Cross-agent skill: one-command check & update for all AI CLI tools, Skills and Plugins. Works with Claude Code, Codex, Hermes, and any agent that supports SKILL.md. Auto-discovers npm/pipx/brew/winget/cargo/go tools, Agent Skills (npx skills), Claude Code Plugins. Detects available updates and applies them. First run…
A lightweight project-maintenance workflow documented in Chinese and English. It reads the project's current files and records what is confirmed, inferred, unknown, changed, and verified.
Initialize or improve AGENTS.md files that define how coding agents operate in a repo. Use when asked to set up or replace an agent init command (Codex, Claude), standardize multi-agent behavior, or audit an existing AGENTS.md for clarity, commands, boundaries, and repo-specific context. For Claude Code, also create…
Create new skills, modify and improve existing skills, and measure skill quality. ALWAYS use this skill when users want to create a skill from scratch, edit or optimize an existing skill, extract a skill from a conversation, test a skill, or optimize a skill's description for better triggering accuracy. Also trigger…
A Chinese-language guide for producing growth strategies. It first classifies the request, then creates a plan using models, experiments, channels, metrics, and stored working notes.
Execute approved bounded browser Test DSL cases with fresh isolated contexts and auditable attempts. Use when running browser tests, reruns, regression checks, or blocked execution diagnostics.
Skill "README" from subhansh-dev/agent-maxxing, covering agent maxxing, ⚡ quick start, step 1: clone the repo, step 2: install for your agent and step 3: restart your agent.
A lightweight way to divide coding work into task groups, assign each group to a coding agent, and review the results in stages. The main agent plans and checks the work while each worker handles its assigned batch.
Generate boilerplate for new API endpoints and frontend pages following this project's conventions (flush/commit transaction pattern, ownership enforcement, domain returns). Use when: adding a new resource, creating CRUD endpoints, wiring up a new frontend page, or asking 'how do I add a new feature end-to-end.'.
Transform existing web application interfaces into Windows 98, Windows XP, Windows 7, or Japanese freeware 2000s desktop styles while preserving behavior. Use for repository-level retro UI conversions, not for greenfield mockups or bitmap-only artwork.
Use when planning or continuing non-trivial project work: project plans, roadmaps, decomposition, large changes, feature builds, migrations, rewrites, multi-step work, 10+ tool calls, multiple phases or sessions, scope changes, or verifiable spec compliance. Also use as reference when .planning/ or an existing…
Generate anime fan posters, scenes, stylized illustrations, and character renders for existing anime, game, visual-novel, or adjacent Japanese-style IP characters with strong identity preservation. Use when the user has only a rough idea in Chinese, cannot write a strong prompt, wants the agent to infer likely…
Use when researching, scripting, sourcing, producing, revising, or quality-checking Chinese or English AI and technology talking-head, presenter-led, voiceover, product-demo, explainer, or social videos whose claims need traceable evidence, real interfaces, synchronized narration, B-roll, or final media QA.
Delegate coding, repository inspection, comparisons, web research, and public X search from Codex to the locally installed Grok Build CLI on Windows. Use when a user asks to run or consult Grok, resume Grok Build authentication, compare Codex and Grok, inspect or modify a project with Grok, or perform public X…
Review the user's recent AI coding threads across Claude Code, OpenAI Codex, and Cursor to learn how THEY prefer to work — the preferences and corrections they keep repeating — and to spot places where a missing rule or script made the agent repeat work, then propose and (on approval) write those updates back into…
Create Vidiohalo one-click talking videos or viral remakes through natural-language conversation. Use when a user wants to turn a script into a talking video, remake a reference or social video, upload/select Vidiohalo assets, start a billable generation, or check its progress.
Run scheduled or manual creator curation that turns recent high-quality X posts into verified image-and-caption packs for Douyin and Xiaohongshu review, with optional private delivery to a pinned WeChat iLink bot review chat or confirmed File Transfer Assistant self-chat. Use when Codex needs to discover, verify…
Use for Android and Compose UI design decisions that must adapt to app domain, target users, data sensitivity, environment, accessibility, performance and platform context after build/tests pass.
Repository-agnostic Neneko CR workflow for triaging, reviewing, fixing, reporting, approving, and optionally merging GitHub pull requests across any project. It separates external-PR review from own-PR maintenance, checks current-head CI and review threads, verifies problem necessity and solution fit, requires an…
Builds a release marketing pack from README Version History: device screenshots, GenerateImage feature board and phone/web mockup posters, and a newsletter draft. Asks for brand/app icon (if not already defined) and platform (Android, iOS, or web). Use when the user says promote release, marketing posters, release…
Use when a learner wants to understand, practice, or build durable skill in a technical or analytical subject instead of outsourcing the thinking to an agent.
A routing skill that searches a library of more than 300 skills and identifies the best match for a task. It is used when no currently installed skill fits or when someone asks to find a skill.
Translate engineering-heavy progress updates, completion reports, errors, code-review findings, implementation summaries, and technical explanations into concise, accurate plain language centered on what happened, what it means for the user, evidence, limitations, and next action. Use when the user asks for…
★not rated 2 1mo agoA105 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: