Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Innate procedural knowledge layer for coding, debugging, and analysis sessions. ACTIVATE when: (1) user says "remember", "save", "log", "follow this rule", "don't forget", "recall", or "what did we learn"; (2) a non-obvious solution, workaround, constraint, or invariant was discovered during this session; (3) starting…
Creates animated video content using HTML5 Canvas and JavaScript. Generates self-contained HTML files with canvas-based animations that can be previewed in a browser and exported to MP4 using Puppeteer and FFmpeg. Use when the user wants to create animated videos, motion graphics, promotional clips, tutorial…
A workflow for running Xiaohongshu accounts, a Chinese social-media platform used for posts and account operations. It stores work in profile-specific folders and uses the xhs command-line tool for live actions.
Explore UI directions by generating several genuinely-different real-data HTML mockups in parallel, serving them so the user picks side-by-side, distilling each pick into locked constraints, and narrowing round by round until approved — then landing the winner in the real stack and refining. Use when the user wants to…
Guides a user and a chat agent through a structured monthly review focused on the benefits gained from using the agent. Use this skill at the end of each month when the user wants to reflect on value created, time saved, friction reduced, knowledge gained, or next improvements. Activate for phrases like: "monthly…
Imitation-write viral social content-marketing notes. Analyzes a reference viral post's structure, style, and traffic logic, then generates original, differentiated content that matches the reference tone while combining your product and selling points — bypassing duplicate detection to iterate quality notes fast. Use…
Delegate bounded, implementation-heavy, repetitive, read-heavy, or independently verifiable coding work from Codex to DeepSeek Harness, preferably through a local Harness MCP worker and otherwise through the official headless CLI. Keep Codex responsible for scope, risky judgment, review, integration, and final…
An AI product-photo workflow for creating Amazon listing images from an original product photograph. It can prepare white-background main images, scene images, and A+ banners, where A+ is Amazon’s enhanced product-detail content.
Explicit-only workflow for coordinating one Codex App background thread per task in Codex-managed worktrees. Use only when the user invokes $codex-managed-worktree-threads. Do not use for natural-language-only parallel work requests, ordinary subagent delegation, manual git worktrees, tmux workflows, Codex CLI worker…
Diagnose live Kubernetes failures (CrashLoopBackOff, OOMKilled, NodeNotReady, ImagePullBackOff, Network/CNI failures, HPA starvation, DNS failures, pending pods) with an evidence-first procedure: capture context, collect signals (events/status/logs), rank falsifiable hypotheses, verify one variable at a time, fix with…
A batch workflow for archiving Douyin favorites or all posts from selected creators into Obsidian. It uses account cookies, rate limits, downloading, transcription, deduplication, and optional scheduled synchronization.
Migrate from ChatGPT to Claude. Trigger on: ChatGPT export/history/migration, switching from ChatGPT, or folders with conversations-.json or chat.html files.
Generate, screen, and rank project, product, company, app, and brand names by checking real domain availability with IsDomainOK. Use when a user asks for naming ideas, available domains, brandable names, TLD comparisons, or wants to avoid suggestions whose domains are already registered or over budget.
A pre-commit code review process with separate checks for general quality and for matching the requested specification. A commit is a saved set of code changes in Git.
Audit this repo's skills + plugins on three axes -- (1) leaks of personal info or Yesterday-internal references in user-facing artifacts, (2) catalog consistency (folder/name/dep/install-target alignment), (3) plugin-spec compliance (Claude Code + Cursor manifest schemas, layout rules). Reports findings as a triage…
Write and review Arabic screen copy with RTL and bidirectional-content guidance. Use for requests combining Arabic interface wording with screen UX decisions, including forms, errors, checkout, navigation, typography, and accessibility. Not for code-only RTL debugging or general translation without product-interface…
End-of-session workflow to leave durable project context for the next chat. Use whenever the user says "handoff," "wrap up," "end of session," "before we end," "close out this session," "let's wrap," "we're done," "wrap this up," "closing out," "starting a new session," or "before I start fresh." Do NOT use for…
Free up disk space by removing dev environment junk — Claude temp, OS temp, browser caches, nodemodules, npm/pnpm/yarn caches, .next builds, Python caches, pip, and VS Code cache. Works on Windows, macOS, and Linux. Use "super" argument for interactive deep-clean mode that discovers hidden space hogs and asks before…
A read-only security audit for DeepSeek Harness extensions, settings, dependencies, and runtime exposure. It looks for risks such as exposed secrets, unsafe file mounts, data leaving the system, persistence, and malware indicators.
Conduct AI/ML research as a science - first-principles reasoning, mechanism-level hypotheses, falsifiable predictions, discriminative experiments, honest evaluation, and claims that survive hostile review. Use when starting or steering an AI/ML research project, deciding what to investigate next, choosing datasets…
Turns a user-defined goal into a structured multi-tool workflow. It scans context, discovers available tools (skills, MCP servers, CLI tools, scripts, project commands), builds an execution plan, coordinates execution, handles blockers, verifies results, and returns a concise operational report. Use when a task spans…
★not rated 2 2mo agoA76 tokens
originalMIT
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: