8 skills found
faugustdev / git-context-controllerStructured context management framework for LLM agents. Implements Git-like operations (COMMIT, BRANCH, MERGE) to manage long-horizon agent memory.
ZeroLu / Ultimate-AI-Media-Generator-SkillOpen-source ai image generator skill and ai video generator skill for Codex, Claude Code, OpenClaw, Cursor, and more. Powered by CyberBara API with Nano Banana, Sora 2, Seedance, and Kling support. No need to master prompt, this skill optimize your prompt for all kinds of creations like slides, anime and much more.
natedemoss / token-surgeonThis skill should be used when the user wants to analyze, audit, optimize, or reduce tokens in a prompt, system prompt, or instruction set. Triggers on phrases like "analyze this prompt", "optimize my prompt", "too many tokens", "trim this prompt", "audit my system prompt", "token-surgeon", or when the user pastes a prompt and asks for feedback on efficiency.
MessiasLima / jules-skillUse this skill whenever Jules (Google's async AI coding agent) is mentioned or implied. Triggers include: starting a new Jules coding task (\"kick off\", \"create a session\"), checking Jules session status or progress, reading a message Jules left, approving or rejecting a Jules plan, replying to Jules mid-task, and scanning for sessions in states like AWAITING_PLAN_APPROVAL or AWAITING_USER_FEEDBACK. Also triggers on bare Jules session IDs (long numeric strings) or any request to monitor, manage, or respond to Jules activity across repos.
udayanwalvekar / clearshotStructured screenshot analysis for UI implementation and critique. Analyzes every UI screenshot with a 5×5 spatial grid, full element inventory, and design system extraction — facts and taste together, every time. Escalates to full implementation blueprint when building. Trigger on any digital interface image file (png, jpg, gif, webp — websites, apps, dashboards, mockups, wireframes) or commands like 'analyse this screenshot,' 'rebuild this,' 'match this design,' 'clone this.' Skip for non-UI images (photos, memes, charts) unless the user explicitly wants to build a UI from them. Does NOT trigger on HTML source code, CSS, SVGs, or any code pasted as text.
viktorvuka / things-todoGenerate a clickable Things 3 import link from tasks discussed in conversation. Use this skill whenever Claude produces a list of actions, tasks, to-dos, next steps, or a project plan that the user might want to track — even if they don't explicitly say "Things" or "todo list." Also trigger when the user says things like "ajoute ça dans Things", "fais-moi une todo", "crée les tâches", "envoie ça dans Things", "make a task list", "send to Things", "plan this out as tasks", or any variation. If a conversation ends with a clear set of actionable items, proactively offer to generate the Things link. Always use this skill instead of outputting a plain markdown checklist when the user could benefit from real task management.
momo2young / humanize-academic-writingTransform AI-generated academic text into natural, human-like scholarly writing for social sciences. Detects AI patterns (repetitive structures, abstract language, mechanical flow) and rewrites with authentic academic voice
reckerswartz / error-detective--- name: error-detective description: >- Correlates Rails errors, log patterns, stack traces, and recent code paths to narrow investigations quickly. Use when diagnosing production-like failures,
