Agent skill

agent-change-walkthrough

Generates a narrative walkthrough of AI-authored code changes. Use after implementation to explain what changed, why, and how it behaves.

View SKILL.md on GitHub Repository
Stars 1
Forks 0

Install this agent skill to your Project

npx add-skill https://github.com/iamladi/cautious-computing-machine--sdlc-plugin/tree/main/skills/agent-change-walkthrough

SKILL.md

Agent Change Walkthrough Skill

Purpose

Generate a single-story walkthrough of AI-authored code changes explaining implementation from trigger to final behavior.

Core Method

Follow six steps:

  1. Capture intent — Restate the change in plain language with scope and non-goals
  2. Build evidence — Collect git diffs using git status, git diff, git show
  3. Build story stack — Order steps dependency-first (contracts/types before usage, definitions before invocations)
  4. Write narrative — Each step: clear title, CHANGED/UNCHANGED marker, filename with line number, code snippet, prose explanation
  5. Integrate analysis — Add trade-offs, alternatives, performance notes, and risks inline at relevant steps
  6. Close out — Summarize what changed, why behavior differs, what to monitor

Key Principles

  • Show dependency order first, then runtime flow
  • No forward references (define before using)
  • Use mini-diff snippets for changes
  • Include sanitized example input/output for data-shape changes
  • Embed analysis naturally in prose, not rigid templates
  • Never include conversation process as walkthrough steps
  • No credentials, keys, or sensitive data in output

Output Structure

# Implementation Walkthrough
[Setup paragraph with intent + scope]

## Step 1 — [behavior description] [UNCHANGED CONTEXT | CHANGED]
Filename: `path/to/file.ext:line`
[code snippet]
[prose explanation]

## Step N — ...

## Final Outcome
[summary of changes and next validation steps]

Trace from runtime trigger to observable behavior as one coherent story.

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

iamladi/cautious-computing-machine--sdlc-plugin

tdd

TDD enforcement during implementation. Reads `tdd:` setting from CLAUDE.md. Modes - strict (human approval for escape), soft (warnings), off (disabled). Auto-invoked by /implement.

1 0
Explore
iamladi/cautious-computing-machine--sdlc-plugin

judgment-eval

Evaluates agent judgment quality through scenario-based testing in-conversation. Use when the user wants to test, validate, or stress-test an agent, skill, or command definition — e.g. "test this agent", "evaluate this skill", "does this prompt handle edge cases", "check this agent's judgment", or after writing or modifying any agent/skill/command .md file.

1 0
Explore
iamladi/cautious-computing-machine--sdlc-plugin

update-models

Re-resolve the model registry by querying OpenAI Codex cache, Google AI API, and Oracle CLI. Use when models feel stale or after a major model release.

1 0
Explore
iamladi/cautious-computing-machine--sdlc-plugin

gemini

Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Resolves the latest flagship model from the model registry.

1 0
Explore
iamladi/cautious-computing-machine--sdlc-plugin

finish-branch

1 0
Explore
iamladi/cautious-computing-machine--sdlc-plugin

interview

Interview me about anything in depth

1 0
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results