Sequential-wave dispatch for WO chains where output of one feeds the next, shared locks, or shared files prevent fan-out. Use when planning dependent multi-WO landings.

macOS menu bar app that identifies USB-C cable capabilities and charging diagnostics using IOKit

WCAG 2.1/2.2 compliance, ARIA patterns, keyboard nav, focus management, a11y testing. Use when implementing accessible components or user mentions WCAG/ARIA/screen readers.

Fully autonomous research pipeline that turns a topic idea into a complete academic paper with real citations, experiments, and conference-ready LaTeX.

Advanced Bevy ECS: complex queries, system scheduling, change detection, and performance tuning. Use when optimizing Bevy architecture or implementing complex game systems.

AI-first knowledge base and startup OS with file-based storage, AI agents, scheduled jobs, and embedded apps

Self-directed iterative research skill for Codex that continuously cycles through modify, verify, retain or discard, and repeat until a measurable goal is reached.

Config sync across FVH repos: extract, diff, propagate tooling improvements. Use when syncing workflows or configs across multiple repos.

CubeSandbox — instant, hardware-isolated, E2B-compatible sandbox service for AI agents built on RustVMM/KVM

Expert skill for using DeepSeek-OCR, a vision-language model for optical character recognition with context optical compression supporting documents, PDFs, and images.

End-to-end commit-to-PR workflow. Use when the user says "create pr", "commit and pr", "push and pr", or wants to go from uncommitted changes to an open PR.

Manage GitHub sub-issues and dependencies (blocked_by/blocking). Use when breaking issues into sub-tasks, checking progress, or viewing a dependency graph.

NtWarden is a Windows Analysis and Research Toolkit providing GUI-based inspection of processes, kernel internals, services, network, ETW, and more via ImGui + DirectX 11 with optional kernel driver support.

LeetCode-style PyTorch interview practice environment with auto-grading for implementing softmax, attention, GPT-2 and more from scratch.

Create a work-order for isolated subagent execution, optionally linked to a GitHub issue. Use when breaking a PRP into delegatable tasks or spawning from an issue.

AI-powered browser extension that filters unwanted posts from Twitter/X feeds using natural language rules and multiple AI backends

Expert skill for using RX, an embedded data store for JSON-shaped data with random-access reads, no-parse lookups, and a text-safe binary encoding format.

Run 397B parameter Mixture-of-Experts LLMs on a MacBook using pure C/Metal with SSD streaming

jq JSON processing: query, filter, transform JSON. Use when parsing JSON files, filtering arrays/objects, transforming structures, or extracting fields from JSON.

NVIDIA NemoClaw plugin for secure sandboxed installation and orchestration of OpenClaw always-on AI assistants via OpenShell

OpenDuck — open-source distributed DuckDB with differential storage, hybrid dual execution, and transparent remote database attach

README.md templates and standards. Use when generating or improving README files, checking README compliance, or applying README best practices.

Open source harness for generating 3D CAD models from text using AI coding agents with build123d/OpenCascade, exporting STEP/STL/URDF, and previewing in a local CAD Explorer viewer.

Expert knowledge for using codex-plusplus to inject tweaks, patch Codex desktop app, and write custom ESM tweak modules with lifecycle APIs.

High-performance Kimi Delta Attention CUDA kernels built on CUTLASS for efficient recurrent state inference

Advanced git rebase — linear history, stacked PRs, --update-refs, --onto. Use when rebasing branches, cleaning history, managing PR stacks, or fixing merge-heavy branches.

Triage GitHub issues and PRs — cross-link, flag stale items, recommend actions. Use when grooming the backlog, pre-release cleanup, or asked to triage issues/PRs.

Feed-forward 3D foundation model for streaming scene reconstruction using Geometric Context Transformer

Open source eBPF-based network monitoring and blocking components for Little Snitch on Linux

Promote rules, skills, or agents from project scope to parent or user-global scope. Use when reorganizing .claude/ directories or when sibling repos hold near-duplicate rules.

Turn any website into a CLI using browser session reuse and AI-powered command discovery

ripgrep (rg) fast code search: smart defaults, regex, file filtering. Use when searching for text patterns, code snippets, or doing multi-file analysis.

SysWatch is a single-host system diagnostics TUI for macOS and Linux with twelve tabs, plain-English insights, and session scrubbing.

AI-powered analysis of Trump's social media posts to predict stock market movements using 31.5M brute-force tested rules

ty: Astral's extremely fast Python type checker (mypy/Pyright alternative). Use when checking Python types or setting up type checking. Triggers: ty, mypy alternative.

WebUSB extension for Firefox using native messaging to enable USB device access from web pages

Validate ADR relationships and domain consistency. Use when auditing ADRs before release, finding broken supersedes/extends links, or detecting cycles.

Scan blueprint docs and assign missing PRD/ADR/PRP/WO IDs. Use when assigning IDs to docs; --dry-run to preview, --link-issues to create GitHub issues for orphans.

Give AI agents access to your live Chrome session via CDP — interact with open tabs, logged-in accounts, and current page state

Assess quality of PRPs and work-orders using systematic confidence scoring. Use when evaluating readiness for execution or subagent delegation.

Check and configure Justfiles with standard recipes. Use when setting up a Justfile, auditing for missing recipes, or migrating from Makefile to Justfile.

fd fast file finding: smart defaults, gitignore-aware, parallel. Use when searching for files by name, extension, or pattern across directories.

Home Assistant YAML configuration management. Use when editing configuration.yaml, setting up integrations, configuring secrets, or troubleshooting HA configuration.

Expert skill for Lightpanda — the headless browser built in Zig for AI agents and automation. 9x less memory, 11x faster than Chrome. Installation, CLI, CDP server, Playwright/Puppeteer integration, and web scraping.

Domain-fronted HTTP/SOCKS5 proxy tunneling traffic through Google Apps Script with MITM TLS interception and DPI evasion

Distill session insights into rules, skill improvements, and justfile recipes. Use when capturing learnings, extracting reusable patterns, or codifying workflow into .claude/rules.

Use quien for interactive TUI and CLI/JSON domain, IP, DNS, mail, SSL/TLS, and tech stack lookups

Shadow mode / dark-launch for validating new systems under production load. Use when testing replacement services, comparing behavior, or planning traffic mirroring for migrations.

Autonomous white-box AI pentester for web applications and APIs using source code analysis and live exploit execution

Skaffold standards with OrbStack and dotenvx for local K8s. Use when configuring Skaffold, setting up K8s profiles, or managing dotenvx secrets.

C++ library for reducing tail latency in RAM reads by hedging across multiple DRAM channels with uncorrelated refresh schedules

Curate docs into ai_docs entries for AI context. Use when documenting library gotchas for PRP reuse or building a knowledge base under docs/blueprint/ai_docs/.

Generate project-specific rules from PRDs with path-scoped frontmatter. Use when auto-creating architecture, testing, or quality rules from docs/prds/.

release-please workflow setup and auditing. Use when configuring release-please, upgrading release-please-action, or adding a package to a monorepo config.

Migrate JS/TS linting from ESLint+Prettier to Biome. Use when .eslintrc* or eslint.config.* exists and no biome.json is present.

Pre-dump-then-dispatch for tools holding an exclusive lock (Ghidra, migrations, single-writer caches). Use when fanning out parallel agents needing a non-concurrent resource.

Sync, search, classify, and query X/Twitter bookmarks locally using the Field Theory CLI

Submit PRs to upstream repos from a fork — commit selection, squashing, cross-fork creation. Use when contributing changes upstream or cherry-picking fork commits.

Deep clean and optimize your Mac using the Mole CLI tool

Async Python bot for Polymarket that buys "No" on all standalone non-sports yes/no markets using the "nothing ever happens" strategy.

Build and publish Python packages with uv. Use when the user mentions building packages, publishing to PyPI, wheel/sdist creation, or entry points.

TFC plan JSON download and analysis. Use when diffing resource changes, inspecting replacements, or feeding plan data downstream. Requires TFE_TOKEN.

Obsidian vault file ops via CLI: read, create, append, move, rename, delete, listings, daily/random notes. Use when managing vault files.

Verify orchestrator premises (file counts, build state, artefact presence) before dispatching parallel subagents. Use when a wave's briefs cite a number, path, or behaviour not yet checked.

WebGPU rigid-body/soft-body physics engine based on the AVBD (Augmented Vertex Block Descent) solver

CLI and TUI tool that explains why processes, services, and ports are running by tracing causality chains across supervisors, containers, and shells.

