tools-only
- 17k skills
- 0 followers
- 7 repo stars
- last week last updated
- ▌ API Reviewer Agent · tools-only bundleYou are the API Reviewer Agent responsible for ensuring PolicyEngine API implementations follow best practices, are performant, secure, and properly tested.
- ▌ Core Web Vitals Thresholds February 2026 · tools-only bundleUse this breakdown to identify which phase is causing LCP issues.
- ▌ Iproute Review Iproute2 Patch Review · tools-only bundleUsing the prompt review-core.md and the review prompt directory, do a deep dive regression analysis of the top commit, or the provided patch/commit.
- ▌ Core Concepts 4 Layer Model Workflow Pipeline Decision Tree · tools-only bundleCore concepts that explain what Claude Code is and how it fundamentally operates.
- ▌ File Selection · tools-only bundleHow ty selects which files to check, include/exclude patterns, gitignore integration, and the default excluded directories.
- ▌ The 8 Lr Primitives The Lego Bricks · tools-only bundleAddValueNode: Adds/copies data to the state. It's the perfect "final" node to copy {draftanswer} to {finalanswer}.
- ▌ Experiment Management · tools-only bundleTest cases in Strands Evals are organized into Experiment objects. This guide covers practical patterns for managing experiments and test cases.
- ▌ Format Specific Exploration Recipes · tools-only bundlePer-format commands for exploring structured data with dasel v3. Each section covers the format's unique characteristics and provides concrete commands.
- ▌ Native Sandboxing In Claude Code · tools-only bundleWrite access is inherently restricted to CWD by the sandbox. To block reads to sensitive directories, use permission deny rules as shown above.
- ▌ AWS Chalice Lambda Framework · tools-only bundleComplete guide for building AWS Lambda functions with the AWS Chalice framework.
- ▌ Cforge Gateway Deployment Tool · tools-only bundleThe cforge gateway command is a powerful deployment tool for ContextForge and its external plugins.
- ▌ Raw Java Lambda Reference · tools-only bundleComplete guide for creating minimal AWS Lambda functions in pure Java without frameworks.
- ▌ Export Workflow · tools-only bundleComplete guide for exporting Aldea slide decks to PDF and static HTML.
- ▌ Ibm Code Engine · tools-only bundleThis file is mounted into the container (via --env-file=.env), so its keys live inside Code Engine at runtime. Treat it as an application secret store.
- ▌ Lua Folder Structure · tools-only bundleThe main game directory for Garry's Mod is the garrysmod folder located next to the game's executable hl2.exe, and contains much of the content you see while playing the game.
- ▌ AI Code Traceability And Attribution · tools-only bundleThe rise of AI coding assistants has created a new challenge: knowing which code came from AI and which from humans.
- ▌ Error Pattern Catalog · tools-only bundleComprehensive catalog of common test error patterns organized by framework and language.
- ▌ Reviewing Pr Arguments 2 · tools-only bundleSpawn a general-purpose agent to analyze the diff and write a short context file. Must be general-purpose (not Explore) because it needs the Write tool to save the summary to disk.
- ▌ Design By Contract In Python · tools-only bundleDesign by Contract (DbC) is a software development approach where software components specify formal contracts consisting of preconditions, postconditions, and invariants.
- ▌ Backdating Arguments · tools-only bundleCoordinate a multi-agent workflow to add historical date entries, fix reference quality, review formula correctness, and improve test coverage for an existing state program's parameters.
- ▌ Plan Bicep Implementation 3 · tools-only bundleCreate a comprehensive, machine-readable implementation plan by discovering governance constraints, verifying AVM module availability, and designing the complete Bicep template structure.
- ▌ Kiro CLI Integration Guide 2 · tools-only bundleThis guide explains how to use Antigravity Awesome Skills with Kiro CLI, AWS's agentic AI-powered coding assistant.
- ▌ Agent Evaluation · tools-only bundleWhen you create custom agents in .claude/agents/, you're encoding specialized expertise into reusable workflows. But how do you know if your agents are actually effective?
- ▌ Deploying Contextforge On Google Cloud Run · tools-only bundleContextForge can be deployed to Google Cloud Run, a fully managed, autoscaling platform for containerized applications.
- ▌ Dead Code Patterns Reference · tools-only bundleThis document catalogs common patterns of dead code and how to identify them.
- ▌ Resource Evaluation Beyond Vibe Coding Addy Osmani · tools-only bundleComprehensive book guiding developers from "vibe coding" (rapid AI-assisted prototyping without deep understanding) to professional AI-aided engineering practices.
- ▌ Editing And Confirming · tools-only bundleConfirming matters for many workflows, especially when exporting back to a CAT tool.
- ▌ Lr V1 2 0 Release Notes · tools-only bundleThis release focuses on "Glass Box" visibility, incorporating feedback from power users who need granular cost tracking and cleaner debug logs.
- ▌ Lr V1 3 0 Release Notes · tools-only bundleThis release focuses on hardening the framework for enterprise and regulatory compliance (EU AI Act), while refactoring the core execution engine for better separation of concerns.
- ▌ Understanding Evaluation Results · tools-only bundleThis guide explains how to interpret and analyze mcpbr evaluation results.
- ▌ Rpc Development Guide · tools-only bundleThis guide covers everything about NotebookLM's RPC protocol: capturing calls, debugging issues, and implementing new methods.
- ▌ REST API Design Rules Reference · tools-only bundleREST APIs should focus on resources (nouns) rather than actions (verbs). The HTTP methods provide the actions.
- ▌ Evolution Scoring Framework · tools-only bundleThe Evolution/Timelessness lens is the core evaluative perspective for SkillForge v4.0. Every skill must score ≥7 on timelessness to be approved.
- ▌ Claude Quickstarts 2 · tools-only bundleClaude Quickstarts is the official Anthropic repository of deployable reference applications built on the Claude API.
- ▌ Debugging Failing MCP Servers In Claude Code · tools-only bundleClaude Code stores per-session JSONL log files for each MCP server in ~/.cache/claude-cli-nodejs//mcp-logs-/.
- ▌ Long Running Agent Start Coding Session 2 · tools-only bundleYou are a Coding Agent starting a new session on an ongoing project. Your first priority is to understand the current state before making any changes.
- ▌ Python Edge Cases And Testing Patterns · tools-only bundlePython-specific edge cases, common pitfalls, and testing patterns using pytest, unittest, and Hypothesis.
- ▌ Claude Code Options · tools-only bundleAdvanced Claude Code SDK options can be passed through API requests using unofficial extension parameters.
- ▌ Cloud Storage Guide For Idc · tools-only bundleIDC maintains all DICOM files in public cloud storage buckets mirrored between Google Cloud Storage (GCS) and AWS S3. This guide covers bucket organization, file structure, access methods, and versioning.
- ▌ Question Patterns For Effective Clarification · tools-only bundleThis reference provides templates, patterns, and best practices for formulating clarifying questions that are grounded in research and lead to actionable answers.
- ▌ Production Safety Rules · tools-only bundleWhen AI reliability crosses ~95%, shift from manual review to automated guardrails.
- ▌ Sandbox Isolation For Coding Agents · tools-only bundleDocker Sandboxes run AI coding agents in microVM-based isolation on your local machine. Each sandbox gets its own private Docker daemon and filesystem. Sandboxes do NOT appear in docker ps — they are VMs, not containers.
- ▌ Contextforge Security Features 2 · tools-only bundleFor production deployments, always include JTI in issued tokens to enable proper caching, revocation, and audit capabilities.
- ▌ Opentelemetry Setup For Navigator · tools-only bundleNavigator will now show real-time statistics when you start sessions.
- ▌ Google OAUTH Oidc Setup Tutorial · tools-only bundleThis tutorial walks you through setting up Google Single Sign-On (SSO) authentication for ContextForge, allowing users to log in with their Google accounts.
- ▌ Dependency Manifest Formats · tools-only bundleThis reference documents the dependency manifest and lockfile formats for supported ecosystems.
- ▌ Lr V1 7 0 Release Notes · tools-only bundleLLMNode has received a major upgrade with enterprise-grade features seamlessly integrated into the LiteLLM backend.
- ▌ Exploration Before Implementation · tools-only bundleBefore coding, ask Claude for multiple approaches with trade-offs. This prevents anchoring bias—the tendency to fixate on the first solution proposed.
- ▌ Developer Onboarding Checklist 2 · tools-only bundleThe fastest way to get started is using the VS Code Dev Container, which provides a fully-configured development environment.
- ▌ Extend Claude With Skills · tools-only bundleSkills extend what Claude can do. Create a SKILL.md file with instructions, and Claude adds it to its toolkit. Claude uses skills when relevant, or you can invoke one directly with /skill-name.
- ▌ Overwatch Mode Data Driven Deck Authoring · tools-only bundleA YAML spec serves as Claude's brief for composing each slide. Claude reads the spec alongside overwatch-slide-templates.md to produce each slide .tsx file.
- ▌ Debugging Strategies · tools-only bundleAdvanced debugging techniques and systematic approaches for diagnosing complex test failures.
