Automation
Task automation and scripting
auto-dream
by Icattj
Automatic memory consolidation inspired by Claude Code's autoDream/KAIROS. Runs as a background cron job every 24h — reviews recent sessions, consolidates memory, prunes stale entries, and updates MEMORY.md. Zero manual intervention needed. Use to enable always-on memory maintenance.
implement
by robdmc
Execute an implementation plan with parallel agents. Analyzes plan, creates tasks with dependencies, spawns concurrent workers, and runs tests once at the end. Use with a plan file path or --resume to continue.
script-to-article
by arielperez82
Transform raw teleprompter scripts, video transcripts, and show outlines
furniture-design
by mhorvvitz
Design, visualize, and produce buildable plans for custom furniture — both freestanding pieces (tables, shelving, beds, desks) and built-ins (closets, wall units, kitchens, מזנונים, ארונות קיר) — from chat, sketches, or photos to a carpenter-ready package: dimensioned shop drawings, cut list/BOM, hardware schedule. Use for designing furniture, planning a built-in, turning a sketch or inspiration photo into something buildable, working out measurements/cut lists/joinery/hardware, modelling in SketchUp, or iterating with 2D drawings or a 3D view — even without saying "cut list" or "shop drawing." With the SketchUp MCP connector present, it drives it as the 3D backend (real .skp), deferring geometry mechanics to the bundled SketchUp skills. Defaults to metric / Israeli shop conventions (mm, סנדוויץ'/מלמין/MDF sheets, System 32).
gemini-auth-nano-banana
by Kunari-Ely
Build and optimize Gemini or Nano Banana image prompts for any coding agent platform, then optionally execute them through a logged-in Gemini web session instead of an API key. Use when Codex, Claude Code, OpenClaw, Antigravity, or similar agents need structured JSON prompt planning, image-to-image editing, identity-preserving redraws, background replacement, pose changes, compositing, or style-guided variations, and the final prompt sent to Nano Banana should itself be JSON.
skill-orchestrator
by taku15eg
Meta-skill that analyzes every prompt's essential purpose and auto-selects the optimal combination from 950+ public agent skills. Determines intent type (Create/Improve/Secure/Ship/Automate/AI-Native/Research/Communicate), then generates an execution plan with skill dependencies and sequencing. ALWAYS activate this skill as the first step for ANY task. Use when: any task, any prompt, planning, skill selection, workflow design, project kickoff, coding, writing, analysis, debugging, deployment, security, marketing.
organizing-documents-diataxis
by squirrel289
"Apply Diataxis framework to organize workflow output into documentation directories. Use to guide skill output placement: inline by default unless user requests file; rationale-heavy content to docs/architecture/; lookup tables and reference guides to docs/reference/. Avoid standalone analysis summaries in docs root. Composable into any analysis or decision-making skill."
pytincture-dhxpyt
by pytincture
Build or modify apps that use the pytincture framework and the dhxpyt widgetset. Use when asked to create pytincture services, add backend-for-frontend (BFF) classes/policies, generate UI layouts with dhxpyt widgets (grid, form, toolbar, sidebar, tabbar, etc.), or embed pytincture.js for browser-only Python UI scripts.
blender-world-build
by temisangerrard
Use when building or refining Junipali 3D stages/characters in Blender and exporting production-ready GLB assets for the game runtime. Covers scene scale, rig/animation export, naming conventions, and handoff checklist.
d1-do-storage
by Sillyvan
Apply Cloudflare D1 and Durable Object SQLite storage best practices with standard Workers APIs and Drizzle ORM. Use when implementing queries, write flows, schema changes, retries, and performance-sensitive storage paths.
loop-skill
by maxoreric
循环执行的 Skill。当需要重复执行直到满足条件时触发。触发词：循环、loop、重复、直到、until、持续。
git-convention
by yanix2445
Standard de référence pour la gestion de Git. Règles de sécurité, workflows atomiques, conventions de commit et bonnes pratiques de configuration.
codex-converter
by gitgoready
Convert coding-agent sessions between Claude Code and Codex (both directions). Use when the user wants to migrate an in-progress conversation from one agent to the other (e.g. after hitting a quota limit on one side), or when they ask to "convert this Codex session to Claude" / "convert this Claude session to Codex" / "import a Claude session into Codex". Produces a rollout JSONL + registers it in Codex's state DB, or writes a Claude-compatible JSONL into ~/.claude/projects/<slug>/, with a "From Claude" / "From Codex" title prefix that includes the original session name and a local timestamp. Cross-platform - Windows, Linux, macOS.
code-review
by lct1407
Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.
plan-split
by rozwer
Auto-split Plans.md into individual phase-N.md files in docs/plans/. Only creates files that don't exist yet.
brainstorming
by tomwangowa
Use before any creative or implementation work — new features, architecture changes, refactoring, or workflow design. Explores intent through Socratic dialogue, proposes approaches with trade-offs, and produces an approved design before any code is written.
rust-learner
by lywa1998
"Use when asking about Rust versions or crate info. Keywords: latest version, what's new, changelog, Rust 1.x, Rust release, stable, nightly, crate info, crates.io, lib.rs, docs.rs, API documentation, crate features, dependencies, which crate, what version, Rust edition, edition 2021, edition 2024, cargo add, cargo update, 最新版本, 版本号, 稳定版, 最新, 哪个版本, crate 信息, 文档, 依赖, Rust 版本, 新特性, 有什么特性"
convex-cron
by aaronvanston
Scheduled functions and cron jobs in Convex. Use when setting up recurring tasks, cleanup jobs, data syncing, scheduled notifications, or any background automation that runs on a schedule.
Claude-Zeroclaw SKILL
by vaskesvo5321
Status: Active & maintained
hype
by rxxuzi
Document-driven development with test-gated progression. Enforces a disciplined workflow: plan tasks with the user in .hype/TODO.md, document before implementing, track progress in .hype/PROGRESS.md, accumulate project knowledge in .hype/KNOWLEDGE.md, and require all tests to pass before advancing. Language-agnostic — works with any programming language or even non-code projects. Use when: (1) starting new projects with structured planning, (2) implementing features or bug fixes with mandatory test verification, (3) managing development tasks with document-based tracking, (4) the user mentions "hype", "document-driven development", "TODO tracking", or wants a disciplined plan-document-implement-test cycle.
ticktick
by 0juano
Manage TickTick tasks and projects for JMO. Use when the user asks to add, create, or capture a task or todo; list, show, or review pending tasks; complete or check off a task; update a task's priority, due date, notes, or tags; delete a task or list; create or manage a project/list; or see what's due today or overdue. Also handles quick captures like "remind me to..." or "don't let me forget...".
subagent-driven-development
by Jackiexiao
（中文）Use when executing implementation plans with independent tasks in the current session
slack
by HartreeWorks
This skill should be used when the user asks to send Slack messages, check notifications, get a Slack digest, or search message history. Supports multiple workspaces.
aidr
by pc-style
Offload context-heavy but low-complexity codebase work to Aider through a thin CLI wrapper. Use when another AI agent should avoid loading large repository context for tasks like discovery, repetitive refactors, cross-file version bumps, and broad search/explain passes. Supports safe read-only scanning, scoped edit runs, model-mode routing, and setup/model diagnostics.