Binary analysis: strings, binwalk, hexdump, xxd, file, objdump. Use when identifying unknown files, extracting strings, hunting credentials, or entropy analysis.

Display feature tracker stats, phase progress, and completion summary. Use when checking feature status, viewing blocked features, or seeing ready-to-start work.

Manage modular rules in .claude/rules/ with path-specific globs. Use when adding or listing rules, syncing with CLAUDE.md, or validating path frontmatter.

Interactive selector for infrastructure standards. Use when setting up specific components or building infrastructure incrementally instead of running /configure:all.

Infrastructure compliance status (read-only). Use when checking overall compliance, generating a report, or reviewing project health without making changes.

Migrate Python linting from flake8/isort to ruff. Use when pycqa/flake8 or PyCQA/isort is in .pre-commit-config.yaml or [tool.flake8]/[tool.isort] config exists.

Citation-backed responses with direct quotes from source documents. Use when analyzing long docs, answering codebase/spec questions, or when response accuracy is critical.

Multi-repo workspace rules: read-only fixtures, upstream/downstream pairs. Use when dispatching agents across sibling repos or editing another repo's .claude/.

CLI smoke recipes: expose pure-function modules via subcommands with a bulk-smoke justfile recipe. Use when designing data-transform modules or authoring smoke tests.

Systematic debugging for memory, performance, and system-level issues. Use when diagnosing memory leaks, tracing syscalls with strace/eBPF, profiling, or reasoning about races.

Git commit trailer conventions — BREAKING CHANGE, Co-authored-by, Signed-off-by. Use when composing messages with trailers or parsing via git interpret-trailers.

Fork management and upstream sync. Use when working with forks, syncing with upstream, detecting divergence, or preparing commits for contribution.

Pre-commit hook standards and configuration. Use when configuring pre-commit hooks, checking hook compliance, or working with conventional commits.

release-please standards and configuration reference. Use when configuring release workflows, checking automation compliance, or working with version bumps.

ArgoCD CLI auth with SSO and gRPC-Web. Use when the user mentions ArgoCD login, argocd authentication, SSO auth, or accessing ArgoCD applications and clusters.

Migrate Python formatting from black to ruff-format. Use when psf/black is in .pre-commit-config.yaml or [tool.black] exists in pyproject.toml.

Compatibility-first Claude CLI reimplementation with faster startup, lower memory, and drop-in command compatibility

Generate DECOMMISSION-<service>.md covering infra, data, access, DNS, dependencies, monitoring, and financial checklists. Use when decommissioning a service.

Obsidian File Recovery and Sync history: inspect, diff, restore previous note versions. Use when undoing edits, restoring versions, or recovering files.

Migrate Python type checking from mypy to ty (Astral). Use when mirrors-mypy is in .pre-commit-config.yaml or [tool.mypy] config exists.

Find and create supporting scripts for plugin skills. Use when auditing skills for script opportunities, improving token efficiency, or extracting bash blocks from SKILL.md.

Run Python scripts with uv (PEP 723 inline deps, --with for one-off deps). Use when running scripts without venv activation or needing one-off dependencies.

Broken Obsidian wikilink detection and repair. Use when fixing `[[Target]]` links, rewriting renamed-note refs, or resolving Zettelkasten/FVH paths.

Collect codebase health attributes as structured JSON. Use when assessing project health before routing to specialized agents via attributes-route.

List blueprint documents (ADRs, PRDs, PRPs) with frontmatter metadata. Use when listing docs, auditing statuses, or generating an index for project documentation.

Move generated artifact to custom layer to preserve manual edits. Use when promoting a generated rule, preserving .claude/rules/ changes, or stopping sync warnings.

Run, list, and inspect Obsidian commands and hotkeys from the CLI. Use when triggering a command, enumerating commands, or checking hotkey bindings.

Deps install: auto-detect package manager (uv, bun, npm, yarn, pnpm, cargo, go) and run the right install. Use when installing deps or syncing lockfiles.

Batch evaluate every skill in a plugin and produce a plugin-level report. Use when auditing an entire plugin's quality or validating before a release.

WARNING - This project is malicious software disguised as an FL Studio crack/patcher