Turns Claude into a senior Angular architect for Angular 17+ standalone components, signals, NgRx, and RxJS patterns.
Official Anthropic skill that drafts internal communications — 3P updates, newsletters, FAQs, incident and leadership reports — in your company's preferred formats.
Official skill that applies one of 10 professional color-and-font themes (or a custom one) to slides, docs, reports, and HTML landing pages.
An output-style skill that reshapes Claude's answers: next action first, numbered steps, no preamble or filler.
Scans a repository and produces an interactive knowledge graph of its architecture, components and relationships.
An interactive advisor that decides whether to scale, test, or kill a growth channel using unit economics, customer quality, and scalability.
A prompt-engineering skill that identifies your target AI tool and returns one paste-ready prompt tuned to that tool's syntax and quirks.
Lists recent local Claude Code and OpenAI Codex conversations for a workspace with one read-only command.
A phase-based playbook for shipping pull requests that maintainers of third-party open-source repos actually merge.
Install, customize, and self-verify the Claude Code statusline — path, git branch, model, absolute token counts, and optional cost.
Restructures a bloated CLAUDE.md / AGENTS.md into a lean Level 1 plus on-demand Level 2 references, with verified zero information loss.
Converts DOCX, PDF, and PPTX files into clean Markdown with eight automatic post-processing fixes.
A quality gate for Claude Code skills: audits your own or others' skills against official best practices and can even open an improvement PR.
An evidence-driven, falsification-first playbook for network, streaming and protocol bugs where the obvious cause is probably wrong.
A Git forensics skill that recovers lost commits, branches and stashes — and proves by content that cleanup won't drop any work.
Sets up, audits, and enforces internationalization in React/Next.js/Vue codebases — from framework config to replacing hard-coded strings and verifying locale key parity.
Measure any OpenAI- or Anthropic-compatible endpoint across six dimensions — availability, request fidelity, speed, concurrency, protocol compliance, and quality regression.
Turns vague requests into precise, testable specifications and structured prompts using EARS syntax.
Sets up and runs Promptfoo-based LLM evaluations, from config files to custom Python and LLM-rubric assertions.
Sets up an end-to-end QA process—test strategy, AAA-style test cases, execution tracking, P0–P4 bug triage, and quality-gate reporting—from ready-made templates and scripts.