thehardwarestore.ai

Humanizer is a skill (prompt) for AI agents that rewrites AI-generated text to sound human-written without altering factual content. It is built on Wikipedia's 'Signs of AI writing' guide and provides 26 numbered patterns grouped into six categories (staging, rhythm, inflation, formatting, leftovers, wrong reader). The skill is distributed as a single markdown file (SKILL.md) with YAML metadata, installable via plugin manifests for Claude Code, Cursor, and other agents through the Skills CLI. The repository also includes a validation script, issue templates, and CI workflows to maintain consistency across package files. While not a traditional software application, it functions as a tool that agents execute, with clear entry points (/humanizer command) and a well-defined workflow (mark tells, draft rewrite, check, finalize). The codebase is meticulously maintained with active issue triage, regular releases, and automated validation.

Codex Autoresearch is an autonomous, goal-driven experimentation CLI tool for Codex. It allows users to define a numeric target (e.g., reduce error count to zero) and then repeatedly runs a loop: the Codex model inspects the repo, makes one focused code change, the control script commits it, runs a verification command to measure the metric, keeps improvements or reverts failures, and appends audit events. The system supports both foreground (Codex Goal-driven) and background (detached controller with `codex exec` workers) modes, with strict state validation, atomic file operations, and Git-based rollback. Architecture: The codebase is split into three Python modules under `scripts/`—`autoresearch.py` (CLI and lifecycle orchestration), `autoresearch_core.py` (primitives for Git, command execution, event validation, and process management), and `autoresearch_report.py` (read-only rendering of history as terminal tables, TSV, or self-contained HTML). State is stored in `autoresearch-results/` as immutable `run.json` and append-only `events.jsonl`. The skill entrypoint is `SKILL.md`, which references three documentation files. The design emphasizes contract enforcement over silent recovery: malformed input, unexpected Git drift, or failed commands halt with precise diagnostics. The repository demonstrates high craftsmanship in defensive programming, strict JSON schema validation, atomic file writes, process tree management, and comprehensive unit/integration tests (including race condition testing for background controllers). It is a practical and well-documented example of building a reliable autonomous agent harness for codebases.

OpenViking is an agent-native context database that unifies memories, resources, and skills under a virtual filesystem paradigm (viking:// URIs). It provides a three-tier context model (L0 abstract, L1 overview, L2 full content), recursive directory-based retrieval with visualized trajectories, and automatic session memory extraction. The system consists of a FastAPI HTTP server with embedded Rust components (RAGFS filesystem, vector index engine), a Rust CLI (ov), Python SDKs, a React/Vite Web Studio dashboard, and VikingBot - an agent framework with multi-channel support (Telegram, Slack, Feishu, etc.) and MCP integration. It integrates with OpenClaw, Claude Code, Codex, OpenCode, Hermes, and LangChain/LangGraph. The codebase demonstrates strong engineering: clean separation of concerns, async-first design, comprehensive test coverage (unit, integration, e2e), and production-ready deployment artifacts (Docker, Helm, multi-arch builds). Benchmarks show significant improvements over baseline agents on LoCoMo (82% vs 24-57% accuracy), tau2-bench (+6-12pp), and HotpotQA (91% at top-20).

llmfit is a comprehensive LLM model analysis and recommendation system that matches models to local hardware specifications. It detects system capabilities (CPU, RAM, GPU/VRAM), analyzes model requirements across multiple dimensions (memory fit, speed, quality, context), and provides recommendations for optimal model selection. The system features multiple interfaces including a terminal user interface (TUI) as the default mode, command-line interface, embedded web dashboard, and REST API. It supports various inference backends (Ollama, llama.cpp, MLX, Docker Model Runner, etc.), includes benchmarking capabilities to measure real-world performance, and enables users to share benchmark results with the community. The architecture follows a modular Rust workspace design with llmfit-core as the shared library containing hardware detection, model analysis, and provider abstractions, while interface-specific concerns are separated into llmfit-tui, llmfit-desktop, llmfit-web, and llmfit-python packages.

