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.
Build, validate, index, and query a private local Memory Forest with provenance-aware layers, pointer-first search, and validated root-first retrieval. Use when creating a new forest, checking an existing forest's structure, building its local SQLite index, or retrieving bounded memory trails without exposing full…
Orchestrates end-to-end resilience testing for LLM agents with AgentBreak, including LLM infrastructure failures, prompt injection, agent skill supply-chain risk, guardrail verification, and MCP server/tool failures. Use when the user asks to "test my agent for resilience", "chaos test this agent", "find failure modes…
Set up OpenAI's harness engineering methodology in any repository. Creates the full agent-first infrastructure: AGENTS.md progressive disclosure map, architectural layer boundaries with mechanical enforcement, testing framework, CI pipeline, golden principles documentation, garbage collection scripts, and pre-commit…
Generate and edit images. Saves the image and prints the exact path it wrote. Use when the user wants any visual creative output, an image generated from a description, or wants to modify an existing image in any way — editing, transforming, or adding visual elements.
Use this whenever the user asks to "implement", "add", "build", "create", or "modify" a feature, page, view, component, or module in this Vue project. Three phases: Phase 0 scope analysis (flows + edge cases + UI needs + plan validation, STOP for user), Phase 1 implementation (layered UI → Store → API, Vue 3…
Learn from experience: self-reflection + self-criticism + self-learning + self-organizing memory + cross-session sync. Agent evaluates its own work, catches mistakes, and improves permanently. Compiles confirmed learnings to global config for automatic cross-session persistence. Use when (1) a command, tool, API, or…
Open a browser-based diff viewer showing all current changes in a VS Code-style file tree with syntax-highlighted diffs. Live-reloads as files change. Use when the user wants to "see the diff", "show changes", "what did I change", or "open diff viewer".
A tool for translating English research-paper PDFs into Chinese while keeping the original page layout, including figures, formulas, and images. It accepts an arXiv link, an arXiv ID, or a local PDF.
Bytebell-public local knowledge graph. Discover, search, lookup, and retrieve from code repositories indexed locally by bytebell-server. TRIGGER when using: listknowledge, smartsearch, keywordlookup, retrievefile.
This skill decomposes large tasks into independent units and coordinates parallel execution. It is a PLANNING + COORDINATION tool — it does NOT spawn agents directly. Agents are spawned via Claude Code's built-in /batch command (git worktree-based parallel).
GitHub Knowledge Base - Unified tool for managing local repos, discovering trending projects, and tracking tech hot topics. Use when: (1) searching local GitHub repos, (2) updating repo index, (3) discovering new repos via social media (Xiaohongshu, Twitter/X) and web search, (4) researching topics on Xiaohongshu, (5)…
Guide for creating Claude Code plugins that bundle skills, agents, commands, hooks, and MCP servers for distribution. Covers plugin structure, marketplace.json format, installation, testing, and publishing. Use when the user wants to create plugins, distribute skills/agents, build marketplaces, or mentions…
Extract design decisions, trade-offs, and non-obvious behaviors from a codebase's current source code. TRIGGER when: starting the design analysis pipeline, running /mine-design (Claude Code) or @mine-design (Cursor) before /synthesize-decisions (Claude Code) or @synthesize-decisions (Cursor), capturing the reasoning…
Convert raw text (emails, meeting notes, markdown documents, pasted prose) into a subtext JSON document — a sentence-level document tree where every sentence has a stable ID and metadata — then interview the user with clarifying questions about anything a reader might find unclear, attaching the answers to the exact…
A collection of 114 command-line skills for Korean users, covering weather, transport, finance, property, shopping, sports, and everyday utilities. A command-line tool is software operated by typing commands.
Send rich interactive cards to Feishu (Lark) users or groups with Markdown support, colored headers, action buttons, embedded images, and AI persona styling.
Read the owner's local history, assets, and person-graph evidence; extract stable workflows, preferences, and personality-level claims; keep them updated; and align future tasks to the owner's style. Use when explicitly asked to initialize, refresh, or apply MeOS.
Production-grade FastAPI development with async patterns, Pydantic v2, dependency injection, ML/AI endpoint design, and modern Python best practices for building high-performance REST APIs.
A tool for controlling Excel workbooks with VBA, Excel's built-in programming language, using plain-language instructions. It can work with VBA modules and existing macros.
★not rated 20 7mo agoA89 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: