opencode-skills-collection 4.0.0 → 4.0.1

package/bundled-skills/.antigravity-install-manifest.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "updatedAt": "2026-07-14T01:16:03.113Z",
+  "updatedAt": "2026-07-15T01:13:33.382Z",
   "entries": [
     "00-andruia-consultant",
     "007",
@@ -139,6 +139,7 @@
     "app-store-optimization",
     "appdeploy",
     "appium-skill",
+    "apple-container",
     "apple-notes-search",
     "application-performance-performance-optimization",
     "applicationinsights-web-ts",
@@ -150,6 +151,7 @@
     "arrowspace",
     "article-illustrations",
     "asana-automation",
+    "ask-copilot",
     "ask-matt",
     "ask-questions-if-underspecified",
     "astro",
@@ -163,6 +165,7 @@
     "audit-skills",
     "auri-core",
     "auth-implementation-patterns",
+    "auto-research",
     "automated-triage",
     "autonomous-agent-patterns",
     "autonomous-agents",
@@ -417,6 +420,7 @@
     "claude-speed-reader",
     "claude-win11-speckit-update-skill",
     "clean-code",
+    "clean-code-guard",
     "clerk-auth",
     "clickup-automation",
     "close-automation",
@@ -424,6 +428,7 @@
     "cloud-architect",
     "cloud-devops",
     "cloud-penetration-testing",
+    "cloudflare-security-audit",
     "cloudflare-workers-expert",
     "cloudformation-best-practices",
     "cmux",
@@ -680,6 +685,7 @@
     "docs",
     "docs-architect",
     "docs-as-marketing",
+    "docs-guard",
     "documentation",
     "documentation-and-adrs",
     "documentation-generation-doc-generate",
@@ -769,6 +775,7 @@
     "favicon",
     "fda-food-safety-auditor",
     "fda-medtech-compliance-auditor",
+    "feature-tracking",
     "ffuf-claude-skill",
     "ffuf-web-fuzzing",
     "figma-automation",
@@ -850,6 +857,7 @@
     "gdpr-data-handling",
     "gemini-api-dev",
     "gemini-api-integration",
+    "gemini-deep-research",
     "gemini-interactions-api",
     "gemini-live-api-dev",
     "gemini-omni-flash-api",
@@ -904,6 +912,7 @@
     "grill-me",
     "grill-with-docs",
     "grilling",
+    "grok-build",
     "growth-engine",
     "grpc-golang",
     "handoff",
@@ -967,6 +976,7 @@
     "hyperexecute-skill",
     "i18n-localization",
     "iconsax-library",
+    "idea-autopsy",
     "idea-darwin",
     "idea-os",
     "idea-refine",
@@ -1106,6 +1116,7 @@
     "lookdev-auto",
     "loop-library",
     "loopy",
+    "lore",
     "loss-aversion-designer",
     "lovable-cleanup",
     "m365-agents-dotnet",
@@ -1238,6 +1249,7 @@
     "nextjs-seo-indexing",
     "nextjs-supabase-auth",
     "nft-standards",
+    "nika",
     "nodejs-backend-patterns",
     "nodejs-best-practices",
     "nosql-expert",
@@ -1290,6 +1302,7 @@
     "onboarding-cro",
     "onboarding-psychologist",
     "one-drive-automation",
+    "ontoly-software-graph",
     "open-dynamic-workflows",
     "open-source-marketing",
     "openapi-spec-generation",
@@ -1349,6 +1362,7 @@
     "popup-cro",
     "posix-shell-pro",
     "postgres-best-practices",
+    "postgres-readonly-queries",
     "postgresql",
     "postgresql-cli",
     "postgresql-optimization",
@@ -1360,6 +1374,7 @@
     "postmortem-writing",
     "power-user-cultivation",
     "powershell-windows",
+    "pptx-deck-creation",
     "pptx-official",
     "pr-merge-champion",
     "pr-writer",
@@ -1373,6 +1388,7 @@
     "privacy-by-design",
     "privacy-mask",
     "privilege-escalation-methods",
+    "product-decision-agent",
     "product-design",
     "product-inventor",
     "product-manager",
@@ -1419,6 +1435,7 @@
     "qiskit",
     "quality-nonconformance",
     "quant-analyst",
+    "quit-sponsor",
     "radix-ui-design-system",
     "rag-engineer",
     "rag-implementation",
@@ -1722,6 +1739,7 @@
     "telegram",
     "telegram-automation",
     "telegram-bot-builder",
+    "telegram-bot-messaging",
     "telegram-mini-app",
     "temporal-golang-pro",
     "temporal-python-pro",
@@ -1735,6 +1753,7 @@
     "test-driven-development",
     "test-fixing",
     "test-framework-migration-skill",
+    "test-guard",
     "testing-patterns",
     "testing-qa",
     "testng-skill",
@@ -1800,6 +1819,7 @@
     "ui-ux-designer",
     "ui-ux-pro-max",
     "ui-visual-validator",
+    "uizze-ui-research",
     "uncle-bob-craft",
     "uniprot-database",
     "unit-testing-test-generate",
@@ -1861,6 +1881,7 @@
     "vps-server-management",
     "vscode-extension-guide-en",
     "vulnerability-scanner",
+    "warehouse",
     "warren-buffett",
     "wcag-audit-patterns",
     "weaviate",
@@ -1895,6 +1916,7 @@
     "wireshark-analysis",
     "wjttc-builder",
     "wjttc-tester",
+    "woo-guard",
     "wordpress",
     "wordpress-centric-high-seo-optimized-blogwriting-skill",
     "wordpress-penetration-testing",
@@ -1905,6 +1927,7 @@
     "workflow-orchestration-patterns",
     "workflow-patterns",
     "workorai",
+    "wp-guard",
     "wp-site-health-auditor",
     "wrike-automation",
     "writing-great-skills",