- ▌ Prompt Optimization · tools-only bundleYou are a prompt engineering expert specializing in transforming basic instructions into production-ready prompts using advanced techniques.
- ▌ Configuration Schema · tools-only bundleAll ty configuration keys, their types, defaults, and valid values. Load when the user asks about ty.toml, pyproject.toml settings, or any configuration option.
- ▌ Policy Quick Reference · tools-only bundleScan policies control all tuning knobs, detection thresholds, and rule enablement in Skill Scanner. Every setting has a sensible default; custom policies merge on top so you only specify what you want to change.
- ▌ Code Quality Checklist · tools-only bundleComprehensive checklist for assessing code quality and identifying technical debt in legacy codebases.
- ▌ Create Data Extensions Workflow 2 · tools-only bundleGenerate data extension YAML files to improve CodeQL's data flow coverage for project-specific APIs. Runs after database build and before analysis.
- ▌ Databricks CLI Installation · tools-only bundleInstall or update the Databricks CLI on macOS, Windows, or Linux using doc-validated methods (Homebrew, WinGet, curl install script, manual download, or user directory install for non-sudo environments).
- ▌ Product Design Skill MCP Integration Implementation Summary · tools-only bundleSuccessfully implemented direct Python → Figma MCP integration for Navigator's product-design skill.
- ▌ Cognitive Foundations 2 · tools-only bundleMental models, error psychology, attention, and measurement approaches for interaction design.
- ▌ Generate Crud Implementation 2 · tools-only bundleYou are a Spring Boot CRUD generation specialist. Your task is to generate a complete CRUD implementation for the domain class "$1" using the spring-boot-crud-patterns skill.
- ▌ Security Analysis For Typescript Node JS Applications · tools-only bundleExecute comprehensive security review for TypeScript/Node.js applications. Analyze vulnerabilities, dependencies, security configurations, and best practices specific to the TypeScript ecosystem.
- ▌ Help Us Test Session Management Features · tools-only bundleI've implemented session management patterns from Anthropic's article "Effective harnesses for long-running agents" in the feature/anthropic-patterns branch.
- ▌ Everything Claude Code · tools-only bundleEverything Claude Code (ECC) is a complete, production-hardened Claude Code plugin delivering 13 specialized sub-agents, 48+ skills, 31+ slash commands, a trigger-based hooks pipeline, multi-language rules, and MCP…
- ▌ Execution Steps 2 · tools-only bundleProvides comprehensive security review for TypeScript/Node.js applications (Next.js, NestJS, Express, etc.). Use when auditing security vulnerabilities or before deploying to production.
- ▌ Admin UI Customization 2 · tools-only bundleContextForge's Admin UI supports flexible section visibility for embedding in third-party portals, restricting views for specific audiences, and reducing dashboard clutter.
- ▌ Capability Probe Spec Gate Artifact 1 · tools-only bundleThis spec is the source of truth for replacing min_version: probe-lock.
- ▌ Vector C CLI Data Fetch · tools-only bundleThe prompt instructs the AI agent to fetch attacker-controlled content at runtime using gh CLI commands.
- ▌ Multi Agent Patterns 4 · tools-only bundlePatterns for coordinating multiple Claude instances for parallel and complex work.
- ▌ Plugin Validator Implementation Task Decomposition 2 · tools-only bundleImplement core data structures for validation results, issues, and error codes. These models are used by all validators and reporters.
- ▌ RAG Evaluation Framework · tools-only bundleEvaluating Retrieval-Augmented Generation (RAG) systems requires a comprehensive approach that measures both retrieval quality and generation performance.
- ▌ Task 09 Plugin Update Migration System · tools-only bundleNeed robust migration system for updating Navigator plugin across versions (v1.6 → v2.0 → v3.0) without breaking existing user projects.
- ▌ Cost And Optimization · tools-only bundleHow to get maximum value from Claude Code while controlling token consumption and costs.
- ▌ Batch Evaluation Quick Start Guide 2 · tools-only bundleThe batch evaluation infrastructure allows you to evaluate multiple skills at once with automatic test data generation, parallel execution, and comprehensive reporting.
- ▌ Enforcing Agent Isolation Technical Options · tools-only bundleAgents work in separate worktrees and are instructed not to access others. This relies on compliance.
- ▌ MCP Servers Ecosystem · tools-only bundleThis guide covers validated community MCP servers beyond the official Anthropic servers. All servers listed have been evaluated for production readiness, maintenance activity, and security.
- ▌ Monorepo Skills Guide · tools-only bundleQuick reference to monorepo management skills for TypeScript/JavaScript projects.
