prodgate
QA that ends in safe-for-production: state-bug hunting with proof, in rounds, on frozen commits.
The most recently added listings, newest first. To search them, choose “Newest on findsafeskills” in search.
QA that ends in safe-for-production: state-bug hunting with proof, in rounds, on frozen commits.
From a skill or an idea to a priced, tested offer with evidence caps on every score.
Visual Learning Notes: compact, hand-copyable visual study notes for technical subjects, with handwriting blueprints, A4 PDFs and Excalidraw diagrams.
Design skills for Claude by Lóránt: processes and rules from practice, packaged for anyone to use.
A morning brief, an evening review and a signals digest, with every failed step printed at the top.
A website and a CRM for a small service business on one Cloudflare Worker and one D1 database.
Dictate a request the way it comes; Koe turns it into a prompt Claude understands. A free skill for Claude.
The launch-kit skill: gets a GitHub repository ready to launch and scores it from 0 to 100.
Emil Kowalski's design skills, adapted for SwiftUI. Unofficial; based on emilkowalski/skills (MIT).
Read-only mirror of Neurologyca’s agent skills for Claude Code, Cursor and Codex. Proprietary; requires a DevLab account.
Angular team kit for coding agents.
AI Werk Skills: open Agent Skills for intake, orchestration, eval and governance, release and operations.
Chinese short-video text effects for AI agents: 12 text effects and 10 interactive overlays. Say it in one sentence and the agent picks a style, checks Chinese word segmentation and line breaks, then exports MP4 or transparent ProRes 4444 / WebM. Seeded and deterministic frame by frame on the same machine and browser; code under MIT.
Skills that teach an AI agent to build, call with and review OmniDimension voice agents
Agent skill that turns Pinterest/Dribbble references into built layouts: SaaS apps, CRM dashboards, landing pages, Figma-style effects, GSAP motion and logo splash. Works with Claude Code, Codex, Trae, Cursor, Gemini CLI and more.
Upstream drilling and well-lifecycle advisory agents: 17 agent contracts, 10 skills and a deterministic advisory MCP. Advisory only — never actuates.
Translate whole books with AI agents, end to end, at low token cost.
Executive-brief reply shaping for Claude Code. Decision first, one thread at a time, park list for the rest.
/vodcut, an open-source Claude Code skill: watches an entire stream VOD on your machine (whisper.cpp + loudness + reaction cues), verifies the best moments on frame sheets, cuts them 1080x1920 and opens each one as an AI Producer project for captions and export. The README's one-paste prompt runs it end to end.
Claude Code skill & plugin to remove dead code: commented-out code, console.log/var_dump/print debug statements, unused imports and unused functions in 40+ languages
Claude Code plugins by rewin0087
Marketplace für das analyse-prompt Plugin: Prompts prüfen, klären und mit echten Probeläufen schärfen.
Claude Code skill for websites that don't look AI-generated. Builds or redesigns a whole site around one idea only your product could use, with a blind AI design critic, every page and state, motion, accessibility and SEO checks, and before/after images. Works with Base44.
cc-sessions: see and safely clean up Claude Code sessions.
The Development Radio plugin: episode search, show notes, primary sources and timed transcripts.
Evidence-first AI data-leakage reviews as an agent skill for Claude Code, GitHub Copilot and Cursor, with offline synthetic canary capture audits, a PDF report and Jira/Notion/Slack task exports. By CTOside.
Plugins by amitauti
ODIN by Viliha: your company's rules and decisions in every AI agent (Claude Code, ChatGPT and more)
Minimal parallel agent orchestration for Claude Code. One lead plans the work as threads in PLAN.md; background workers build them side by side, coordinated by file locks and a shared log. Markdown-only state, no dependencies.
A quiz duel that keeps you up to speed while the AI codes: short quizzes about the code Claude writes, in an RPG battle. Claude Code plugin + MCP server.
Crescentic's session-logger plugin for Claude Code.
Claude Code mod that shows the topic of the conversation in one line above the prompt
Branchline: a live Git history pane beside the chat, for Claude Code
The UserJot plugin: your feedback board, roadmap, changelog, conversations and help center in Claude.
Claudia: an animated, character-themed look for Claude Code in the Claude desktop app (unofficial fan theme)
One Claude Code skill: the whole YouTube upload package, checked by code, with rendered thumbnails.
Guardrails that keep AI-generated code at production quality.
AMICUS: audit a quantitative social-science paper against 14 methods checklists and a universal checklist, inside Claude Code
Claude skill for designing native Lian Li L-Connect 3 Universal Screen 8.8" templates.
Skills de áudio para o Claude: engenharia de som, mixagem, masterização e loudness.
Career Harness: a Claude Code plugin for job search, CVs and applications.
Apuntes de clase ORT: Vimeo → Notion, transcripción local.
Evidence-first tenant isolation reviews as an agent skill for Claude Code, GitHub Copilot and Cursor, with synthetic GET probes, a PDF report and Jira/Notion/Slack task exports. By CTOside.
Windows desktop todo widget you share with Claude — tag a task @claude, press ▶, review the result. CLI + MCP + Claude Code plugin.
Interlace: check what coding agents ship. subagent-gateway sends the heavy reading to read-only Haiku workers and shows what every agent is doing.
envoy1084's skills, plus the external skills they build on, pinned to tested commits.
A minimal, muted one-line status line plugin for Claude Code
Lie Eater: a Claude Code mod that checks the proof when a coding AI says "done".