Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    ap cycle time and bottleneck analyzer

    1

    Your accounts payable process is a black box until you measure the gaps between receipt and settlement.

    $2.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    ap cycle time and bottleneck analyzer

    ap cycle time and bottleneck analyzer

    Example session with this skill installed

    Analyze the attached AP log for Entity_A. I am authorized by the Finance Director. Use 3 days for validation and 5 days for approval SLAs. Identify why our P90 is so high.

    • Read your context and instructions
    • Compiled the ap cycle time

    The AP event log for Entity_A (E1) has been processed. The analysis covers 152 invoices processed between 2023-10-01 and 2023-12-31.

    AP Cycle Time and Bottleneck Analysis — Entity_A, 2024-01-20

    1. Scope, sources and assumptions

    Analysis based on source E1. Scope limited to authorized_entities: ["Entity_A"] granted by Finance Director. Total invoices: 152. Analysed: 148. Excluded: 4 (missing receipt_at). Time is calculated as calendar time.

    2. Stage cycle times

    StagenMeanMedianP90MaxShare of measured timeSLABreaches
    Receipt to Validation1482.41.04.512.018%3.022
    Validation to Approval1306.84.015.228.052%5.041
    Approval to Posting1251.10.52.05.08%n/a0
    Posting to Settlement1102.92.05.010.022%n/a0
    End-to-End11013.27.526.755.0100%n/a63

    3. Bottleneck

    RankStageImpact
    1Validation to ApprovalPrimary bottleneck (52% of duration)
    2Posting to SettlementSecondary delay (External/Terms)
    3Receipt to ValidationMinor delay

    4. Settlement timeliness

    Late rate: 14.5%. Mean days late: 3.2. Open past due: 8 items.

    5. Open invoices

    Invoice IDPending StageDays WaitingSLAOver SLA
    INV-9980Approval145Yes
    INV-9985Approval95Yes

    6. Control exceptions

    • SoD Conflict: Invoice INV-8821 (Validated and Approved by ACTOR_042).
    • Skipped Stage: Invoice INV-8840 (Posted without recorded Approval).
    • Information gap — organizational validation required: Actor ID missing for INV-8855 settlement.

    7. Draft actions for human approval

    • Investigate approval backlog for Business Unit: North_Logistics. (requires_human_approval: true, executed: false)
    • Review SoD conflict for ACTOR_042 on INV-8821. (requires_human_approval: true, executed: false)
      Management decision required before any escalation or payment.

    8. Warnings and information gaps

    • W04: Minimum stage sample not met for 'Posting to Settlement' in Dept_Marketing.
    • W09: 22 invoices missing due_date; late rate may be understated.

    9. Interpretation and items for human review

    1. The Validation to Approval stage is the primary driver of cycle time, exceeding SLA in 31% of cases.
    2. P90 variance (26.7 days) suggests significant outliers in the approval chain.
    3. Analytical estimate — validation required: Reducing approval median to 4 days would cut total cycle time by 28%.
      This analysis supports, and does not replace, professional judgment and management's decision.

    Next steps

    1. Review the list of 8 open invoices currently past due.
    2. Confirm if ACTOR_042 has emergency override permissions for SoD conflicts.
    3. Validate missing due dates for the 22 flagged invoices to correct the late settlement rate.

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

    About this skill

    Your accounts payable process is a black box until you measure the gaps between receipt and settlement. This skill stops the guesswork by analyzing event logs to identify exactly where invoices stall, from validation delays to approval bottlenecks.

    What it does

    • Stage timing analysis calculates mean, median, and P90 duration for every step from receipt to settlement.
    • Bottleneck ranking identifies and ranks the stages causing the most significant internal processing delays.
    • SLA monitoring flags specific invoices and stages that breach defined service level agreements.
    • Open item aging tracks currently active invoices, their pending stage, and days elapsed.
    • Control auditing identifies segregation-of-duties (SoD) conflicts and skipped process stages for human review.

    How it works

    1. Supply an AP event log containing timestamps for receipt, validation, approval, posting, and settlement.
    2. Define the analysis scope, including authorized entities and optional SLA thresholds for each stage.
    3. The skill generates a request.json and executes a deterministic Python script to process the calculations.
    4. Review the structured report detailing cycle times, bottlenecks, late rates, and control exceptions.

    Frameworks & tools

    This skill uses a deterministic Python processing engine to ensure calculation integrity. It relies on standard JSON schemas for data ingestion and provides outputs in GitHub-flavored Markdown.

    Why this beats prompting it yourself

    Generic prompts often hallucinate dates or fail to handle time-zone-agnostic calendar days correctly. This skill uses a hard-coded script to ensure every mean, median, and P90 value is mathematically accurate without rounding errors or inferred data.

    Use cases

    • Identify which business units or vendors experience the longest approval delays.
    • Audit segregation-of-duties by flagging invoices handled by the same actor across stages.
    • Quantify the impact of late settlements and track the late-payment rate.
    • Generate a prioritized list of "stuck" invoices for immediate follow-up.

    Known limitations

    Does not support three-way matching against POs or receipts. Calculations are restricted to calendar time and do not account for business hours or holidays. Requires a minimum group size for statistical reporting to ensure privacy.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.

    Read-only. No PO matching or duplicate detection. Calendar time only (no holiday logic). Requires minimum sample sizes for group stats. Actor IDs must be provided; does not deanonymize.

    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 buying a skill.

    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 days ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Listed3 days ago

    What's inside

    Frequently Asked Questions

    This skill identifies hidden bottlenecks by calculating the exact time spent between AP stages—like receipt to approval—and flags specific risk areas like segregation-of-duties (SoD) violations.

    The skill is compatible with any AI agent that supports Python code execution and JSON data handling, such as AutoGPT, BabyAGI, or custom LLM-based assistants.

    You will receive the pre-configured analysis logic, the deterministic Python processing script, and the standardized JSON schemas required for data ingestion and reporting.

    No, this skill uses a hard-coded script for all calculations to ensure mathematical precision, preventing the common rounding errors or date hallucinations found in standard text-based prompting.

    You need to provide an AP event log in a structured format (like CSV or JSON) containing timestamps for key process steps and unique identifiers for the actors involved.

    Current versions track total elapsed calendar time; however, future updates to the underlying Python engine will be made available to existing purchasers to include business-hour filtering.