ClawHub is a full-stack registry marketplace for AI agent skills and OpenClaw plugins. It provides a web application (React + TanStack Router + Convex backend), a CLI tool (clawhub) for publishing and managing skills, an admin CLI for moderation, and a public HTTP API. The system handles skill/plugin publishing, versioning, search (with OpenAI embeddings), trending leaderboards, security scanning (VirusTotal, ClawScan, static analysis), moderation, and catalog feeds. It also mirrors an external skills.sh catalog. The architecture is a monorepo with shared schema packages, extensive test coverage (unit, e2e, Convex), and CI/CD via GitHub Actions. While primarily an application, it includes data/research elements like security dataset export and ranking metrics pipelines.

Caveman is a multi-agent AI coding skill/plugin that compresses LLM output tokens by ~65-75% using a 'caveman' terse communication style. It's not a library or service but a distributed configuration package that installs into 30+ AI coding agents (Claude Code, Codex, Gemini, Cursor, Windsurf, Cline, Copilot, opencode, OpenClaw, etc.) through their native plugin/extension/rule-file mechanisms. The core deliverable is a set of SKILL.md prompt files that instruct models to drop articles, filler, pleasantries, and hedging while preserving exact technical substance, code blocks, URLs, and paths. The architecture is a single Node.js installer (bin/install.js) that auto-detects installed agents and dispatches to per-provider installation paths. For Claude Code specifically, it adds SessionStart and UserPromptSubmit hooks plus a statusline badge. The repo includes several sub-skills: caveman-commit (terse conventional commits), caveman-review (one-line PR comments), caveman-compress (rewrites memory files like CLAUDE.md into caveman format to save input tokens), caveman-stats (reads session logs to report real token savings), and cavecrew (compressed subagent definitions for investigator/builder/reviewer patterns). There's also caveman-shrink, an MCP middleware proxy that compresses tool descriptions. The codebase demonstrates strong engineering practices: symlink-safe flag file writes with O_NOFOLLOW and ownership verification, atomic settings.json merges with JSONC tolerance, defensive hook validation before writes, idempotent install/uninstall cycles, and a three-arm eval harness (baseline/terse/skill) for honest token compression measurement. The Python compress tool has safety guards against exfiltrating sensitive files and verifies backup integrity before overwriting. Test coverage is substantial across installer e2e flows, hook symlink safety, opencode plugin lifecycle, and config resolution order.

Taste-skill is not a software application in the traditional sense; it is a portable library of AI-agent 'skills' - extremely detailed Markdown instruction files (SKILL.md) distributed via the `npx skills add` CLI (Vercel agent-skills spec) and a .claude-plugin marketplace. The repo's product is the prompt content itself: 13 frontend design-direction skills that agents like Claude Code, Codex, and ChatGPT load to avoid generic 'AI slop' output. The flagship is `taste-skill` v2 (`design-taste-frontend`), a ~5000-line instruction document that codifies anti-pattern bans (zero em-dashes, no section-number eyebrows, no three-equal-card rows), a brief-inference protocol, design-system mapping to official packages (Fluent, Carbon, Polaris, GOV.UK), canonical GSAP/scroll-reactive code skeletons, and a hard pre-flight checklist with mechanical pass/fail criteria. It is complemented by image-generation-only skills (brandkit, imagegen-frontend-web/mobile) that produce reference comps for downstream coding agents, plus variant skills (brutalist, minimalist, soft, stitch, output-enforcement). The repository also contains a `research/laziness/` folder documenting LLM output-truncation causes and remediation, and a small set of Node/Sharp image-processing scripts used to build the README assets. Those scripts contain one genuinely valuable, extractable algorithm: a flood-fill outer-background removal with auto-cropping to content bounds. The scripts are one-off (hardcoded `C:/Users/User/Downloads` source paths, tightly coupled to specific sponsor assets), so they are not drop-in reusable without adaptation, but the background-removal technique itself is portable. This is a content/instruction repository rather than a codebase; software-engineering quality bars (tests, CI) do not apply. Its craftsmanship lives in the rigor, specificity, and mechanical enforcement of the prompt files, which is exceptional for the prompt-engineering domain. The active development cadence, current dependency references (Tailwind v4, Motion/react, React Server Components), and 92k-star traction confirm it is the leading project in its niche.