- ▌ Serverless Deployment Reference · tools-only bundleComplete deployment patterns for PHP Lambda functions using Serverless Framework and AWS SAM.
- ▌ Deployment Strategies For Nestjs Lambda · tools-only bundleThis reference covers deployment strategies, CI/CD pipelines, and optimization techniques for NestJS Lambda applications using AWS SAM and Serverless Framework.
- ▌ Serverless Deployment For Python Lambda · tools-only bundleDeployment patterns for Python Lambda functions using Serverless Framework, AWS SAM, and CI/CD pipelines.
- ▌ Serverless Deployment Reference 2 · tools-only bundleComplete guide for deploying Java Lambda functions with Serverless Framework, AWS SAM, and CI/CD pipelines.
- ▌ Keycloak Oidc Setup Tutorial 2 · tools-only bundleThis tutorial walks you through setting up Keycloak Single Sign-On (SSO) authentication for ContextForge, enabling enterprise identity management with the popular open-source identity and access management solution.
- ▌ Define Generic Context Interfaces For Dependency Injection · tools-only bundleDefine a generic interface for your component context with three parts: state, actions, and meta.
- ▌ SEO Crawlability Checker Agent · tools-only bundleYou audit a web application's crawlability — whether search engines can discover, access, and understand all the app's content. You report findings but do NOT make code changes.
- ▌ Execution Steps · tools-only bundleValidates security posture for Java enterprise applications (Spring, Jakarta EE, etc.). Use when auditing application security or before production deployments.
- ▌ Using Self Signed Certificates With MCP Servers · tools-only bundleWhen integrating with internal or development MCP servers that use self-signed TLS certificates, you must provide the Certificate Authority (CA) root certificate to the gateway.
- ▌ Environment And Module Resolution · tools-only bundleHow ty discovers Python environments, resolves first-party and third-party modules, and what environment variables affect behavior.
- ▌ Security Analysis For Java Enterprise Applications · tools-only bundleExecute comprehensive security review for Java enterprise applications. Analyze vulnerabilities, dependencies, security configurations, and best practices specific to the Java ecosystem.
- ▌ Git MCP Server Official Anthropic Resource Evaluation · tools-only bundleThe Git MCP Server is an official Anthropic MCP server providing programmatic Git access with 12 structured tools.
- ▌ MCP Architecture Patterns And Anti Patterns · tools-only bundleThis document provides an architecture-focused reference for designing systems using the Model Context Protocol (MCP).
- ▌ Generic Oidc Provider Setup Tutorial · tools-only bundleThis tutorial walks you through setting up generic OpenID Connect (OIDC) Single Sign-On (SSO) authentication for ContextForge, enabling integration with any OIDC-compliant identity provider including Keycloak, Auth0…
- ▌ Java Class Refactoring Assistant 2 · tools-only bundleIntelligently refactor complex Java classes following Clean Architecture, DDD patterns, and Spring Boot best practices.
- ▌ Credential System Complete Code Path Analysis · tools-only bundleThe credential is NOT added to invalid. Agent starts with a bad key. Only logger.debug records the issue.
- ▌ Gepa Integration Analysis · tools-only bundleWe need to be able to integrate with other AI frameworks besides DSPY, so we can optimize the AI systems that our clients are already using.
- ▌ Architecture Internals · tools-only bundleClaude Code's core execution is a single loop: parse → build prompt → call API → execute tools → loop until done. The agentic behavior emerges from this simple cycle.
- ▌ Plugin Validator QA Report Task T23 2 · tools-only bundleThe plugin-validator implementation (T1-T22) is 93% complete. All 23 error codes are implemented, type checking passes, and the validator successfully validates real plugins.
- ▌ Evaluation Agentskills Io Agent Skills Open Specification · tools-only bundleScore 4/5 maintenu. L'argument "spec pour implementeurs" est valide mais le guide documente deja l'architecture interne (guide/architecture.md), les hooks, le MCP protocol - il ne se limite pas au "how-to utilisateur".
- ▌ Security And Production · tools-only bundlePatterns for safely running Claude Code in sensitive and production environments.
- ▌ Multi CLI Orchestrator Proposal Claude Codex Gemini · tools-only bundleRouting and SLOs should be based on these tiers, not provider names.
- ▌ Duckdb Lock Fix Scope Flag Gitignore And Consolidation Todo · tools-only bundlemcp-server-motherduck is launched with --read-write, which acquires DuckDB's exclusive write lock. When sentiment-score.py runs while the MCP server is active, it fails with IOException: Could not set lock.