outlinedriven/odin-claude-plugin/pr-impact-quiz

Claude Code and agent skill by outlinedriven/odin-claude-plugin

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use when the user invokes this skill to generate targeted questions proving the author understands the change''s codebase effect. Not for reviewing the change: use review.

Install

npx vskill@latest install outlinedriven/odin-claude-plugin/pr-impact-quiz

SKILL.md

PR impact quiz

Contract

FieldBound contract
TriggerUser wants a small set of impact questions proving the author understands how the change affects the existing codebase.
AuthorityRead-only. No file, VCS, credential, paid, published, deployed, or remote mutation.
Side effectChat output of three impact questions.
DoneThree impact questions are generated for the author to answer.

Inputs

The skill requires:

  • PR description: The authored description of the change, including motivation, scope, and expected behavior. Required.
  • Diff or change summary: The diff or a structured summary of what changed. Required.
  • Codebase context: The language, primary modules, and key patterns in the affected area. Required.

Procedure

  1. Read the PR description and diff or change summary. Done when: the description and diff are read.
  2. Identify the primary modules, interfaces, and data flows the change touches. Done when: the touched modules, interfaces, and data flows are identified.
  3. Identify possible effects on callers, downstream consumers, or shared state. Done when: possible effects on callers, consumers, and shared state are identified.
  4. Write three impact questions that require the author to confirm how the change affects the existing codebase. Each question must target a specific area of the codebase (not a generic concern), require a concrete answer (not a yes/no or "I checked"), and probe a different impact axis (call-site behavior, data invariants, or backward compatibility). Done when: three concrete, non-generic questions probing distinct impact axes are written.
  5. Present the three questions in the chat output. Done when: the three questions are presented in chat.

Failure and recovery

Failure classConditionResult
Missing inputPR description or diff is absent or emptyState what is required and do not generate questions.
Empty diffDiff contains no changed linesState that no changes are present and do not generate questions.
Non-convergedQuestions are generic, redundant, or require only yes/no answersStop; do not present. The done predicate does not hold.

No rollback is required. No partial result is returned when the done predicate does not hold.

Output

Three concrete, non-generic impact questions in chat, each addressing a distinct area of potential effect on the existing codebase.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/outlinedriven/odin-claude-plugin/pr-impact-quiz/badge)](https://verified-skill.com/skills/outlinedriven/odin-claude-plugin/pr-impact-quiz)

Something wrong with this skill or its page? Tell us.