Threat-Vector-Security/guardian-agent

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.

Threat-Vector-Security/guardian-agent

Skill Claude CodeCodex

Use when implementing or changing code behavior, before writing production code.

Threat-Vector-Security/guardian-agent

Skill Claude CodeCodex

When the user is working with threat indicators, watchlists, or intelligence findings.

Threat-Vector-Security/guardian-agent

Skill Claude CodeCodex

Use this as a bootstrap workflow when the user explicitly wants help choosing or applying the right skill.