Claude Skills by black141312

Apply RAII and smart pointers to replace manual resource management in C++

Set up a reliable scheduled job via cron or a systemd timer, with logging and failure visibility

Fix CV model preprocessing mismatch — resize, normalize, mean/std, channel layout, value range

Implement a polished dark mode via semantic tokens and prefers-color-scheme, not naive color inversion

Design a clean, scannable data dashboard — clear hierarchy, restrained color, and fast comprehension.

Build a Grafana/observability dashboard organized around the four golden signals

Export and transform database data to CSV or JSON safely and reproducibly

Add data-quality and schema checks that fail fast on bad data

Transform tabular data with pandas or polars cleanly and reproducibly

Find and remove unused code, exports, and files across the project

Apply a systematic debugging procedure — reproduce, isolate, fix, verify — instead of guessing at fixes

Review a slide deck for clarity, narrative flow, and per-slide density; return concrete fixes.

Remove duplicate and unused dependencies to shrink install size and the dependency tree

Collapse duplicated logic into a single shared implementation

Run npm/pip/etc audit, triage advisories, and apply the safest upgrades

Bump dependencies safely, regenerate the lockfile, and confirm the test suite still passes

Write a repeatable deployment script or checklist that ships the app safely with a rollback path

Build a cohesive design system from tokens up to components, with one source of truth and zero magic numbers

Define color, space, type, radius, and shadow tokens as layered CSS custom properties with semantic roles

Draw a diagram — architecture, flow, sequence, ER, state or dependency — as mermaid, diagram-as-code, or inline text, then show it.

Explain what a diff changes and why, summarizing intent, behavior shifts, and risks for a reviewer

Add a Django view with its URL route and template

Lint docs in CI for broken links, spelling, and style so prose breakage fails the build like code does.

Write a docker-compose stack that brings up the app plus its dependencies for local dev

Write a Dockerfile and .dockerignore that build a small, reproducible image for the app

Add docstrings or JSDoc to public APIs describing behavior, params, returns, and errors

Manage dotfiles and machine setup as a version-controlled, reproducible, idempotent install

Fix retina/HiDPI blur and layout — devicePixelRatio mismatch between canvas backing store and CSS size

Write an end-to-end test that drives the real app through a user flow with Playwright or Cypress

Set up embeddings and a vector store for semantic search or retrieval

Design empty, loading, and error states that orient the user and offer a clear next action.

Add a .env.example and validate required config at startup so missing vars fail fast

Implement a standards-compliant ERC-20 token using OpenZeppelin with tests

Wire up Sentry/error reporting with context, releases, and source maps

Break a task into estimated subtasks with assumptions, dependencies, and a total range

Build an ETL/data pipeline that extracts, transforms, and loads data idempotently

Build a reproducible evaluation harness for a model or agent

Fix images that appear rotated or flipped because EXIF orientation metadata was ignored or double-applied

Explain an unfamiliar region of the codebase by reading it in context and summarizing intent and risks

Add Express middleware for auth, logging, or error handling in the right order

Pull a cohesive block of code into a well-named function or method

Build and maintain an FAQ from real, recurring questions — answer-first, searchable, and kept current.

Add a FastAPI endpoint with Pydantic request/response models and DI

Generate a full favicon and app-icon set (SVG, PNG, Apple touch, manifest) with the correct head markup.

Engineer features for a model without leakage and reproducibly

Build few-shot examples that steer an LLM toward the format and behavior you want

Locate where a feature or behavior lives in the codebase starting from a symptom or user-facing string

Write a bare-metal peripheral driver against a memory-mapped register interface

Diagnose an intermittent failure — a flaky test or a race in real code — and remove the nondeterminism behind it

Build a Flutter widget that owns and updates local state