leeguooooo/prompt-language-coach
Cursor rule Cursor
Real-time language coaching. Corrects your writing in your target language before answering every prompt.
371 tagged claude-code-plugin, measured the same way as everything else here.
Browse within: codex-skills 144agentic-framework 143copilot-skills 143opencode-skills 143ai-coding 39claude-code-skills 33gemini-cli-extension 33claude-ai 27ai-assisted-development 25Multi-Agent 21institutional-memory 21ai-tools 14agent-orchestration 13subagents 13
leeguooooo/prompt-language-coach
Cursor rule Cursor
Real-time language coaching. Corrects your writing in your target language before answering every prompt.
Cursor rule Cursor
Cladding is available only in this project. Do not initialize or invoke Cladding for ordinary work. Use the cladding-init skill only when the user explicitly names Cladding and asks to initialize, adopt, or refresh it.
Cursor rule Cursor
ControlFlow orchestration: state machine, tier routing, Task delegation to controlflow subagents.
Cursor rule Cursor
TokenDiet honesty contract for LLM cost. Apply whenever the conversation is about LLM API cost, spend, token usage, prompt caching, batching, model choice/downgrade, or "how much will this save." Enforces: describe technical waste + published provider rates only, NEVER a fabricated dollar total.
Cursor rule Cursor
Report slop-mop tool friction — when sm itself blocks valid work, file a barnacle instead of routing around it.
Cursor rule Cursor
Product Manager Guidelines for AI-Native Development.
Cursor rule Cursor
Search Wire memory for relevant context when connected.
Cursor rule Cursor
Ken, Thompson-mode systems discipline. Think first, build bottom-up, brute force until proven, rewrite over patch.
PhAlves23/prompt-engineering-skill
Cursor rule Cursor
Optimize and rewrite prompts using proven prompt engineering techniques. Invoke when the user wants to improve, optimize, or rewrite a prompt, or pastes a prompt draft asking to make it better.
Cursor rule Cursor
Agent Inspector - AI Agent Security Analysis (scan, correlate static ↔ dynamic).
Cursor rule Cursor
You are a lazy senior developer. Lazy means efficient, not careless. The best code is the code never written.
Cursor rule Cursor
Plumber, root cause first. Always fix the pipe, not the floor.
Cursor rule Cursor
Software factory house rules. Use when running a factory lane or /feature /bug /review /ci /telemetry /lead.
mzored/superpowers-cc-to-codex
Cursor rule Cursor
Scripts — Core runtime adapter and utilities for Codex CLI integration.
Cursor rule Cursor
Cursor rule "cursorrules" from s977043/river-review, covering river reviewer — cursor agent rules, npm i -g @s977043/river-review, verify: river --version, https://river-reviewer.s977043.dev/docs/quickstart and when to run river reviewer.
Cursor rule Cursor
Global RTK + Context Mode enforcement — hard requirements for all Cursor workspaces.
Cursor rule Cursor
Douchebag mode — vulgar gym-bro-chad persona with scoped intensity, voice-marker discipline, and full technical accuracy.
Cursor rule Cursor
DeepInit projection provenance (R3) stage: EMIT → PROJECT (cursor) runid: run-2026-06-13-kemal-e2e source: AGENTS.md (lean tier) — deterministic projection, no new findings note: content inside the DEEPINIT markers is owned + regenerated; edit OUTSIDE them. -->.
Cursor rule Cursor
Offer init-deep only when the user explicitly asks to generate or refresh agent documentation.
Cursor rule Cursor
Premium keynote-style UI with refined motion. Dark, minimal, cinematic reveals. Trigger words — "premium," "polished," "cinematic," "Apple-like," "keynote," "launch page," "product reveal," "elevate this screen," "audit this UI.".
PlanVault/ai-engineering-playbook
Cursor rule Cursor
JavaScript / TypeScript Backend Execution Agent (Node.js / Express / Fastify / NestJS).
Cursor rule Cursor
Use Agent Mesh to ask and answer cross-project questions.
Cursor rule Cursor
Decorate Japanese GitHub Markdown with mojiemoji before posting.
Cursor rule Claude CodeCursor
A source-code security assessment system for vulnerability checks, architecture reviews, penetration testing, red-team analysis, compliance checks, and reports.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: