Best fit
Classify a consequential people-facing action as suitable for automation, revision, delay, human review, human delivery, or no automation.
// Productivity
Should This Be Automated?
Classify a consequential people-facing action as suitable for automation, revision, delay, human review, human delivery, or no automation.
What problem does Should This Be Automated? solve?
Classify a consequential people-facing action as suitable for automation, revision, delay, human review, human delivery, or no automation.
Use it to
- Preflight an automated suspension or rejection
- Check whether a customer-facing notice needs human delivery
- Review an agent action before it becomes irreversible
What it returns
- Stable verdict and risk level
- Evidence, inference, alternatives, and missing-context ledger
- Bounded next action and explicit human-review reason
A representative input and result
input A billing agent plans to publicly flag a disputed account and freeze access without an appeal path.
result verdict: do_not_automate
confidence: limited
observations: [directly supplied facts]
alternative_explanations: [at least one]
recommended_action: reversible next step
human_review: explicit when stakes or authority require it
Access and approval boundaries
- Read only the text or structured context the user deliberately supplies.
- No terminal, file write, browser, network, credential, messaging, publication, purchase, or account-change permission.
Known limitations
- It does not authorize an action or establish legal compliance.
- It cannot verify facts or infer a recipient's mental state.
- Organizations remain responsible for policy, appeals, human staffing, and final decisions.
// choose with context
Is Should This Be Automated? the right skill?
It returns
Stable verdict and risk level. Evidence, inference, alternatives, and missing-context ledger.
Do not use it as
It does not authorize an action or establish legal compliance.
Compatibility, access, version, and licence
- Reads or accesses
- Declared local scope: No filesystem access required; user-supplied prompt context only.
- Compatibility
- SKILL.md-compatible agents Plain-language prompts or YAML/JSON-shaped context No API key, provider account, browser, or network access
- Version
- 1.0.0
- Licence
- Review the package licence and seller terms at the linked destination.
Questions
Can it know what another person feels or intends?
No. It separates observations from calibrated hypotheses and alternative explanations.
Does it diagnose manipulation, abuse, attachment, or mental health?
No. It refuses diagnosis and does not turn communication patterns into claims about a person.
Can it send, publish, or act for me?
No. It returns decision support or a draft only and performs no external action.
What happens in a high-stakes case?
It lowers certainty, avoids authorization, and recommends an accountable qualified human when appropriate.
Does a benign case always escalate?
No. The contract requires proportionality and includes benign regressions specifically to prevent reflexive handoff.
Are the tests proof that people will react well?
No. They verify package and safety contracts, not human reaction, legal sufficiency, or semantic perfection.
Should This Be Automated? keeps proof and approval boundaries visible.
The listing includes the tested package, realistic samples, declared permissions, and known limitations.
Get Should This Be Automated? on Agensi