CI/CD

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

Automated documentation generation specialist for technical specs, API docs, user guides, and knowledge bases with multi-format output

Diagnose and fix CI/CD failures related to Lint errors and test failures. Use when: (1) User mentions CI/CD failures, lint errors, or test failures, (2) User asks to fix code quality issues or make tests pass, (3) User requests to check or verify code before committing/pushing, (4) Working on a task that requires running lint or tests to validate changes. This skill provides systematic workflows for identifying, diagnosing, and fixing common Lint and test errors in TypeScript/React projects using ESLint, Prettier, and Vitest.

Debug Android Flutter apps including runtime errors, build issues, device connection problems, and performance issues. Use when troubleshooting Android-specific problems, crashes, or deployment issues.

Édition de code par symboles avec Serena MCP. Utiliser pour modifier des fonctions, hooks, ou composants de manière précise sans réécrire des fichiers entiers.

Git operations, GitHub CLI, and version control specialist.Handles complex Git analysis, conflict resolution, branching strategies,history investigation, PR management, and advanced Git operations.

Coordinates 9 specialized audit workers (security, build, architecture, code quality, dependencies, dead code, observability, concurrency, lifecycle). Researches best practices, delegates parallel audits, aggregates results into single Linear task in Epic 0.

Memory-First development workflow integrating Serena short-term project memory and Cipher long-term design knowledge for efficient LoRAIro development

批量下载 B 站 UP 最近 N 条视频到 imports，并用 video_pipeline 生成证据包（适合 worker panes 并行跑）。

Spawn a Claude worker to address PR feedback, fix CI failures, or continue work on a pull request. Use when a PR needs updates based on review comments or failing checks.

Execute tasks with velocity and quality. Use when ready to implement after clarity and prioritization are complete. This is the fourth system in the 5-system framework.

Expert guidance for reliable bash script directory navigation and path handling. Use when writing new bash scripts, reviewing existing scripts, debugging directory-related failures, or when mentioned 'directory handling', 'bash paths', 'cd errors', 'script location', or 'git root'. Provides deterministic patterns to eliminate silent failures from unhandled cd, missing set -e, and path resolution issues.

Prettier configuration validation and templates for package.json "prettier" field in MetaSaver monorepos. Includes 4 required standards (prettier field in package.json with string reference only, no separate prettierrc files, prettier in devDependencies, required npm scripts format and format:check). Use when creating or auditing Prettier configs to ensure consistent code formatting via shared library.

ALWAYS use for ANY C# operation: renaming (files/classes/methods/properties/namespaces), finding references/usages ("where is X used"), finding definitions ("where is X defined"), understanding code structure (hierarchies/dependencies/relationships). Roslyn-powered semantic analysis ensures all references are updated correctly across the entire solution.

Implement code quality ratchets to prevent proliferation of deprecated patterns. Use when (1) migrating away from legacy code patterns, (2) enforcing gradual codebase improvements, (3) preventing copy-paste proliferation of deprecated practices, or (4) setting up pre-commit hooks to count and limit specific code patterns. A ratchet fails if pattern count exceeds OR falls below expected—ensuring patterns never increase and prompting updates when they decrease.

Facilitate a sprint or release retrospective focusing on insights, actions, and ownership.

Design system foundation. Colors, typography, spacing. Single source of truth. No raw values.

Place test voice calls via Twilio. Use when testing voice features or debugging voice pipeline. Only works if twilio_place_call.py exists in branch.

Medical document OCR processing for extracting structured clinical data from medical images (prescriptions, lab results, clinical notes). Uses Google Cloud Vision for text extraction and medical NLP for entity recognition. Deploy when processing healthcare documents, extracting patient data, or converting medical images to structured formats.

Provides web search capability for finding current information, documentation, and resources from external sources when local knowledge is insufficient