发现 Skills

Configure, extend, or contribute to Hermes Agent.

Naval Ravikant的思维操作系统。基于著作、播客、推文、决策记录和外部批评的深度调研， 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 激活后沉浸式扮演Naval，直接以「我」的视角回应问题。 当用户提到「用Naval的视角」「Naval会怎么看」「纳瓦尔模式」「Naval perspective」「切换到Naval」时使用。 即使用户只是说「这份工作有杠杆吗」「什么是specific knowledge」「什么是真正的财富」「欲望太多怎么办」「无需许可的路径」也可触发。 不要在用户只是问「我该怎么选择」「帮我想清楚」等一般性决策问题时触发——只在涉及杠杆/特定知识/欲望管理/财富定义等Naval核心概念时激活。

Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.

W&B: log ML experiments, sweeps, model registry, dashboards.

Create Railway projects, services, and databases with proper configuration. Use when user says "setup", "deploy to railway", "initialize", "create project", "create service", or wants to deploy from GitHub. Handles initial setup AND adding services to existing projects. For databases, use railway-railway-database skill instead.

Python interface to OpenMS for mass spectrometry data analysis. Use for LC-MS/MS proteomics and metabolomics workflows including file handling (mzML, mzXML, mzTab, FASTA, pepXML, protXML, mzIdentML), signal processing, feature detection, peptide identification, and quantitative analysis. Apply when working with mass spectrometry data, analyzing proteomics experiments, or processing metabolomics datasets.

Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines.

This skill should be used when establishing comprehensive QA testing processes for any software project. Use when creating test strategies, writing test cases following Google Testing Standards, executing test plans, tracking bugs with P0-P4 classification, calculating quality metrics, or generating progress reports. Includes autonomous execution capability via master prompts and complete documentation templates for third-party QA team handoffs. Implements OWASP security testing and achieves 90% coverage targets.

Simon Prince's comprehensive deep learning framework for understanding neural networks, architectures, and training.

Set up scheduled automated backups with version tracking and cleanup. Use when users need to (1) schedule periodic backups of directories or files, (2) monitor version changes and back up on updates, (3) automatically clean up old backups to save space, or (4) create backup strategies for configuration files, code repositories, or user data.

Generates a frontend interface that is visually pleasing and experientially sound by jointly optimizing aesthetics, motion graphics, and user experience (UX) using quantified evaluation. Use only when the user explicitly invokes this skill by name to redesign a frontend. Trigger keywords: use human-optimized-frontend, redesign frontend, redesign interface.

name: react-beast-practices description: Senior-level React best practices: composition, container/presenter, custom hooks, Context, performance (React.memo/useMemo/useCallback), code splitting, error boundaries

Use when a designer asks to work on guidance or documentation issues, process documentation queue, or close out doc tickets - fetches oldest issue from quarterly epic and guides through resolution

Diagnose agent instruction files (AGENTS.md, CLAUDE.md, CLAUDE.local.md, etc.) against best practices, report issues, and optionally improve them with user consent. Performs anti-pattern detection, token efficiency analysis, and structure checks. Never modifies files without user approval. "check rules", "review AGENTS.md", "inspect rules", "improve agent config", "audit rules", "optimize rules", "reduce context", "clean up rules", "check CLAUDE.md", "diagnose config", "rules seem too long", Use after editing agent instruction files to verify quality.

REQUIRED for every task. Log every error, failure, unexpected outcome, or friction encountered — no exceptions. Covers: (1) Any tool, command, script, or build step that fails or produces unexpected results, (2) Any instruction, workflow, or environment that behaves differently than expected, (3) Code bugs, compilation errors, test failures, or runtime exceptions, (4) MCP server, subagent, or integration misbehavior, (5) User-requested friction or diagnostic reporting, (6) Any problem, error, or divergence from expected behavior during task execution. If anything goes wrong, it gets logged here. Do not skip this skill.

Best practices for integrating LLM providers (Anthropic, OpenAI, Google, AWS Bedrock, Ollama) into backend applications. Covers client setup, streaming, error handling, token management, context compaction, caching, observability, cost control, and provider abstraction. Use when connecting any backend to an LLM API.

Manage specification files for spec-driven development. Use when creating, updating, or deleting spec files. Supports feat, fix, docs, refactor, and chore scopes.

Query up-to-date documentation and code examples for any programming library or framework. Use when looking up API docs, finding code examples, or checking library usage. Triggers on "how to use [library]", "docs for [package]", "show me examples of [framework]", "Context7 lookup".

Use when creating Continue rules — provides a required name field, alwaysApply semantics, glob/regex patterns, and Markdown format with an optional YAML frontmatter.

Create new OpenCode skills with valid SKILL.md frontmatter.

Analyzes and rewrites prompts for better AI output, creates reusable prompt templates for marketing use cases (ad copy, email campaigns, social media), and structures end-to-end AI content workflows. Use when the user wants to improve prompts for AI-assisted marketing, build prompt templates, or optimize AI content workflows. Also use when the user mentions "prompt engineering," "improve my prompts," "AI writing quality," "prompt templates," or "AI content workflow."

Evaluate how well a codebase supports autonomous AI development. Analyzes repositories across eight technical pillars (Style & Validation, Build System, Testing, Documentation, Dev Environment, Debugging & Observability, Security, Task Discovery) and five maturity levels. Use when users request `/readiness-report` or want to assess agent readiness, codebase maturity, or identify gaps preventing effective AI-assisted development.

Extract EXIF metadata from images including GPS coordinates, camera settings, and timestamps. Map photo locations and strip metadata for privacy.

Deterministic SVG generation, validation, and rendering. Use for icons, diagrams, charts, UI mockups, or technical drawings requiring structural correctness and cross-viewer compatibility.