Loading...
Loading...
Found 21 Skills
Use for authorized security assessment of LLM applications and AI agents, including prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.
Audits AGENTS.md and CLAUDE.md files using execution-first standards. Checks commands, gotchas, and signal-to-noise ratio. Use when asked to audit, review, score, refactor, or improve agent instruction files, fix stale commands, or reduce bloat.
Use this skill when auditing AI agent skills for security vulnerabilities, prompt injection, permission abuse, supply chain risks, or structural quality. Triggers on skill review, security audit, skill safety check, prompt injection detection, skill trust verification, skill quality gate, and any task requiring security analysis of AI agent skill files.
Data Cloud 360° view of a single Agentforce session. Pulls 24 STDM + GenAI DMO rows via the DC Query REST API, assembles a hierarchical session tree (Interaction → Step → Generation → GatewayRequest), renders a human-readable summary with transcript + per-turn topic/action invocations + LLM generations + tool calls + audit chain. TRIGGER when user asks to trace, inspect, summarize, or describe a specific Agentforce session by session id (Agent Session UUID `019d…` or MessagingSession id `0Mw…`). Also triggers on session discovery — find/list/search sessions by time, agent, channel, outcome, or conversation text — when the user has no session id yet. DO NOT TRIGGER for design-time architecture questions (use investigating-agentforce-architecture instead) or for runtime perf/latency/SLO questions that require platform telemetry beyond Data Cloud.
Comprehensive security audit of codebase using multiple security-auditor agents. Use before production deployments or after major features.
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, inspect what the agent actually changed and verified, report gaps, and optionally make scoped fixes when the user authorizes repair.
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches. AI agents running in CI/CD pipelines.
Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.
Perform a systematic diagnostic scan of an AI workflow across 5 quality dimensions — prompt quality, context efficiency, tool health, architecture fitness, and safety — producing a scored report with prioritized remediation actions.
Creates or audits a Claude Code subagent file. Use when user says 'create an agent', 'build a subagent', 'review this agent', 'audit our agents', 'add a code-reviewer agent', or 'our agents are too broad'. Do NOT use for skills (use create-or-audit-skill), hooks (use create-or-audit-hook), or CLAUDE.md files (use create-or-audit-claude-md).
Run comprehensive agent-native architecture review with scored principles
Full agent verification suite. Runs security, patterns, quality, and language-specific checks. Use when asked to "verify agent", "verify my agent", "audit agent", or "full verification".