harness-writing
allanninal/claude-code-skills/skills/harness-writing/SKILL.md
Techniques for writing effective fuzzing harnesses across languages. Use when creating new fuzz targets or improving existing harness code.
One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
allanninal/claude-code-skills/skills/harness-writing/SKILL.md
Techniques for writing effective fuzzing harnesses across languages. Use when creating new fuzz targets or improving existing harness code.
allanninal/claude-code-skills/skills/health-check/SKILL.md
Check health status of all running services and dependencies. Use when verifying services are running, debugging connectivity issues, or monitoring system status.
allanninal/claude-code-skills/skills/huggingface-skills/SKILL.md
Hugging Face Hub operations - models, datasets, Spaces, training with TRL, evaluation, and CLI operations. Use when working with ML models, datasets, or Hugging Face infrastructure.
allanninal/claude-code-skills/skills/internal-comms/SKILL.md
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Often used withacademy-guideskill-shareslack-gif-creator
allanninal/claude-code-skills/skills/interpreting-culture-index/SKILL.md
Use when interpreting Culture Index surveys, CI profiles, behavioral assessments, or personality data. Supports individual interpretation, team composition (gas/brake/glue), burnout detection, profile comparison, hiring profiles, manager coaching, interview transcript analysis for trait prediction, candidate debrief, onboarding planning, and conflict mediation. Handles PDF vision or JSON input.
allanninal/claude-code-skills/skills/ios-simulator/SKILL.md
Interact with iOS Simulator for mobile app testing and development. Use when testing iOS apps, taking screenshots, simulating user interactions, or debugging mobile interfaces.
allanninal/claude-code-skills/skills/kaizen/SKILL.md
Apply continuous improvement methodology to code, processes, and workflows. Use when optimizing development practices, reducing waste, or improving team efficiency.
allanninal/claude-code-skills/skills/kiro-skill/SKILL.md
Interactive feature development workflow from idea to implementation. Creates requirements (EARS format), design documents, and task lists. Triggers: "kiro", ".kiro/specs/", "feature spec", "需求文档", "设计文档", "实现计划".
allanninal/claude-code-skills/skills/libafl/SKILL.md
LibAFL is a modular fuzzing library for building custom fuzzers. Use for advanced fuzzing needs, custom mutators, or non-standard fuzzing targets.
allanninal/claude-code-skills/skills/libfuzzer/SKILL.md
Coverage-guided fuzzer built into LLVM for C/C++ projects. Use for fuzzing C/C++ code that can be compiled with Clang.
allanninal/claude-code-skills/skills/lint-fix/SKILL.md
Auto-format code and fix linting issues across Python and JavaScript/TypeScript projects. Use when cleaning up code, fixing style issues, or preparing for commit.
allanninal/claude-code-skills/skills/logs/SKILL.md
View and aggregate logs from various sources (systemd, docker, application files). Use when debugging, monitoring services, or investigating errors.
allanninal/claude-code-skills/skills/mcp-builder/SKILL.md
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Often used withchinese-code-reviewacademy-guidecodebase-migrate
allanninal/claude-code-skills/skills/modern-python/SKILL.md
Configures Python projects with modern tooling (uv, ruff, ty). Use when creating projects, writing standalone scripts, or migrating from pip/Poetry/mypy/black.
allanninal/claude-code-skills/skills/ossfuzz/SKILL.md
OSS-Fuzz provides free continuous fuzzing for open source projects. Use when setting up continuous fuzzing infrastructure or enrolling projects.
allanninal/claude-code-skills/skills/pdf/SKILL.md
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
192 projects use a version of this
Often used withVideo Generationgift-evaluatormigrate-to-codex
allanninal/claude-code-skills/skills/postgres-best-practices/SKILL.md
PostgreSQL performance optimization guidelines. Use when writing SQL queries, designing schemas, implementing indexes, reviewing database performance, configuring connection pooling, or working with Row-Level Security (RLS).
allanninal/claude-code-skills/skills/pptx/SKILL.md
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Often used withfile-readingcontext7-efficientproduct-self-knowledge
allanninal/claude-code-skills/skills/prompt-engineering/SKILL.md
Optimize prompts for LLMs - structure, clarity, and effectiveness. Use when writing system prompts, designing AI features, or improving LLM interactions.
allanninal/claude-code-skills/skills/property-based-testing/SKILL.md
Provides guidance for property-based testing across multiple languages and smart contracts. Use when writing tests, reviewing code with serialization/validation/parsing patterns, designing features, or when property-based testing would provide stronger coverage than example-based tests.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.