Ship agent workflows in 30 seconds. Browse 2,000+ expert-built and security scanned skill -> Browse skills
THE AGENSI STORE
89 skills found
by Matthew King
Audit, score, and improve your AI agent skills for higher quality, lower token costs, better reliability, and marketplace success. Get actionable recommendations for prompts, instructions, tool usage, error handling, and user experience.
Audit and refine vulnerability reports to maximize bounty payouts and reduce N/A or duplicate closures.
A professional security triage workflow for mapping attack surfaces and prioritizing DeFi smart contract vulnerabilities.
by LocoLoboZ
Orchestrate independent reviews, adversarial audits, and multimodal analysis via secondary models and external tools.
by LB Creations
Security review of Kandji agent configurations, library items, and automation for compliance and safety
An adversarial gate that audits an AI eval or test suite — LLM-judge rubrics, datasets, regression tests, metrics — for gameable criteria, data leakage, missing edge cases, and non-determinism, then returns one PASS/REVISE/FAIL verdict.
by Shandra
Turns dependency scan reports and security alerts into prioritized remediation plans with severity, exploitability, affected area, safe fix strategy, and verification checklists.
Audit, verify, and format academic citations across AMA, APA, and Vancouver styles to eliminate AI hallucinations.
by Shandra
Converts internal SOPs, policies, checklists, and process notes into structured AI-agent workflows with decision trees, escalation rules, QA checkpoints, and audit-ready outputs.
Audits any AI draft for unsupported claims — flags each one, grades its source, and returns a substantiation report.
by LocoLoboZ
A structured governance auditor to optimize AI project instructions, clean up context, and manage workspace health.
Analyzes AI agents for performance, reliability, security, and optimization opportunities.
Systematic audit for AI prompts to detect security flaws, bias, and cost-inefficiencies with auto-optimization.
An adversarial security gate that audits untrusted content — web pages, tool outputs, documents, emails — for embedded instructions, exfiltration, and authority spoofing, then returns a SAFE/REVIEW/BLOCK verdict.
Find the model-version coupling that breaks when you swap LLMs. Flags hardcoded model names and versions, deprecated or renamed parameters (the max_tokens to max_completion_tokens class of change), hardcoded token and context-window limits, response-format parsing tied to one model's output, tool-schema format coupling between providers, and hardcoded per-token cost constants. The patterns load from an editable model-rules table you update as new models ship.
An adversarial gate that audits an MCP server or agent tool definition — schemas, descriptions, scopes, auth — for tool poisoning, excessive agency, injectable descriptions, and missing access controls, then returns one SAFE/REVIEW/BLOCK verdict.
by Ryan lyell
Intelligently audit your repo and workflow to recommend, install, or create custom AI agent skills.
by Timoranjes
Evaluate third-party agent skills for command injection, prompt injection, and data exfiltration before installation.
Write and review the docs AI agents actually read — AGENTS.md for your repo and llms.txt for your site. Drafts them from scratch or audits existing ones for completeness, clarity, and wasted context, with a PASS or REVISE verdict.
Adversarially audit your agent hooks before you trust them. Catches command injection, secret leakage, over-broad matchers, destructive actions, and blocking-logic mistakes in pre/post-tool-use, prompt, and stop hooks — with a PASS or REVISE verdict and severity-ranked fixes.
Find and fix every legacy Salesforce API version before the Summer '27/'28 retirements break your integrations — scan, phased plan, CIO-ready report. Audits, reports, and upgrades legacy Salesforce API versions to prevent integration failures and 410 GONE errors.
Automated security auditing and risk assessment for Model Context Protocol (MCP) servers.
by Shandra
Audits AI agent failures and converts recurring mistakes into durable rules, anti-patterns, regression tests, memory candidates, and improved SKILL.md sections.
An adversarial gate that audits a research brief or AI-generated answer for unsupported claims, weak or outdated sources, missing citations, and one-sided framing — returning a structured TRUST/VERIFY/REJECT verdict with the exact passage quoted and what to verify for each.