FormKit is a form-building framework for Vue and React, organized as a monorepo of 15+ packages. The architecture is a core (framework-agnostic) node tree that manages form state, validation, schema rendering, and plugins, with separate packages for framework bindings (Vue, React, Nuxt), inputs, validation rules, internationalization (30+ locales), icons, themes (CSS, Tailwind, UnoCSS), addons (multi-step, floating labels, localStorage), a CLI for scaffolding and theme generation, and Zod integration. It uses a schema system (JSON-serializable) to define form layouts and conditional rendering, and a plugin/feature pattern for extensibility. The repository demonstrates high engineering quality: extensive test coverage (unit, type, e2e memory leak tests), well-structured abstractions (observers, message stores, composables), and cross-framework consistency. However, there are minor inconsistencies (license declared as UNLICENSED despite README claiming MIT, incomplete translations in some locales, deprecated packages like @formkit/tailwindcss, and potential brittleness in remote API dependencies in the CLI). Overall, it's a production-grade form solution with solid reusability of its core patterns.

Activeloop's DeepLake is a production-grade, multi-vector database engine for AI data. At its core, it is a columnar, chunked, compressed storage system for tensors (multi-dimensional arrays) with native support for embeddings, images, video, text, and other complex AI data types. It exposes a Python library for dataset management, ingestion (COCO, Labelbox, CSV, Parquet), version control, and integration with PyTorch/TensorFlow/MMDetection. A high-performance C++ backend provides lazy NumPy-like array operations (nd::array), a composable async framework (async::promise), and a Tensor Query Language (TQL). The most distinctive component is a PostgreSQL extension (pg_deeplake) that allows SQL access to DeepLake datasets via custom table and index access methods, supporting vector similarity search (cosine, BM25) and hybrid search. Query execution is delegated to DuckDB through a custom scan node, enabling efficient analytical queries. The extension also includes WAL-based DDL replication across instances. This is primarily an application (a database system), with substantial research-oriented features such as medical image formats, compression codecs, and TPC-H benchmarking.

Word-Formatter-Pro is a cross-platform desktop application and CLI tool for automatically formatting Word documents (.docx, .doc, .wps, .txt, .md) into a consistent Chinese government/official document style. It is built with Python, uses Tkinter for the GUI, python-docx for document manipulation, and integrates with WPS/Word COM on Windows or LibreOffice on macOS/Linux for legacy format conversion. The application features intelligent detection of headings (four levels), title/subtitle, figure/table captions, attachments, and can perform conservative symbol normalization, table auto-formatting, and blank line compression for text sources. The architecture is well-separated: a core formatting engine independent of GUI, a CLI interface, a configuration module, and a bundled Agent Skill. The code is actively maintained, with regular version releases and built-in unit tests covering critical logic.

FigMirror is a reference-conditioned scientific figure style transfer system that iteratively generates matplotlib scripts matching the visual style of a reference figure. It operates as a multi-agent loop (Drawer/Reviewer) orchestrated by a runner backend (Codex, Claude, or Mock), with a local web UI for upload, iteration browsing, and refinement. The system is packaged as skills for both Claude Code and Codex, plus a standalone web server. While primarily an application, it has a strong research component: the prompts, aesthetic library, and evaluation benchmarks (PlotTwin-Bench) are the result of extensive empirical iteration. The codebase demonstrates high craftsmanship in its runner architecture, atomic file operations, SSE streaming, and deterministic review gates. However, it suffers from dual skill bundles (Claude/Codex) that must stay synchronized, retired artifacts, and some incomplete features (ClaudeRunner, SSE integration).

Autoresearch-opencode is an OpenCode plugin and skill that enables autonomous code optimization experiments. It provides a slash command (`/autoresearch`) and a TypeScript plugin that injects context into the AI agent's system prompt to guide it through an iterative experiment loop. The system defines a protocol for the agent: it reads/writes a JSONL state file (`autoresearch.jsonl`), generates experiment scripts (`autoresearch.sh`), and maintains a worklog (`experiments/worklog.md`). The core logic is documented in markdown files (SKILL.md, commands/autoresearch.md) rather than executable code, making it a hybrid of documentation and configuration. The repository includes a well-crafted bash backup utility (`scripts/backup-state.sh`) and example optimization targets (bogo_sort.py). The system is designed to be used within the OpenCode environment and does not function as a standalone application.

