Loading...
Loading...
Found 2,007 Skills
Enforces a 'Document-then-Execute' workflow. Use when an agent needs to run shell commands, execute tests, build projects, or perform any task that should favor established task runners (Makefile, npm run) and be logged to .cmds-by-agents/ for auditability.
Create and manage Obsidian notes for projects, companies, technical challenges, brag documents, daily logs, AI conversations, and quick captures using the Obsidian CLI. Use when documenting projects, tracking job applications, recording interview challenges, maintaining brag documents, creating daily notes, or saving AI conversations. Triggers on "create project", "new project note", "document company", "job application", "technical challenge", "brag document", "daily note", "today's log", "obsidian note", "save conversation", "chat summary", "session summary", "save this", "capture this", "quick note".
Scaffolds new projects with README.md, AGENTS.md, and CI/CD (GitLab CI, GitHub Actions). Handles project type (generic / Flask backend / React frontend / Taro miniapp), tech stack, coding standards, quality level, and SDD (OpenSpec, SpecKit, GSD). All init flows (Flask, React, Taro) and conventions (backend-python-cicd, frontend-codegen, flask-backend-codegen, QA/testing, agent-roles/subagents) are built-in; no separate skills. Docs default to Chinese. Use when creating a project, initializing a repo, or setting up CI/CD/SDD.
Integrate with HyperAPI for financial document processing - OCR text extraction, document classification, PDF splitting, and structured data extraction from invoices, receipts, and financial documents. Use when the user needs to parse PDFs, extract text from documents, classify document types, split multi-document PDFs, or extract structured entities like invoice numbers, vendor names, line items. Keywords: hyperapi, hyperbots, document parsing, OCR, PDF processing, invoice extraction, receipt processing, document classification, VLM, vision language model.
Applicable to code-centric tasks such as coding, debug/debugging, bug fixing, refactor/refactoring, code review, scripting, automation, and implementation planning.
Build PHPStan rules, collectors, and extensions that analyze PHP code for custom errors. Use when asked to create, modify, or explain PHPStan rules, collectors, or type extensions. Triggers on requests like "write a PHPStan rule to...", "create a PHPStan rule that...", "add a PHPStan rule for...", "write a collector for...", or when working on a phpstan extension package.
Operate an Obsidian vault via the official CLI for note, search, task, and metadata workflows. Use for Obsidian notes, wikilinks, daily notes, templates, and `obsidian ` commands. Not for plugins, MCP servers, or other note apps.
Provides calibrated decision analysis using Charlie Munger-style multiple mental models, inversion, incentive mapping, circle-of-competence checks, misjudgment audits, second-order effects, and forecast updates. Use when the user asks for an oracle take, a hard call, a decision memo, a premortem, an outside view, a red-team, a sanity-check, what am I missing, think this through, or wants a strategy, hire, investment, plan, product, partnership, or major life choice analysed. Avoid for simple factual lookups or time-sensitive legal, medical, or market questions without fresh evidence.
Generates Mermaid mindmap diagrams from codebases, topics, files, or conversations. Visually summarizes source material as branching diagrams. Use when asked to create a Mermaid mind map, visualize a topic, map out a codebase, summarize a file as a diagram, generate a concept map, or create a visual overview.
Expert guidance for building production-grade AI agents and workflows using Pydantic AI (the `pydantic_ai` Python library). Use this skill whenever the user is: writing, debugging, or reviewing any Pydantic AI code; asking how to build AI agents in Python with Pydantic; asking about Agent, RunContext, tools, dependencies, structured outputs, streaming, multi-agent patterns, MCP integration, or testing with Pydantic AI; or migrating from LangChain/LlamaIndex to Pydantic AI. Trigger even for vague requests like "help me build an AI agent in Python" or "how do I add tools to my LLM app" — Pydantic AI is very likely what they need.
Generates detailed, architect-quality GitHub issues from short instructions. Analyzes the project's actual stack, architecture, and codebase before writing. Detects duplicate issues with intelligent multi-strategy search, validates and creates labels, enforces title conventions, controls scope, and publishes via `gh` CLI with robust error handling. Use this skill whenever the user wants to create a GitHub issue, report a bug, propose a feature, request a refactor, or file any kind of technical issue — even if they just say something brief like "we need to fix the auth flow" or "create an issue for X". Also triggers on: "open an issue", "file a bug", "I want to propose...", "add this to the backlog", "gh issue", or any request that implies creating a trackable work item on GitHub.
Regenerates documentation files (agents.md, agent-skills.md, plugins.md, usage.md) from marketplace data using Jinja templates. Use when plugins are added, updated, or removed to keep documentation in sync.