Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Guide for building high-quality MCP (Model Context Protocol) servers and tool suites. Use this whenever the user asks to build, design, refactor, review, or evaluate an MCP server, expose an API through MCP, or improve tool naming, schemas, pagination, auth, or error handling.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use the native Microsoft 365 tools for Outlook Mail, Calendar, OneDrive, and Contacts via the Microsoft Graph API.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Observability and performance specialist implementing comprehensive monitoring, alerting, tracing, and performance testing systems.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use this skill when ordinary websearch is not enough and you need engine-specific public-web search strategy.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use nano-pdf to apply edits to a specific page in a PDF using a natural-language instruction.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use this when the user is asking about Windows Defender or native host protection rather than generic host-monitor output.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
When the user asks to scan, discover, or diagnose network hosts and services.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use the Notion API to create/read/update pages, data sources (databases), and blocks.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Obsidian vault = a normal folder on disk.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Oracle bundles your prompt + selected files into one “one-shot” request so another model can answer with real repo context (API or browser automation). Treat outputs as advisory: verify against the codebase + tests.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
When the user is managing contacts or running outreach campaigns.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use memory tools only when the user explicitly wants a stable fact or preference remembered beyond the current conversation.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use when addressing code review or QA feedback, especially when the feedback is unclear, broad, or technically questionable.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use this when the main job is to manage alert state cleanly: acknowledge, resolve, suppress, or reduce duplicate noise.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use this when the job is to decide whether the system should remain in monitor or move to guarded, lockdown, or irassist.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use this when the user wants repeatable defensive behavior instead of one-off triage.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use when the user is reviewing a security alert, posture change, suspicious network behavior, firewall issue, or combined monitoring output.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Guide for creating new skills, improving existing skills, and evaluating skill quality. Use this whenever the user wants to turn a workflow into a skill, revise a skill, improve triggering behavior, or add evals and benchmarks for a skill.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use slack to react, manage pins, send/edit/delete messages, and fetch member info through the configured Slack provider.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use when implementing or reviewing framework-specific code that should be verified against current official docs, versioned guidance, or source-cited examples rather than memory.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use this when the user is troubleshooting the local machine, checking service health, or reviewing host and gateway monitoring state.
Threat-Vector-Security/guardian-agent
Skill Claude CodeCodex
Use when encountering a bug, failing test, broken integration, or unexpected behavior, before proposing fixes.