More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    standard operating procedure builder agent

    1

    Converts fragmented operational knowledge into audit-ready, controlled standard operating procedures.

    $7.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    standard operating procedure builder agent

    standard operating procedure builder agent

    Example session with this skill installed

    I have a transcript of a workshop where we discussed the new invoice approval flow. We use SAP and Slack. Can you turn this into a formal SOP with controls for segregation of duties?

    • Read your context and instructions
    • Compiled the standard operating procedure

    STANDARD OPERATING PROCEDURE: Invoice Approval

    Roles: Accounts Payable Clerk, Finance Manager
    Systems: SAP ERP, Slack
    Trigger: Invoice receipt in AP inbox

    Step 1: AP Clerk validates invoice against PO in SAP.
    Control: Duplicate check must pass...

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

    About this skill

    The problem

    Operational knowledge is often trapped in tribal memory, fragmented chat logs, or outdated screenshots. This lack of formal documentation leads to inconsistent execution, audit failures, and high onboarding costs.

    What it does

    • Extracts structured process steps from interviews, transcripts, meeting notes, and screenshots.
    • Builds audit-ready SOPs including roles, prerequisites, decision logic, and control points.
    • Identifies gaps in segregation of duties, missing approvals, and undocumented exceptions.
    • Generates supplementary artifacts like operator checklists, runbooks, and training packages.
    • Produces gap reports when source materials conflict or lack authoritative evidence.

    Why this beats prompting it yourself

    Basic prompts often hallucinate missing steps or ignore critical compliance controls. This tool enforces a strict governance framework that distinguishes policy from procedure and prevents the "invention" of authority. It treats documentation as a structured data problem, ensuring every step has an owner, an expected result, and an evidence requirement.

    Use cases

    • Converting SME interviews and screen recordings into executable work instructions.
    • Standardizing fragmented processes across different regional teams or departments.
    • Creating controlled documentation for audit preparation or regulatory compliance.
    • Modernizing outdated manuals after system migrations or organizational changes.

    Known limitations

    Requires authoritative source material to avoid assumptions. It cannot independently verify legal, medical, or high-risk safety requirements without qualified human review.

    Requires authoritative source material. Cannot verify legal, medical, or high-risk safety requirements without specialist human review. Does not independently confirm system access permissions.

    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 3 months ago

    Permissions

    Read Files
    Browser
    Write Files

    File Scopes

    *.md
    *.txt
    *.csv
    *.xlsx
    *.xls
    *.json
    *.jsonl
    *.yaml
    *.yml
    *.xml
    *.html
    *.pdf
    *.doc
    *.docx
    *.ppt
    *.pptx
    *.png
    *.jpg
    *.jpeg
    *.webp
    *.tif
    *.tiff
    *.eml
    *.msg
    *.vtt
    *.srt
    *.drawio
    *.bpmn
    README.md
    interviews/**
    transcripts/**
    recordings/**
    screenshots/**
    annotations/**
    notes/**
    workshops/**
    meetings/**
    policies/**
    standards/**
    regulations/**
    contracts/**
    sops/**
    procedures/**
    work-instructions/**
    runbooks/**
    job-aids/**
    checklists/**
    forms/**
    templates/**
    process-maps/**
    swimlanes/**
    bpmn/**
    raci/**
    roles/**
    organization/**
    systems/**
    manuals/**
    training/**
    onboarding/**
    tickets/**
    incidents/**
    escalations/**
    audit/**
    quality/**
    controls/**
    risks/**
    compliance/**
    security/**
    privacy/**
    safety/**
    business-continuity/**
    records/**
    retention/**
    metrics/**
    validation/**
    approvals/**
    revision-history/**
    change-control/**
    localization/**
    regional-variants/**
    ai-readiness/**
    reports/**
    drafts/**
    published/**
    retired/**
    docs/**

    This skill uses file access to read user-provided interviews, transcripts, notes, recordings, screenshots, process maps, policies, standards, regulations, contracts, existing SOPs, work instructions, runbooks, checklists, forms, templates, training materials, system manuals, role descriptions, organizational charts, control matrices, risk registers, audit reports, quality findings, incident records, ticket histories, escalation records, business-continuity plans, retention schedules, revision histories, and approval records. It uses write access to create SOPs, work instructions, runbooks, desk procedures, operator checklists, reviewer checklists, approval checklists, process maps, role matrices, control records, exception catalogs, escalation paths, evidence matrices, validation plans, training outlines, competency checklists, revision histories, governance recommendations, audit reports, future-state procedures, structured JSON specifications, and SKILL.md files. Browser access is useful when the host environment permits authorized intranet access, policy-reference review, current public standards research, regulatory-source validation, platform-documentation review, terminology research, or system-interface reference validation. The skill should clearly distinguish: Verified Source Fact: Directly supported by an approved document, system record, observation, or authorized stakeholder. Approved Policy Requirement: A mandatory rule supported by the organization's authoritative policy source. Observed Current Practice: What operators currently do, whether approved or not. Recommended Future State: A proposed process improvement requiring review and approval. Assumption: An unverified interpretation used only to structure a draft. Conflict: Two or more sources provide incompatible instructions, ownership, controls, or requirements. Open Question: A missing decision preventing authoritative completion. Blocked: A section that cannot be finalized because evidence, ownership, system validation, or approval is unavailable. Draft: A procedure that has not completed validation and approval. Approved: A procedure formally authorized under the organization's governance process. The agent must never invent policy requirements, legal obligations, regulatory obligations, system fields, system behavior, approvals, thresholds, service-level commitments, escalation contacts, access permissions, retention periods, safety controls, security rules, forms, or authoritative process steps. The agent must not silently reconcile conflicting sources. The agent must not present observed employee practice as approved policy unless authority is verified. The agent must not present a future-state recommendation as the current operating procedure. The agent must never expose passwords, access tokens, private keys, authentication secrets, protected health information, confidential customer data, complete banking details, employee personal data, or restricted security information. Screenshots should support written instructions rather than replace them. Sensitive information should be masked, and every screenshot should be linked to a specific step or decision. An SOP should not be described as approved, effective, compliant, validated, or operationally proven without documented evidence. Public examples should use fictional, anonymized, masked, aggregated, or approved data.

    Listed3 months ago

    What's inside

    Frequently Asked Questions

    The agent extracts information from interviews, meeting transcripts, chat logs, and screenshots to build structured documentation, identifying gaps in decision logic and control points along the way.

    Unlike basic prompting, this skill enforces a strict governance framework that prevents hallucinated steps and ensures every procedure includes specific owners, expected results, and evidence requirements for audits.

    Your purchase includes the core SOP Builder agent, pre-configured templates for checklists and runbooks, and a gap report generator to identify missing process information.

    While the agent handles the heavy lifting of structuring and cross-referencing, a qualified human must review all outputs to verify legal, medical, or high-risk safety compliance before implementation.

    This skill is designed for compatibility with leading LLM-based agent platforms and can be integrated into your existing operations workflow via standard API or marketplace-supported interfaces.

    Updates are delivered through the marketplace to ensure the agent stays aligned with evolving documentation standards and improved logic for identifying segregation-of-duty conflicts.

    New in Business & Operations