A Chinese-language guide for turning computer-vision and computer-graphics research papers into complete, easier-to-read academic HTML articles. It explains the original paper's sections, formulas, figures, tables, algorithms, experiments, limitations, and appendices.
Use when an interviewer needs an evidence-driven interview guide, a live follow-up probe, or a multi-round handoff based on a candidate resume, job description, interviewer perspective, and any previous interview questions and candidate responses.
This skill should be used when writing, reviewing, converting, or executing terminal commands for native Windows PowerShell on Windows, including requests like "convert this Bash command", "use PowerShell syntax", "Windows Terminal command", "run this on Windows", or "fix this PowerShell command". It keeps commands in…
A local backup system for important configuration files, such as SSH or shell settings. It watches selected files and saves changed versions in separate Git histories.
Analyze and document the flow of a code feature, generating a markdown file and an interactive HTML page with flow diagrams and function reference tables.
Use when designing, orchestrating, or executing autonomous multi-agent coding loops with financial budget caps, minimal fixes, and continuous dev-QA gates.
Test web applications in real browsers via Chrome DevTools Protocol including DOM inspection, console analysis, network profiling, performance auditing, Lighthouse CI, and visual regression.
Compresses AI agent session logs (.log, .out, .txt, .trace over 10KiB) to .zst, .xz, .gz, or .tar.gz (Windows), saving 77%-99.9% disk space. Purges empty 0-byte logs, skips locked and in-flight files, safe for concurrent multi-instance running agents. Use when wrapping up, ending sessions, or asked to clean logs…
Design or generate original warm humanist editorial illustrations built from sparse hand-drawn near-black gestures, warm off-white abstract systems, and one flat muted background; or semantically redraw a user-uploaded image into the same visual language. Text-only generation retains the v2.1.0 workflow unchanged.…
Generate a complete, production-ready design system from a single brand color. Outputs OKLCH color palettes, W3C Design Tokens (JSON), CSS custom properties, component styles (Button, Card, Input, Badge, Alert, Modal, etc.), and a live preview HTML page with Light/Dark theme toggle. Trigger this skill when the user…
Implements new Agent Skills for the project. Identifies the AI coding tool (Cursor, Claude Code, Gemini CLI), ensures specification compliance, and provides specialized templates. Use when creating, authoring, or adding a new skill, or when the user asks about Agent Skills format or SKILL.md.
Use when changing software whose existing behaviour matters — fixing bugs or regressions, refactoring, migrating schemas or APIs, changing auth, payments, webhooks, persistence, or user-visible behaviour, removing code, resuming inherited work — and when reviewing such changes or judging whether they are done. Every…
Plan, delegate, and accept a durable, git-tracked Goal Ledger for multi-phase or long-running work: .goal-ledger/GOAL.md plus phase-NNNN.md files, a planner/executor role split so a stronger model plans and reviews while cheaper models run the phases, approval gates, an isolated goal branch, committed recovery…
Create, update, and validate repository-local AI agent context files such as AGENTS.md, .agents/core.md, .agents/routing.md, provider-specific profiles, and task SKILL.md routing. Use when an AI coding agent (Codex, Claude Code, Gemini, Copilot, Cursor, or others) is asked to make AGENTS.md or SKILL instructions…
A production workflow for Himice brand, product, case-study, and social-media videos. It covers locking brand facts, planning direction and shots, arranging reference assets, writing prompts for video models such as Seedance, maintaining continuity, compositing, and fixing failed shots.
Run long-term, evidence-based adaptive learning and reconnect named study requests to local project records across sessions. Use when a learner says to start, continue, or resume learning a subject; for systematic study plans, source-grounded teaching, layered practice, review, or maintaining a knowledge graph and…
Use at the start of any session, or when a prompt arrives without an explicit skill named. Reads the installed skill library at runtime, matches prompt intent against skill descriptions, resolves prerequisite chains, and outputs the correct skill sequence with a ready-to-execute trigger — without requiring the user to…
Use when the user wants to compile work evidence into an operational artifact — daily recap, weekly recap, ADR, session handoff, client update, retro, or loose-ends triage. These are presets of the same engine: evidence → normalization → preset → artifact. The input doesn't change, the preset does. Triggers on…
★not rated 1 3mo agoA0 tokens
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: