How do I install the Assess Service Change skill?

Run npx skillmds@latest add mashimashica/assess-service-change in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Assess Service Change safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Assess Service Change?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Assess Service Change free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Assess Service Change?

mashimashica (@mashimashica) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Assess Service Change by mashimashica

Name: Assess Service Change
Author: mashimashica

Assess Service Change

Assess whether a service change meets the criteria for a specified pilot using baseline and candidate request measurements. Use when measurement comparability, responsiveness, reliability, and the limits of a pilot decision need to be established.

mashimashica Updated Sep 17, 2026

File contents

Service Change Assessment

Purpose

Support a justified decision about a service change's suitability for the specified pilot conditions.

Outcomes

A judgment against each applicable pilot criterion is supported by comparable measurements and traceable calculations.
The scope and limits of the judgment, including their effects on the pilot decision, are explicit.

Activities & Tasks

The following Tasks are required for this assessment. Their dependencies follow the evidence needed for each judgment.

Establishing the assessment basis

Identify the baseline and candidate measurements and confirm the source and applicability of the pilot conditions. Check that the service operation, load, duration, and environment are comparable. Identify missing or contradictory information.
Select the applicable criteria and parameters from those conditions. A changed pilot needs criteria and evidence that apply to that pilot.

Producing and interpreting evidence

Use the measurement tool as described in the tool instructions to validate the inputs, calculate metrics, and compare them with the selected limits. Check its diagnostics and the identity of the measurements used.
Evaluate each criterion using the calculations and confirmed measurement conditions. Report a justified positive or negative assessment and its scope. If evidence is insufficient, report the gap and its effect; the affected Outcome remains unconfirmed.

Inputs

Baseline and candidate request measurements and their measurement context.

Controls

The applicable pilot criteria in pilot conditions govern the assessment. For this Process Description, apply the Process Framework.

Constraints

This assessment concerns the specified pilot. Production suitability requires evidence for production conditions. Deployment and collection of new measurements are outside this example's scope. The supplied measurements are synthetic teaching data, not evidence about a real service.

Enablers

An agent able to inspect the context, use a command tool, and interpret results; a local Python 3.11 or later environment; and the bundled measurement script. See tool instructions for its interface and limits.

Resources

This file is the source description for the Japanese translation. The example guide explains its supporting configuration and evaluation cases.

---name: assess-service-changedescription: Assess whether a service change meets the criteria for a specified pilot using baseline and candidate request measurements. Use when measurement comparability, responsiveness, reliability, and the limits of a pilot decision need to be established.---# Service Change Assessment## PurposeSupport a justified decision about a service change's suitability for the specified pilot conditions.## Outcomes- A judgment against each applicable pilot criterion is supported by comparable measurements and traceable calculations.- The scope and limits of the judgment, including their effects on the pilot decision, are explicit.## Activities & TasksThe following Tasks are required for this assessment. Their dependencies follow the evidence needed for each judgment.### Establishing the assessment basis1. Identify the baseline and candidate measurements and confirm the source and applicability of the [pilot conditions](references/pilot-context.md). Check that the service operation, load, duration, and environment are comparable. Identify missing or contradictory information.2. Select the applicable criteria and parameters from those conditions. A changed pilot needs criteria and evidence that apply to that pilot.### Producing and interpreting evidence1. Use the [measurement tool](scripts/compare_measurements.py) as described in the [tool instructions](references/tool-use.md) to validate the inputs, calculate metrics, and compare them with the selected limits. Check its diagnostics and the identity of the measurements used.2. Evaluate each criterion using the calculations and confirmed measurement conditions. Report a justified positive or negative assessment and its scope. If evidence is insufficient, report the gap and its effect; the affected Outcome remains unconfirmed.## InputsBaseline and candidate request measurements and their measurement context.## ControlsThe applicable pilot criteria in [pilot conditions](references/pilot-context.md) govern the assessment. For this Process Description, apply the [Process Framework](../../skills/design-process-description/references/process-framework.md).## ConstraintsThis assessment concerns the specified pilot. Production suitability requires evidence for production conditions. Deployment and collection of new measurements are outside this example's scope. The supplied measurements are synthetic teaching data, not evidence about a real service.## EnablersAn agent able to inspect the context, use a command tool, and interpret results; a local Python 3.11 or later environment; and the bundled measurement script. See [tool instructions](references/tool-use.md) for its interface and limits.## ResourcesThis file is the source description for the [Japanese translation](references/locales/ja/SKILL.md). The [example guide](../README.md) explains its supporting configuration and evaluation cases.

Frequently asked questions