Reproduce, minimize, localize, identify root cause, and distinguish diagnosis from an authorized fix. Prefer root-cause over symptom patches.

Local text-to-speech via sherpa-onnx (offline, no cloud)

Create, search, and manage Bear notes via grizzly CLI.

SOAP / WSDL exploitation — WSDL enumeration via ?wsdl, XXE in SOAP envelope, WS-Addressing replay, WS-Security UsernameToken brute, SAML token injection in WS-Trust, schema validation bypass.

Hunt XML External Entity flaws in parsers and validate file read / SSRF impact with strict negative controls.

Use this skill when you need to initialize or restart local web and mobile app projects through the bundled Rust `ii-app` CLI instead of calling MCP tools.

Add a new knowledge domain to your existing system. Derives domain-specific configuration through conversation, generates domain folders, templates, and vocabulary while preserving and connecting to your existing architecture.

Use this skill when reviewing or writing code that handles user input, authentication, file I/O, network requests, or database queries. Always check for common security vulnerabilities before considering the code complete.

Modify an asset file in the project. Use 'assets-get-data' first to inspect the asset structure before modifying. Not allowed to modify asset files in the 'Packages/' folder — modify them in 'Assets/'. Three modification surfaces are available (content, pathPatches, jsonPatch) — see the skill body for details.

Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.

How to author custom commands for the null-type CLI using the co-generated SDK.

How to author custom commands for the api CLI using the co-generated SDK.

How to author custom commands for the api-wide-base-path-with-default CLI using the co-generated SDK.

Market strategy analyst performing SWOT, competitive positioning, market-timing assessment, and go-to-market recommendations from research findings. Use after the research-agent has produced market data.

AATMF T11 — Agentic & Orchestrator Exploitation. MCP tool poisoning, agent-to-agent prompt injection, tool-result spoofing, orchestrator state confusion.

AATMF T8 — External Deception & Misinformation. Misinfo generation at scale, persona impersonation, document fabrication, hallucination weaponization.

AATMF T5 — Model & API Exploitation. Rate-limit abuse, token-cost amplification, schema bypass, model-version manipulation.

Process screenshot-based UI/UX feedback to fix visual issues — use when users share screenshots of bugs

Use this when you have finished making code changes and you are ready to update the documentation based on those changes.

Discover and install agent skills from the open ecosystem. Use when you encounter an unfamiliar domain, framework, or workflow that you lack specialized knowledge about, or when your coordinator suggests searching for skills before starting a task.