More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Compliance, Certifications and Risks

    1

    Run SOC 2, ISO 27001, third-party risk, transparency and AI oversight. 10 ordered skills, starting with Transparency and Explainability, Bias Mitigation and Fairness, Human Oversight of AI.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Compliance, Certifications and Risks

    Compliance, Certifications and Risks

    Example session with this skill installed

    Fictional lender "Northbeam Credit" uses a scoring model to pre-decline small-business loan applications. Declines are sent automatically; staff only see approvals. The team wants an oversight design before an internal audit.

    • Read your context and instructions
    • Compiled the compliance certifications

    Human Oversight Design: Northbeam small-business pre-decline model v3

    Date: fictional | Owner: Head of Credit Risk | Status: Draft (not legal advice)

    1. Risk and pattern

    Pattern: human-on-the-loop for approvals; human-in-the-loop for declines meeting a trigger. Rationale: declines affect access to credit and current process has no human check.

    2. Ability matrix

    | Ability | Mechanism | Owner | Gap? |
    | Understand limits/anomalies | Training module + model card limits section (thin files, new businesses) | Credit Risk | Training not yet written |
    | Awareness of automation bias | Reviewer must record own assessment before seeing model score on sampled cases | Credit Ops | Needs tooling change |
    | Interpret outputs | Screen shows score, confidence band, top factors | Data Science | Top factors missing |
    | Override/reverse | Analyst can overturn any decline and trigger re-score | Credit Ops | None |
    | Stop the system | Risk lead can switch to manual queue in under one working hour | Risk | Not yet tested |

    3. Review triggers

    | Trigger | Rule | Action | Owner |
    | Thin file | fewer than 12 months of data | mandatory analyst review before decline | Credit Ops |
    | Low confidence | band marked low | mandatory review | Data Science |
    | Group-sensitive drift | weekly decline-rate gap alert | pause + investigate | Risk |

    4-5. Reviewer experience and stop procedure

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The problem

    Risk and security leaders often need a repeatable process, not a one-off prompt. This pack targets: Run SOC 2, ISO 27001, third-party risk, transparency and AI oversight.

    What's inside (10 skills, suggested learning order)

    1. Transparency and Explainability — Communicate how models decide.
    2. Bias Mitigation and Fairness — Reduce algorithmic discrimination.
    3. Human Oversight of AI — Design human controls.
    4. AI Incident Management — Respond to AI failures.
    5. Financial Compliance (SOC 2, PCI) — Meet financial standards.
    6. SOC 2 — Prepare SOC 2 certification.
    7. ISO 27001 — Information security management.
    8. Third-Party Risk Management — Assess vendors.
    9. Compliance and Integrity Management — Integrity programs.
    10. Data Sovereignty — Data residency and jurisdiction.

    Why a skill pack instead of a one-off prompt

    Each skill gives the agent a defined trigger, step-by-step procedure and output format, so results are consistent across sessions and easier to review.

    How to use

    1. Install the pack in your SKILL.md-compatible agent.
    2. Ask for the task in plain language (for example: "communicate how models decide").
    3. Review the output against the skill's quality checks before using it.

    Outputs are drafts that need human review; they are not professional, legal or financial advice. Tools, APIs and prices change; check current vendor documentation before relying on version-specific details. Quality depends on the context you give the agent (data, requirements, constraints). Instruction-only skills: they produce documents and plans, not running software.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 8 days ago

    Permissions

    No special permissions declared or detected

    Listed8 days ago

    What's inside

    Frequently Asked Questions

    10 skills, each with SKILL.md and references/sources.md: Transparency and Explainability; Bias Mitigation and Fairness; Human Oversight of AI; AI Incident Management; Financial Compliance (SOC 2, PCI); SOC 2; ISO 27001; Third-Party Risk Management; Compliance and Integrity Management; Data Sovereignty.

    Risk and security leaders.

    Agents that read the SKILL.md format. See the Compatibility note for what was actually tested.

    New in Legal & Compliance