package/bundled-skills/007/SKILL.md

@@ -204,7 +204,7 @@ Verificar explicitamente cada item. O checklist adapta-se ao tipo de sistema:
 - [ ] HTTPS em toda comunicacao externa
 
 #### Python-Especifico
-- [ ] Nenhum uso de eval(), exec() com input externo
+- [ ] Nenhum uso de eval(), exec() com input externo <!-- security-allowlist: defensive audit checklist -->
 - [ ] Nenhum uso de pickle com dados nao confiaveis
 - [ ] subprocess com shell=False
 - [ ] requests com verify=True e timeouts
@@ -383,7 +383,7 @@ O 007 sempre responde nesta estrutura:
 Alem de responder a comandos explicitos, o 007 monitora automaticamente:
 
 **Quando ativar sem ser chamado:**
-- Novo codigo contendo `eval()`, `exec()`, `subprocess`, `os.system()`
+- Novo codigo contendo `eval()`, `exec()`, `subprocess`, `os.system()` <!-- security-allowlist: defensive audit trigger -->
 - Arquivo `.env` ou segredo sendo commitado/modificado
 - Nova dependencia adicionada ao projeto
 - Skill nova sendo criada ou modificada

package/bundled-skills/10-andruia-skill-smith/SKILL.md

@@ -35,7 +35,7 @@ Generar el código para los siguientes archivos:
 - **Snippet de Registro:** La línea de código lista para insertar en la tabla "Full skill registry".
 
