Freeze a repeatable, tool-call-driven task into a replayable Reelier skill, and replay an existing skill instead of redoing deterministic work. Use after finishing a task that was mostly API/MCP tool calls (data pulls, report generation, deploy checks, CRUD sequences) — never for arbitrary coding/file-edit sessions…
Bound and record an agent's writes before granting them. Use when the user is adding or configuring an MCP server, planning to run an agent unattended or on a schedule or in CI, or deciding whether to give an agent write access to a real system. Covers the recorder, the policy seatbelt, approvals, and what a receipt…
Use when reviewing n8n workflows or validating workflow JSON before deployment. Prevents production errors by catching anti-patterns in node configuration, connection wiring, and expression syntax. Covers workflow JSON structure, node configuration, connection wiring, expression syntax, credential setup, error…
Claude Code hook configuration that binds Phionyx self-governance to lifecycle events. Loaded when the assistant is editing .claude/settings.json, writing a new hook script under tools/claudecodemcp/, or asked about hook coverage / strict mode / why a hook fired.
Phionyx two-layer MCP architecture rules (pipeline + server). Loaded on demand when the assistant is about to call phionyxresponsegate, phionyxverifyclaim, phionyxcausaltrace, phionyxverifypaths, phionyxcheckpoint, phionyxsessionreport, or any mcpphionyx- tool. Codifies ADR-0006 (two-layer MCP, shared traceid) and the…
How to ground state-fact assertions about external systems (repo visibility, deployment, PyPI, URL liveness) with authoritative checks in the same turn. Loaded when the assistant is about to write or commit a line that claims X is live / X is public / X is deployed / X has version V / branch X has commit Y. Codified…
Use when the user asks to write, debug, import, or migrate Terraform / HCL, or names any cloud / SaaS provider in a "deploy / provision / configure" context. Provides per-resource argument schemas, import-ID formats, deprecation flags, recent-change knowledge cards, cross-provider recipes, and recommended-companion…
This skill should be used when the user asks to "publish to npm", "npm publish", "/publish-npm", "/publishnpm", or "submit to the MCP registry"; or when the session hits EOTP, E403, ENEEDAUTH, 2FA, "bypass 2fa", "cannot publish over the previously published versions", redacted auth/cli/, "+ package@version" that still…
Whole-repo financial audit. Use for ledger-audit, financial audit, or /ledger-audit. Scan for non-kernel money math, reconstruct flows as JournalEntry sequences, prove with validateEntry + Ledger.apply + runTrace + auditHash.
Complete guide for designing, writing, testing, iterating, and packaging Claude Skills (SKILL.md files). Use this skill whenever someone wants to: create a new skill from scratch, improve or update an existing skill, understand the skill format, write a SKILL.md, build a skill folder with scripts and references…
Digest a folder of documents into local, token-free knowledge-graph memory and recall from it. Use when the user wants to "memorise", "digest", "ingest", or "remember" files/attachments/a folder, build a knowledge graph from documents, or ask questions grounded in their own documents without paying tokens to read…
Turn a game prompt into a Renderoni scene with a compact inventory JSON, optional reference image, and img2threejs object factories. Use when the user wants prompt-to-game, image-to-scene, or token-efficient 3D content.
Comprehensive guide and best practices for building high-performance 3D games, deterministic simulations, and headless test suites with Renderoni, Three.js, and Rapier WASM physics.
Resolve prerequisites, ready work, execution order, blockers, change impact, dependency slices, and path explanations with Deterministic Dependency Engine over an explicitly declared graph. Use when a task asks who depends on what or why work is blocked; do not use it to infer undeclared relations or solve…
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: