers
Identifies super-enhancers from H3K27ac ChIP-seq data using ROSE and related tools. Use when studying cell identity genes, cancer-associated regulatory elements, or master transcription factor binding regions that cluster into large enhancer domains.
roblox-game-development
Use this skill for any Roblox-related tasks.
marathon-ralph
Autonomous long-running development from specifications. Use when user wants to build an application from a spec file, run continuous development, or automate feature implementation. Triggers on phrases like "marathon this", "build from spec", "autonomous development", "keep coding until done".
build-inspector
Analyzes build-system topology to identify independent build units, multi-artifact risks, and version-drift hazards.
runtime-inspector
Analyze runtime behavior, process boundaries, and IPC mechanisms to detect 'protocol drift' risks and process lifecycle issues.
wardley-mapping
Create professional interactive Wardley Maps with strategic analysis, evolution rationale, and actionable recommendations. Produces React artifact maps with hover tooltips, dependency highlighting, and a figure legend, plus OWM-format text and structured strategic commentary. Use this skill when the user asks to create a Wardley map or mentions "wardley mapping".
box-automation
Automate Box cloud storage operations including file upload/download, search, folder management, sharing, collaborations, and metadata queries via Rube MCP (Composio). Always search tools first for current schemas.
fal-generate
Generate images and videos using fal.ai AI models
notebooklm
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and running OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
salesforce-development
Expert patterns for Salesforce platform development including Lightning Web Components (LWC), Apex triggers and classes, REST/Bulk APIs, Connected Apps, and Salesforce DX with scratch orgs and 2nd generation packages (2GP). Use when: salesforce, sfdc, apex, lwc, lightning web components.
schema-markup
Design, validate, and optimize schema.org structured data for eligibility, correctness, and measurable SEO impact. Use when the user wants to add, fix, audit, or scale schema markup (JSON-LD) for rich results. This skill evaluates whether schema should be implemented, what types are valid, and how to deploy safely according to Google guidelines.