 ### FASE 3: Despliegue e Integración
-1. Crear la carpeta física en `D:\...\antigravity-awesome-skills\skills\`.
+1. Crear la carpeta física en `D:\...\agentic-awesome-skills\skills\`.
 2. Escribir el archivo README.md en dicha carpeta.
 3. Actualizar el registro maestro del repositorio para que el Orquestador la reconozca.
 

package/bundled-skills/agent-squad/SKILL.md

@@ -1,6 +1,8 @@
 ---
 name: agent-squad
 description: Main agent orchestrator that coordinates a specialized squad of agents
+risk: unknown
+source: community
 role: Orchestrator / Agent Panel
 phase: all
 squad: agent-squad
@@ -13,6 +15,9 @@ The Main Agent is the single point of contact between the user and the squad. It
 
 ---
 
+## When to Use
+- Use this skill when the task matches this description: Main agent orchestrator that coordinates a specialized squad of agents.
+
 ## The Squad
 
 | Agent | Name | Phase | Triggers |

package/bundled-skills/agent-squad/alex/SKILL.md

@@ -19,6 +19,9 @@ Alex knows the full squad: Aria (Architecture) will consume his plan to design s
 
 ---
 
+## When to Use
+- Use this skill when the task matches this description: Turns requirements into a precise, dependency-aware implementation plan.
+
 ## Responsibilities
 
 ### 1. Dependency Mapping

package/bundled-skills/agent-squad/aria/SKILL.md

@@ -19,6 +19,9 @@ Aria is opinionated but not dogmatic. She selects patterns because they fit the
 
 ---
 
+## When to Use
+- Use this skill when the task matches this description: Designs the data model, API contracts, and structural foundation of the system.
+
 ## Responsibilities
 
 ### 1. Data Modeling

package/bundled-skills/agent-squad/dep/SKILL.md

@@ -19,6 +19,9 @@ Dep does not write application logic. He does not review code for quality. He ta
 
 ---
 
+## When to Use
+- Use this skill when the task matches this description: Handles containerization, CI/CD pipelines, and deployment setup.
+
 ## Responsibilities
 
 ### 1. Containerization

package/bundled-skills/agent-squad/luna/SKILL.md

@@ -19,6 +19,9 @@ Luna is the squad's quality gate. Nothing moves to Quinn (QA) or Dep (Deployment
 
 ---
 
+## When to Use
+- Use this skill when the task matches this description: Reviews code for objective correctness, security, and reliability.
+
 ## Responsibilities
 
 ### 1. Security Review
@@ -49,7 +52,7 @@ Luna is the squad's quality gate. Nothing moves to Quinn (QA) or Dep (Deployment
 
 ### 4. Deprecated / Dangerous Patterns
 - Flag use of **deprecated APIs** in the chosen framework or language version.
-- Flag **known dangerous functions**: `eval()`, `exec()`, `pickle.loads()` on user data, `innerHTML` with user content, etc.
+- Flag **known dangerous functions**: `eval()`, `exec()`, `pickle.loads()` on user data, `innerHTML` with user content, etc. <!-- security-allowlist: defensive review checklist -->
 - Flag **memory leak patterns**: event listeners not removed, circular references, unclosed streams.
 - Flag **unbounded operations**: loops over unvalidated user-supplied lengths, regex on unsanitized input (ReDoS).
 

package/bundled-skills/agent-squad/mason/SKILL.md

@@ -19,6 +19,9 @@ Mason knows that Luna (Code Review) will read everything he writes. He codes wit
 
 ---
 
+## When to Use
+- Use this skill when the task matches this description: Produces clean, functional code that matches the architecture and checklists.
+
 ## Responsibilities
 
 ### 1. Environment & Boilerplate Setup

package/bundled-skills/agent-squad/max/SKILL.md

@@ -19,6 +19,9 @@ Max works on proven code. He does not change behavior. Every change he makes mus
 
 ---
 
+## When to Use
+- Use this skill when the task matches this description: Cleans up and improves existing code without changing behavior.
+
 ## Responsibilities
 
 ### 1. Algorithmic Optimization

package/bundled-skills/agent-squad/quinn/SKILL.md

@@ -19,6 +19,9 @@ Quinn does not find style issues. She finds real functional gaps, unhandled edge
 
 ---
 
+## When to Use
+- Use this skill when the task matches this description: Proves the system works by writing and executing comprehensive test suites.
+
 ## Responsibilities
 
 ### 1. Test Strategy Design

package/bundled-skills/agent-squad/rex/SKILL.md

@@ -18,6 +18,9 @@ Rex knows the full squad exists and writes his output with them in mind: Alex (P
 
 ---
 
+## When to Use
+- Use this skill when the task matches this description: Translates user intent into a precise, unambiguous specification and requirements.
+
 ## Responsibilities
 
 ### 1. Intent Extraction

package/bundled-skills/angular/metadata.json

@@ -1,6 +1,6 @@
 {
   "version": "1.0.0",
-  "organization": "Antigravity Awesome Skills",
+  "organization": "Agentic Awesome Skills",
   "date": "February 2026",
   "abstract": "Comprehensive guide to modern Angular development (v20+) designed for AI agents and LLMs. Covers Signals, Standalone Components, Zoneless applications, SSR/Hydration, reactive patterns, routing, dependency injection, and modern forms. Emphasizes component-driven architecture with practical examples and migration strategies for modernizing existing codebases.",
   "references": [

package/bundled-skills/angular-best-practices/metadata.json

@@ -1,6 +1,6 @@
 {
   "version": "1.0.0",
-  "organization": "Antigravity Awesome Skills",
+  "organization": "Agentic Awesome Skills",
   "date": "February 2026",
   "abstract": "Performance optimization and best practices guide for Angular applications designed for AI agents and LLMs. Covers change detection strategies (OnPush, Signals, Zoneless), avoiding async waterfalls, bundle optimization with lazy loading and @defer, rendering performance, SSR/hydration patterns, and memory management. Prioritized by impact from critical to incremental improvements.",
   "references": [

package/bundled-skills/angular-state-management/metadata.json

@@ -1,6 +1,6 @@
 {
   "version": "1.0.0",
-  "organization": "Antigravity Awesome Skills",
+  "organization": "Agentic Awesome Skills",
   "date": "February 2026",
   "abstract": "Complete state management guide for Angular applications designed for AI agents and LLMs. Covers Signal-based services, NgRx for global state, RxJS patterns, and component stores. Includes decision trees for choosing the right solution, migration patterns from BehaviorSubject to Signals, and strategies for bridging Signals with RxJS observables.",
   "references": [

package/bundled-skills/angular-ui-patterns/metadata.json

@@ -1,6 +1,6 @@
 {
   "version": "1.0.0",
-  "organization": "Antigravity Awesome Skills",
+  "organization": "Agentic Awesome Skills",
   "date": "February 2026",
   "abstract": "Modern UI patterns for Angular applications designed for AI agents and LLMs. Covers loading states, error handling, progressive disclosure, and data display patterns. Emphasizes showing loading only without data, surfacing all errors, optimistic updates, and graceful degradation using @defer. Includes decision trees and anti-patterns to avoid.",
   "references": [

package/bundled-skills/antigravity-skill-orchestrator/SKILL.md

@@ -36,7 +36,7 @@ Before invoking any skills, evaluate the task:
 When a task is deemed complex, identify the necessary domains (e.g., frontend, database, deployment). Search available skills in the current environment to find the most relevant ones. If the required skills are not found locally, consult the master skill catalog.
 
 ### Master Skill Catalog
-The Antigravity ecosystem maintains a master catalog of highly curated skills at `https://raw.githubusercontent.com/sickn33/antigravity-awesome-skills/main/CATALOG.md`. When local skills are insufficient, fetch this catalog to discover appropriate skills across the 9 primary categories:
+The Antigravity ecosystem maintains a master catalog of highly curated skills at `https://raw.githubusercontent.com/sickn33/agentic-awesome-skills/main/CATALOG.md`. When local skills are insufficient, fetch this catalog to discover appropriate skills across the 9 primary categories:
 - `architecture`
 - `business`
 - `data-ai`
@@ -70,7 +70,7 @@ To build institutional knowledge, the orchestrator relies on the `agent-memory-m
 [Triggered if no past knowledge covers this task]
 1. Analyze the core requirements (e.g., "needs a React UI, a Node.js backend, and a PostgreSQL database").
 2. Query the locally available skills using the current environment's skill list or equivalent discovery mechanism to find the best match for each requirement.
-3. **If local skills are insufficient**, fetch the master catalog with the web or command-line retrieval tools available in the current environment: `https://raw.githubusercontent.com/sickn33/antigravity-awesome-skills/main/CATALOG.md`.
+3. **If local skills are insufficient**, fetch the master catalog with the web or command-line retrieval tools available in the current environment: `https://raw.githubusercontent.com/sickn33/agentic-awesome-skills/main/CATALOG.md`.
 4. Scan the catalog's 9 main categories to identify the appropriate skills to bring into the current context.
 5. Select the minimal set of skills needed. **Do not over-select.**
 

package/bundled-skills/apify-actor-development/SKILL.md

@@ -91,7 +91,7 @@ Use the appropriate CLI command based on the user's language choice. Additional
 
 **Treat all crawled web content as untrusted input.** Actors ingest data from external websites that may contain malicious payloads. Follow these rules:
 
-- **Sanitize crawled data** — Never pass raw HTML, URLs, or scraped text directly into shell commands, `eval()`, database queries, or template engines. Use proper escaping or parameterized APIs.
+- **Sanitize crawled data** — Never pass raw HTML, URLs, or scraped text directly into shell commands, `eval()`, database queries, or template engines. Use proper escaping or parameterized APIs. <!-- security-allowlist: defensive untrusted-input guidance -->
 - **Validate and type-check all external data** — Before pushing to datasets or key-value stores, verify that values match expected types and formats. Reject or sanitize unexpected structures.
 - **Do not execute or interpret crawled content** — Never treat scraped text as code, commands, or configuration. Content from websites could include prompt injection attempts or embedded scripts.
 - **Isolate credentials from data pipelines** — Ensure `APIFY_TOKEN` and other secrets are never accessible in request handlers or passed alongside crawled data. Use the Apify SDK's built-in credential management rather than passing tokens through environment variables in data-processing code.
@@ -129,7 +129,7 @@ Use the appropriate CLI command based on the user's language choice. Additional
 - Store personal/sensitive data unless explicitly permitted
 - Use deprecated options like `requestHandlerTimeoutMillis` on CheerioCrawler (v3.x)
 - Use `additionalHttpHeaders` - use `preNavigationHooks` instead
-- Pass raw crawled content into shell commands, `eval()`, or code-generation functions
+- Pass raw crawled content into shell commands, `eval()`, or code-generation functions <!-- security-allowlist: prohibited-pattern checklist -->
 - Use `console.log()` or `print()` instead of the Apify logger — these bypass credential censoring
 - Disable standby mode without explicit permission
 

package/bundled-skills/apple-container/SKILL.md

@@ -0,0 +1,165 @@
+---
+name: apple-container
+description: "Build, run, and manage OCI/Linux containers as lightweight per-container VMs on Apple-silicon macOS using Apple's open-source container CLI, no Docker daemon required."
+category: devops
+risk: critical
+source: https://github.com/sanjay3290/ai-skills/tree/main/skills/apple-container
+source_repo: sanjay3290/ai-skills
+source_type: community
+date_added: "2026-07-09"
+author: sanjay3290
+tags: [macos, containers, oci, apple-silicon]
+tools: [claude, cursor, gemini]
+license: "Apache-2.0"
+license_source: "https://github.com/sanjay3290/ai-skills/blob/main/LICENSE"
+---
+
+# Apple `container`
+
+## When to Use
+
+- Use when building, running, or managing OCI/Linux containers on Apple-silicon macOS with Apple's open-source `container` CLI
+- Use when you want lightweight per-container VMs instead of a Docker daemon
+- Use when translating Docker-style workflows (build, run, exec, logs, networking) to Apple's container tooling
+
+Apple's `container` is an open-source CLI for building, running, and managing OCI/Linux
+containers on Apple-silicon Macs. Each container runs inside its own lightweight virtual
+machine (backed by the Containerization framework and the Virtualization API), so there is no
+shared daemon like Docker — services run per-user via `launchd`. Images are standard OCI
+artifacts, so they interoperate with Docker registries and other OCI tooling. The CLI is
+deliberately Docker-like (`container run`, `container build`, and image ops under
+`container image push`/`pull`), but it is a distinct tool: do not assume Docker command paths,
+flags, defaults, or daemon behavior carry over (e.g. there is no `container images`/`push`/`pull`
+top-level command — image verbs live under `container image`).
+
+## Safety Gate
+
+Container installation, service startup, image pulls, builds, runs, registry login, pushes,
+and resource cleanup change local or remote state. Explain the exact command, image registry,
+mounts, ports, privileges, and data-persistence impact, then obtain explicit user approval
+before executing it. Do not provide registry credentials, mount sensitive paths, or expose
+ports without the user's explicit instruction.
+
+## Requirements
+
+- **Apple silicon only** (M1 or later). Intel Macs are not supported.
+- **macOS 26 (Tahoe) is the officially supported target.** The maintainers do not support
+  older macOS and typically will not fix issues that can't be reproduced on 26. The binary
+  still runs on **macOS 15 (Sequoia)** but with reduced networking: only the single default
+  subnet is available, and the `container network` group and `--network` flag error out.
+  macOS-26-gated features are called out throughout the reference files.
+- **Version:** this skill documents the **1.0.0** release (the fullest feature set). The `machine`
+  group, `container cp`, `container export`, `container prune`, `container image prune`,
+  `container registry list`, and `container system version` were **added in 1.0.0** (not in 0.7.1)
+  — features that postdate 0.7.1 are flagged *(1.0.0+)* in the reference files. Run `container --version` and
+  `container <group> --help` to see what your installed build supports.
+- Install by downloading the signed `.pkg` installer from the project's GitHub releases
+  (`apple/container`) and running it. See `references/concepts.md` for the full
+  requirements/compatibility matrix and how the VM-per-container model works.
+
+## Setup
+
+Install the signed package, then start the background services once:
+
+1. **Download** the latest signed installer `.pkg` from the
+   [GitHub releases page](https://github.com/apple/container/releases).
+2. **Double-click** the downloaded package and follow the prompts, entering your admin
+   password so it can place files under `/usr/local`. (There is no documented CLI `installer`
+   invocation — installation is via the GUI package.)
+3. **Start the services** and confirm they are healthy:
+
+```bash
+# Start the container services (container-apiserver + helpers via launchd). On first run it
+# offers to install the default Linux kernel — accept it, or start non-interactively with
+# `--disable-kernel-install` and add a kernel later via `container system kernel set`.
+container system start
+
+# Verify services are healthy
+container system status
+```
+
+`container system start` must have run before any container/image/build command works — a
+connection/XPC error almost always means the services are stopped, so run it again. Stop and
+deregister the `launchd` services with `container system stop` (which takes only `-p/--prefix`).
+The startup flags for `container system start` (`-a/--app-root`, `--install-root`, `--log-root`,
+`--enable-kernel-install`/`--disable-kernel-install`, `--timeout`) are in
+`references/configuration.md`.
+
+**Upgrade / downgrade / uninstall** use helper scripts in `/usr/local/bin` (stop first with
+`container system stop`): `update-container.sh` (add `-v <version>` to pin a version), and
+`uninstall-container.sh -d` to remove user data or `-k` to keep it. Full recipes in
+`references/workflows.md`.
+
+## Command groups at a glance
+
+Invoke everything as `container <group> <subcommand>`. Container-lifecycle verbs (`run`,
+`create`, `start`, `stop`, `exec`, `logs`, `inspect`, `list`/`ls`, `delete`/`rm`, `kill`,
+`stats`) and `build` are top-level; image operations like `push`, `pull`, and `tag` live
+under `container image`. Run `container <group> --help` for exact flags, or read
+`references/commands.md` for the exhaustive matrix.
+
+| Group | What it does | Example |
+|-------|--------------|---------|
+| container lifecycle | Create, start, run, stop, exec, inspect, list, remove containers | `container run --rm -it docker.io/library/alpine sh` |
+| build | Build an OCI image from a Dockerfile in the builder VM | `container build -t myapp:latest .` |
+| image | List, tag, inspect, remove, load/save, prune local images; push/pull to registries | `container image ls` |
+| registry | Authenticate (login/logout/list) to OCI registries | `container registry login ghcr.io` |
+| system | Start/stop/status services, logs, disk usage (`df`), DNS, kernel, properties | `container system status` |
+| network | Create/list/remove container networks (**macOS 26 only**) | `container network create mynet` |
+| volume | Create/list/inspect/remove persistent volumes | `container volume create data` |
+| builder | Manage the builder VM that runs `container build` (start/stop/status) | `container builder status` |
+| machine *(1.0.0+)* | Persistent Linux "machine" environments (added in 1.0.0) | `container machine --help` |
+
+Exact subcommand names, aliases, arguments, and flags for each group live in
+`references/commands.md` — consult it before running an unfamiliar command rather than
+guessing Docker-equivalent syntax.
+
+## Navigating this skill
+
+Read the reference file that matches the task; do not guess flags or behavior.
+
+- **`references/commands.md`** — exhaustive CLI reference: every command group, subcommand,
+  alias, argument, and flag. Read this to construct any concrete `container ...` invocation,
+  or to confirm a flag exists before using it.
+- **`references/concepts.md`** — architecture (VM-per-container, Containerization framework),
+  system requirements and macOS 15 vs 26 differences, networking model, per-container IPs,
+  security model, and a Docker-vs-`container` comparison. Read this to explain how or why
+  something works, or when a Docker mental model gives the wrong answer.
+- **`references/configuration.md`** — the system service, `config.toml` / property model,
+  default kernel, DNS domains, default registry, builder resources, and machine settings.
+  Read this to change defaults, tune CPU/memory, point at a private registry, or manage the
+  kernel.
+- **`references/workflows.md`** — copy-pasteable task recipes (run an image, build & push,
+  wire up local DNS, mount a volume, expose ports) and troubleshooting for common failures.
+  Read this first when the user wants to accomplish a concrete end-to-end task.
+
+## Key rules
+
+- **This is not Docker.** The CLI resembles Docker, but flags, defaults, and daemon behavior
+  differ. Verify syntax in `references/commands.md` instead of assuming Docker equivalence.
+- **Always ensure services are up first.** Run `container system start` (and confirm with
+  `container system status`) before any container/image/build command; connection errors
+  usually mean the services are stopped.
+- **Images are standard OCI artifacts** and interoperate with Docker registries and other OCI
+  tools. Image references that omit a registry default to `docker.io` (configurable via the
+  `registry.domain` property — see `references/configuration.md`).
+- **Each container gets its own IP address** on its network (one lightweight VM per
+  container). There is no shared Docker bridge; reach a container directly by its IP, or set
+  up a local DNS domain (`container system dns create ...`, admin required) for name-based
+  access.
+- **`container network` requires macOS 26.** On macOS 15 only the single default subnet is
+  available and the network command group is unavailable — see `references/concepts.md`.
+- **Use fully-qualified image references** when precision matters (e.g.
+  `docker.io/library/alpine` rather than bare `alpine`) to avoid ambiguity about the source
+  registry.
+
+## Limitations
+
+- Apple Container requires Apple silicon and has materially different support and networking
+  behavior across macOS releases; verify the installed CLI version before relying on a flag.
+- OCI images and registry content are third-party inputs. Inspect and trust the image source
+  before pulling or running it.
+- This skill does not make container workloads safe by default: mounts, published ports,
+  privileged settings, registry credentials, and cleanup can expose or destroy data.
+- Stop before uninstalling, pruning, deleting containers, volumes, or images, and require
+  explicit approval for each destructive action.