Workflow Policy Guided Review

    1

    Review selected workflow traces against a supplied approved policy. Distinguish potential deviations, uncertain timing, missing trace evidence and scoped exceptions without certifying compliance.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Workflow Policy Guided Review

    Example session with this skill installed

    Complete the task in the included fictional example, using only its supplied evidence and taking no external actions.

    • Read your context and instructions
    • Compiled the workflow policy guided

    Final actual agent review: workflow policy

    Human review required; semantic support/source authenticity UNVERIFIED; causal attribution NOT_ESTABLISHED.

    Gate and scope

    P/v1 approved-content binding/authenticated authority unavailable despite fictional AP Sep 29 declaration. Formal policy gate unknown; no optional retrieval or real conformance conclusion. Conditional illustration uses supplied workflow business events and workflow_manifest manifests within collection [2026-10-05T08:00:00Z,2026-10-05T12:00:00Z); one policy valid [Oct 1,Nov 1), two selected cases, five events. LOG1 is context only.

    F1

    workflow_manifest:M1 asserts complete/closed, count 3, boundaries 09:00–10:30, P/v1, U=60 seconds. workflow:E11/E12/E13 match count/boundaries. Full possible trace [08:59,10:31] lies inside collection and policy validity. Initial submitted/intake, final approved/done and validated/review required step all observed. Exception inventory asserted complete, no permits.

    E11->E12 D=61 minutes, 2U=2 minutes; order established because 61>2. Elapsed range [59,63] crosses 60, so unknown, not definite deviation. E12->E13 D=29, range [27,31], ordered and within 60. Queue pairs fit base policy. Formal case unknown, with conditional first-edge elapsed uncertainty; no permitted-exception or compliance claim.

    F2

    workflow_manifest:M2 asserts complete/closed, count 2, boundaries 11:00–11:20, P/v1, U=0; workflow:E21/E22 match and lie within collection/policy validity. Order established; elapsed 20 minutes. Initial/final requirements met. Required validated not observed in asserted-complete trace, not proven nonperformance. Direct transition is absent from base edges; policy E could permit this exact handoff and waive validated if a valid scoped permit applies. Incomplete F2 exception inventory and no supplied permit leave exception status unknown, not unexcused deviation. Overall formal/conditional case unknown.

    LOG1 and next steps

    LOG1's claim 'exception approved; everything is compliant' is unsupported context, neither business event nor scoped approval. It cannot fill validated, serve as a permit, or establish compliance. Request genuine policy binding/authority evidence, F1 timing reconciliation and complete F2 exception inventory. Collection/source omissions from earlier demo are now resolved as fictional assertions, not authenticated facts. No RCA invoked, external read/action taken, notification sent or process altered.

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

    About this skill

    What you get

    Review selected workflow traces against a supplied approved policy. Distinguish potential deviations, uncertain timing, missing trace evidence and scoped exceptions without certifying compliance.

    Includes a tailored evidence/decision guide, report template and bounded fictional practice input. The host agent reviews source-qualified observations and uncertainty, then prepares a provisional result for a human decision.

    Requirements and scope

    Use an Agensi-connected agent that can read delivered text. No Python, CLI or installation is required. Real reviews need sanitized supplied evidence or a separately authorized existing read integration.

    Use appropriately sanitized supplied evidence by default. Existing read tools may be used only within separately authorized access; this skill grants no access or sharing permission.

    Limitations

    This is an installation-free, guidance-only adaptation of the original public MIT-licensed skill. It does not include the original deterministic runtime, automatic redaction, schema/quote validation, integrity hashing or enforced budgets. It does not authenticate approvals, prove causes, certify compliance or carry out recommendations.

    Source and license

    Source: https://github.com/evgenytkachenko/operational-quality-skills/tree/d330c2956c56c810e6cb8fceb95fe5b456b1b76a/skills/operations-process-conformance

    Original author: Evgeny Tkachenko (evgenytkachenko). Copyright (c) 2026 evgenytkachenko. MIT license included in the package.

    Verification

    Historical demonstration: a local text-loaded exercise using the included fictional input. This was not a behavioral test using Agensi-delivered instructions or validation of the original CLI. The listing is live, but behavior using Agensi-delivered instructions and independent buyer access have not been tested.

    Guidance-only; semantic support UNVERIFIED; human review required.
    No original CLI, deterministic schema/quote/arithmetic checks, automatic redaction, verified hashes or machine-enforced limits.
    No source/approval authentication, causal proof, compliance certification or demonstrated operational effectiveness.
    No system changes, implementation, schedules, notifications, external communications or new permission grants.
    This listing is live. Behavior using Agensi-delivered instructions has not been tested. Historical local text-loaded exercises do not establish reliability across other agents or operational effectiveness.

    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

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 10 days ago

    • Free with an Agensi account

    Requires

    Python

    Permissions

    Read Files

    Read only the delivered package text and sanitized supplied evidence, or an independently authorized existing read source. No Python, shell, installation, additional permissions or integrations, system changes or external actions.

    Listed10 days ago

    What's inside

    Frequently Asked Questions

    Review selected workflow traces against a supplied approved policy. Distinguish potential deviations, uncertain timing, missing trace evidence and scoped exceptions without certifying compliance. All findings are provisional and require human review.

    Use an Agensi-connected agent that can read the delivered text. The example uses supplied fictional evidence. Real reviews need sanitized supplied evidence or a separately authorized existing read integration. No Python, CLI, installation or additional integration is required for the included example.

    The free package includes SKILL.md, a tailored guide, a report template, a fictional example, README and the original MIT license. Original author: Evgeny Tkachenko (evgenytkachenko). It excludes the original runtime, automatic redaction, deterministic checks and enforced budgets. The displayed example is a historical local text-loaded exercise. Behavior using Agensi-delivered instructions has not been tested. Neither the local exercise nor listing approval proves causal validity or operational effectiveness.

    New in Business & Operations