Guard task boundaries and preserve confirmed critical project state across Codex compaction. Use when a user wants topic-switch guidance, write-through critical memory, compact HANDOFF checkpoints, PreCompact and compact-resume hooks, four-layer Markdown memory initialization, or memory workflow auditing.
🏭 Dark Factory — agentic build system with sealed-envelope testing. Orchestrates 8 specialist agents through a gated pipeline with cross-family adversarial validation. Say "dark factory" to build something, "dark factory express" for quick tasks, "dark factory tournament" to race model families against one sealed…
A way to track the gap between what an automated agent produces and what a person actually understands. As automation creates more code or content, the person may know less about how it works.
Bootstrap a new realtime eval folder inside this cookbook repo by choosing the right harness from examples/evals/realtimeevals, scaffolding prompt/tools/data files, generating a useful README, and validating it with smoke, full eval, and test runs. Use when a user wants to start a new crawl, walk, or run realtime eval…
Deutsches IT-Recht & DSGVO: Ersteinschätzungen zu Datenschutz, Verträgen, AGB, Impressum, Cookies, NIS2, EU AI Act. Keine Rechtsberatung. Nutzen bei DSGVO- und IT-Rechtsfragen (DE/EU).
Review a specific GitHub pull request with gh — fetch the diff, fan out reviewers, consolidate, and optionally post the review. Requires the gh CLI or the GitHub MCP server.
Strategic review for defense, autonomy, and dual-use ventures. Evaluates capability gaps, incumbent failure modes, vertical integration decisions, and prototype paths. Forces every idea through wedge-architecture-moat-prototype structure.
Use this skill when reading or writing RPG Maker MV or MZ database files (Actors.json, Skills.json, Items.json, Weapons.json, Armors.json, Enemies.json, States.json, Troops.json, Classes.json, Animations.json, Tilesets.json, CommonEvents.json, System.json). Triggers: any modification to data/.json database entries…
An automated Chinese enterprise-WeChat customer-service program that watches external group chats, reads messages from screenshots, generates DeepSeek replies, and types them into the chat.
Use when designing, debugging, training, researching, or evaluating an AI agent and the decision concerns one of seven areas: minimum agent loop, inference-time compute allocation, verifier or LLM-judge trust, long-horizon dependency and rollback control, verified-trajectory post-training, evidence-gap research, or…
Automate a professional LinkedIn presence end-to-end using Claude: daily posting with pillar calendar, engagement with anti-detection rules, DM triage, reporting, and growth tracking. Use when the user wants to automate LinkedIn, manage a profile with AI, create a content strategy, or set up engagement automation.…
Run a security review of code changes exactly like Claude Code's /security-review command — but in ANY AI coding agent (Claude Code, Cursor, Codex, Windsurf, Gemini CLI, Cline…). Reviews the pending branch diff (or a specific PR, uncommitted changes, or a whole file/folder) for HIGH-CONFIDENCE, actually-exploitable…
Repo-local Sage eval-gauge / hill-climbing Phase-0 toolkit. Use when an operator, Claude Code, or Codex needs to measure Sage capability with a GROUND-TRUTHED gauge (not substring eval scores), run the Gate Experiment (does the eval track reality?), compare bare-model vs harness, get the noise floor /…
Clean and consolidate the shadow knowledge base. Scans all shadow files for duplicate discoveries (same claim, different wording), near-duplicates (one extends another), and conflicting entries (contradicting claims). Merges duplicates, resolves conflicts by investigating the code, and asks the user only when…
A local tool for a Chinese AI trading assistant that reads market data, simulates trades, and reports reviews through an API. Its journal counterpart handles saved local notes and state.
Reclaim disk space on a macOS developer machine by finding and safely cleaning build caches and artifacts (Xcode DerivedData, nodemodules, Docker, and package-manager/editor/AI caches) with the Harbofly CLI. Everything goes to the Trash and is recoverable. Use when the user wants to free up disk space, clean dev…
Use when building, editing or reasoning about an RPG Maker MV game through the RpgMakerMVUltimate MCP server (tools prefixed rpgmaker / the 13 consolidated tools: querydatabase, createdatabaseentry, generatemap, managemapevent, analyzeproject, etc.). Covers the correct workflow so maps, NPCs, chests, shops, doors…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: