docs-reconcile
Reconcile normalized CI/PL/BL fields and output mismatch report
Discover DevOps skills, compare source repositories and read the instructions for each workflow.
Reconcile normalized CI/PL/BL fields and output mismatch report
Create, edit, and build Observable Notebooks using Notebook Kit. Use when working with .html notebook files, generating static sites from notebooks, querying databases from notebooks, or using data loaders (Nod...
Sync timetrvlr public assets (embeddings, index files) to/from S3. Use this skill before deploying to ensure S3 has the latest assets. Invoke with /timetrvlr-assets.
Deploy applications to AWS (SageMaker, Amplify, EC2). Use this skill to deploy models, frontends, or manage infrastructure. Invoke with /deploy.
Manage VLM (Vision-Language Model) embedding service and jobs. Use this skill to start the Flask embedding service, run embedding jobs, or train the AE3D autoencoder. Invoke with /vlm-embed.
Work with Jupyter notebooks in the wc_simd project. Use this skill to run, convert, or explore notebooks. Invoke with /notebook.
Manage AWS EC2 instances for GPU workloads and Spark jobs. Use this skill to start, stop, or check status of EC2 instances. Invoke with /ec2.
Manage Docker Spark infrastructure for local development or production (S3). Use this skill to start, stop, or check status of Spark clusters. Invoke with /spark-docker.
Generate text embeddings using Qwen3 models via HuggingFace TEI. Use this skill to embed texts, configure the embedding service, or batch process documents. Invoke with /embed.
Work with IIIF manifests and the Wellcome Collection API. Use this skill to download manifests, extract metadata, or process canvases. Invoke with /iiif.
Explore Hive tables and datasets in the Wellcome Collection data warehouse. Use this skill to query tables, understand schemas, or analyze data distributions. Invoke with /data-explore.
Run tests for the wc_simd project using pytest. Use this skill to run all tests, specific test files, or individual test functions. Invoke with /run-tests.
Create a git commit following this repo's conventional commit style. Use this skill to commit staged changes or all changes. Invoke with /commit.
Ensure quality through testing, documentation, and security audits. Use when asked to add tests, improve test coverage, update documentation, write docs, security audit, review safety rules, or verify protected...
Fix bugs, optimize performance, and maintain code quality in CClean-Killer. Use when asked to fix detection issues, false positives, false negatives, optimize scan speed, improve performance, refactor code, or...
Research and document new parasites, cleanup locations, and hidden data. Use when asked to add a parasite, discover zombie processes, research app persistence, add cleanup locations, or run iterative discovery...
Port CClean-Killer features to Linux and Windows platforms. Use when asked to add Linux support, Windows support, cross-platform compatibility, port a feature, or implement platform-specific scripts.
Git branching strategy and versioning workflow. Use when creating branches, PRs, or releasing versions.
Test-Driven Development workflow. Use when implementing new features with tests first. Activated by "TDD", "test first", "write tests".
Release Workflow - Merge develop to main, bump version, publish to npm, and create GitHub release.
Auto-generate README and API documentation from code analysis
Thorough code review. Use when reviewing PR, checking code quality, or auditing changes.
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for...
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.