Machine Learning

Detects and prevents manual edits to release-please managed files (CHANGELOG.md,version fields in package.json, pyproject.toml, Cargo.toml). Provides conventionalcommit templates. Use when editing changelogs, version bumps, release files, orwhen user mentions "release", "changelog", "version bump", or "conventional commits".

GO Feature Flag (GOFF) self-hosted feature flag solution with OpenFeatureintegration. Covers flag configuration, relay proxy, targeting rules, rollouts.Use when user mentions GO Feature Flag, GOFF, gofeatureflag, self-hostedfeature flags, or flags.goff.yaml configuration.

Skill for validating and repairing evidence references in the dismech knowledge base. Use this skill when working with evidence items in disorder YAML files, validating that snippet text matches PubMed abstracts, and repairing misquoted or fabricated evidence. Critical for ensuring scientific accuracy and preventing AI hallucinations.

Python project setup, dependencies, and lockfiles with uv package manager. Coversuv init, uv add, uv remove, uv lock, uv sync, and pyproject.toml configuration.Use when user mentions uv, creating Python projects, managing dependencies,lockfiles, pyproject.toml, or Python packaging with uv.

Génère des notes de release HTML orientées utilisateurs finaux. Transforme les commits techniques en descriptions accessibles sans jargon.

Extract videos from all enabled YouTube channels in channels.yaml. Use for batch updating video lists before downloading transcripts overnight, when the user mentions "sync channels", "update video lists", "refresh channels", or before running download-all-transcripts.

Build and publish Python packages with uv and modern build tools. Covers uv build,uv publish, pyproject.toml, versioning, entry points, and PyPI publishing.Use when user mentions building packages, publishing to PyPI, uv build, uv publish,package distribution, or Python wheel/sdist creation.

Investigate website structure and debug web scraping using Chrome DevTools MCP. Use when analyzing documentation frameworks, debugging extraction issues, understanding HTML structure, investigating why web content isn't being captured correctly, or exploring API documentation sites. Covers Redocly, Swagger UI, and other modern documentation frameworks.

Detect unused dependencies in Rust projects for cleaner Cargo.toml files and faster builds.Use when auditing dependencies, optimizing build times, cleaning up Cargo.toml, or detecting bloat.Trigger terms: unused dependencies, cargo-machete, dependency audit, dependency cleanup, bloat detection, cargo-udeps.

Docker Compose orchestration for Vigil Guard v2.0.0 microservices (11 services). Use when deploying services, managing containers, troubleshooting Docker network issues, working with vigil-net, configuring docker-compose.yml, handling service dependencies, or working with 3-branch detection services (heuristics, semantic, prompt-guard).

Python-specific testing practices with pytest, fixtures, mocking, async testing, coverage configuration, and uv execution rules. Activate when working with pytest files, conftest.py, test directories, pyproject.toml testing configuration, or Python test-related tasks.

Develops data processing pipelines, integrations, and machine learning scenarios in SAP Data Intelligence Cloud. Use when building graphs/pipelines with operators, integrating ABAP/S4HANA systems, creating replication flows, developing ML scenarios with JupyterLab, or using Data Transformation Language functions. Covers Gen1/Gen2 operators, subengines (Python, Node.js, C++), structured data operators, and repository objects.

This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.

Testing patterns for LLM-based applications. Use when testing AI/ML integrations, mocking LLM responses, testing async timeouts, or validating structured outputs from LLMs.

Ansible automation workflow guidelines. Activate when working with Ansible playbooks, ansible-playbook, inventory files (.yml, .ini), or Ansible-specific patterns.

Best practices for building CLI applications across languages. Covers CLI design principles (Unix philosophy, command structure, subcommands vs flags), argument parsing (required/optional args, flags, environment variables, config files, precedence), user interface (help text, version info, progress indicators, color output, interactive prompts), output formatting (human-readable vs machine-readable JSON/YAML, exit codes), error handling (clear messages, suggestions, debug mode), cross-platform considerations (paths, line endings, terminal capabilities), testing strategies (integration tests, output verification, exit codes), documentation (README, man pages, built-in help), and language-specific libraries. Activate when working with CLI applications, command-line tools, argument parsing, CLI utilities, argument handling, commands, subcommands, CLI frameworks, or building command-line interfaces.

Comprehensive incident response skill for security incident detection, containment, investigation, and recovery. Includes alert triage, severity classification, evidence collection, root cause analysis, and post-incident documentation with automated playbook execution.

This skill should be used when a user wants to create Chat Memo update release materials, specifically to generate an HTML poster and a markdown update description document for a new version release. Use this when a user says "发布新版本", "创建更新", "生成更新海报" or similar phrases, or provides version information and feature lists for a release.

Provides intelligent context-aware PM workflow guidance with automatic phase detection. Prioritizes 6 natural workflow commands (plan, work, sync, commit, verify, done) for streamlined project management. Auto-activates when user mentions planning, implementation, verification, spec management, or asks "what command should I use". Detects workflow phase and suggests optimal command path. Provides learning mode for new users. Prevents common mistakes and offers error prevention. Works with pm-workflow state machine (IDEA → PLANNED → IMPLEMENTING → VERIFYING → VERIFIED → COMPLETE).

SAP HANA Machine Learning Python Client (hana-ml) development skill. Use when: Building ML solutions with SAP HANA's in-database machine learning using Python hana-ml library for PAL/APL algorithms, DataFrame operations, AutoML, model persistence, and visualization. Keywords: hana-ml, SAP HANA, machine learning, PAL, APL, predictive analytics, HANA DataFrame, ConnectionContext, classification, regression, clustering, time series, ARIMA, gradient boosting, AutoML, SHAP, model storage