More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Proof of Done

    1

    Makes your agent verify every change it makes to real records, wait for approval on anything irreversible, and report with counts that add up.

    $29

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Proof of Done

    Proof of Done

    Example session with this skill installed

    contacts.csv is an export of our CRM and call_results.csv is what my sales rep logged from yesterday's calls. Update the call_outcome and next_step columns from the call results and tell me when it's done.

    • Read your context and instructions
    • Compiled the proof of done
    • Generated the data export

    Result: 8 of 12 call results applied and verified – 2 need you

    OutcomeCount
    Updated and verified8
    Already correct, left alone1
    Skipped (duplicate row in the call log)1
    Needs your decision2
    Total rows in call_results.csv12

    Needs your decision

    Rana Haddad – two contacts share this name: C-104 (Levant Tech) and C-116 (Northern Mills). I updated neither. Which one took the call?

    • Huda Farah, Balqa Paints – no such contact in contacts.csv. I did not create one.

    How it was verified

    After writing, I re-read contacts.csv and compared each of the eight rows to the call log. Only those eight rows changed, and only in call_outcome and next_step.

    Undo

    The original is saved in the audit folder; say "undo" and I'll restore it.

    call_results.csv

    CSV · data export

    Generated

    Example file from a real run - the skill writes it into your workspace.

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

    About this skill

    Stop your agent saying "done" when it isn't.

    When an agent updates 50 CRM records, cleans a folder or sends a batch of emails, the usual failure is quiet: three records that silently failed, a duplicate updated twice, a file deleted that shouldn't have been, and a cheerful "all done!" on top. Proof of Done is a routine that makes those failures impossible to miss.

    What it makes the agent do

    1. Scope – pin down exactly which items are in play.
    2. Inspect – read the live state first; spot records that are already correct, missing, ambiguous, duplicated or conflicting.
    3. Plan – one planned action per item, shown as counts plus exceptions.
    4. Approve – wait for your yes before anything that can't be undone (send, delete, pay, merge, publish).
    5. Execute – canary first, log each item, never blindly retry a send or a payment.
    6. Verify and report – read every change back from the system, reconcile, and report honestly.

    Every item ends in one of eight statuses, and the totals must add up to the number in scope before the agent is allowed to report.

    What's inside

    • Three levels of care (light, standard, strict), so a one-cell fix is not treated like a bulk delete.
    • A change-ledger script (single Python file, no installs). It records before, intended and read-back values, refuses "verified" without evidence, refuses a final report while anything is unresolved, and produces the audit report, an item CSV and an undo list.
    • Playbooks for nine kinds of system: CRMs, spreadsheets, email and messaging, calendars, files, databases, ticket trackers, payments and accounting, online stores.
    • A risk catalogue of which actions need approval and why.
    • Report templates, including partial runs, unattended runs, undo reports, a compliance sign-off record and a "the agent made a mistake" report.

    Tested

    Three scenarios, each run three times with and without the skill on Claude, scored by independent graders (18 runs, 57 checks per side):

    TestWith skillWithout
    Bulk CRM update with planted traps24 of 2417 of 24
    "Delete all the draft files"18 of 1815 of 18
    One-cell fix that should stay lightweight15 of 1515 of 15

    Without the skill, all three delete runs permanently removed five files with no confirmation and no backup. With it, none did. On the bulk update the data was right both ways; the difference was the report: counts that add up, and a statement of how the result was checked.

    This is a small sample on one model, and the unassisted model was already careful about ambiguous matches. What the skill adds is approval before irreversible actions, and reports you can check. It costs about 13% more tokens per task.

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

    It guides the agent's behaviour; it cannot technically block an action or guarantee an outcome. It does not connect to any system: your agent still needs its own access to the CRM, sheet or inbox. Sends, payments and permanent deletes cannot be undone, so for those it relies on approval beforehand. Verification of what happened inside a third-party system is only as good as what the agent can read back. Tested on three scenarios with one model.

    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 2 days ago

    Nothing to install. It runs in your AI agent.

    Optional
    Python 3.8+

    The ledger script needs an agent that can run Python. Without it, the skill keeps the same ledger as a table and reconciles by hand.

    Permissions

    File Scopes

    An
    audit
    folder
    in
    the
    working
    directory:
    ledger
    (.jsonl)
    audit_report.md
    audit_items.csv
    and
    backup
    copies

    The skill makes no network calls and needs no API keys. Any access to your CRM, inbox or other systems comes from your own agent's connectors, not from this skill. It tells the agent to keep passwords and card numbers out of the ledger.

    Listed4 days ago
    Updated2 days ago

    What's inside

    Frequently Asked Questions

    No. It has three levels of care. A one-cell fix or a file rename gets a check, the change, a read-back and a one-line report, with no ledger and no approval step. In testing, a small fix ran the same with and without the skill.

    Any system your agent can already reach. It includes playbooks for CRMs, spreadsheets, email and messaging, calendars, files, databases, ticket trackers, payments and accounting, and online stores. It does not provide the connection itself.

    Only for the bundled ledger script, which uses the standard library and needs no installs. If your agent cannot run code, the skill keeps the same ledger as a table and does the reconciliation explicitly.

    For updates, yes: it saves the before-value of every field it changes and can restore them, after checking nobody has edited the record since. Sends, payments and permanent deletes cannot be undone, which is why the skill asks for approval before those.

    It does everything reversible, holds back anything irreversible as 'pending approval' with the plan ready, and says so at the top of its report.

    Three scenarios, three runs each with and without the skill on Claude, scored by independent graders: 57 of 57 checks passed with the skill, 47 of 57 without. It is a small sample on one model, so treat it as indicative.

    New in Workflow Automation