This repository is a content-based Claude Code skill package rather than a conventional software service. It contains two agent skills — /tutor-setup and /tutor — that an LLM coding assistant executes using filesystem and WebFetch tools. tutor-setup scans a working directory, auto-detects whether it contains source code or documents, and generates an Obsidian StudyVault: concept notes, dashboards, exam-traps, and practice questions, with strict rules for source traceability, tag registries, wiki-linking, and folder conventions. tutor-setup operates through detailed phase models (D1-D9 for documents, C1-C9 for codebases), and codebase mode produces architecture maps, module notes, API surfaces, and onboarding exercises. tutor then reads that vault and runs interactive 4-question quiz rounds, updating concept-level progress files and a compact dashboard; it supports diagnostic, weak-area drill, section review, and hard-mode sessions, all governed by a zero-hint quiz design rule in references/quiz-rules.md. The implementation is almost entirely Markdown instructions plus two small Bash install/uninstall scripts; there is no compiled code, test suite, CI pipeline, or dependency manifest. The operational logic is prompt/instruction engineering that Claude Code interprets. External dependencies are Claude Code (or a compatible npx-skills-aware assistant), Obsidian for reviewing generated vaults, pdftotext/poppler for PDF extraction, and the assistant's built-in Read, Write, Edit, Glob, Grep, Bash, WebFetch, and AskUserQuestion tools. The data flow is unidirectional: source files in the CWD are scanned and extracted, transformed into StudyVault markdown, then quiz answers update concept files and dashboard aggregate stats. The skill enforces a CWD boundary to avoid accessing files outside the working directory. The strong point is unusually detailed and internally consistent procedural specification: mandatory source-content verification, per-topic coverage rules, tag registries, active-recall fold callouts, interlinking requirements, and self-review quality checklists. Weaknesses are the absence of automated tests/CI and versioned dependency pins, and behavior ultimately depends on the host LLM following prompt rules correctly. The README also references a different GitHub owner (RoundTable02) than the repository path (bevibing/tutor-skills), indicating a fork or repackage whose provenance should be verified before use. Overall, it fulfills its stated purpose well, and several Markdown modules are genuinely reusable as templates for other agent skills, study-vault generators, or adaptive quiz systems.

This repository is a curated collection of Claude skills—markdown instructions and supporting scripts that enable Claude (or any MCP-compatible agent) to perform a wide range of tasks, from document manipulation (DOCX, PPTX, PDF, XLSX) and GIF animation to web testing, MCP server building, and automation of hundreds of third-party SaaS services via Composio's Rube MCP. The repo is primarily a skill library with a standardized template for each skill, but it also contains several well-crafted Python libraries (e.g., easing functions, particle systems, OOXML validation frameworks) that are genuinely reusable. The architecture is modular: each skill lives in its own directory with a SKILL.md and optional scripts. The heavy reliance on external services (Composio, Rube MCP) and the massive duplication of templated skill documentation introduce maintenance risks, but the core utility scripts demonstrate solid engineering craftsmanship.

This repository implements a meta-skill (ex-skill) that generates digital personas of former romantic partners by analyzing chat histories from WeChat and iMessage. It is designed to be consumed by AI agent runtimes like OpenClaw, Claude Code, or DeepSeek Harness via the AgentSkills standard. The system guides users through conversational intake of relationship details (astrology, MBTI, attachment style), automatically decrypts and extracts WeChat/iMessage chat databases, analyzes communication patterns using LLM prompt templates, and writes a structured persona skill that can be interactively chatted with. The codebase consists of a SKILL.md orchestrator, six detailed LLM prompts (intake, analysis, persona builder, merger, correction handler), four Python tools (database decryption, message parsing, skill file management, version management), and an example persona. It is a specialized tool for cyber-immortality and digital persona creation, blending reverse engineering with psychological profiling.