All skills
oaustegard avatar

/assessing-impact

@4b31e7d

Pre-change blast-radius report for a symbol or file. Walks tree-sitting references, augments with a plain-text scan over non-parsed files (configs, plain docs), and clusters affected sites by feature (`_FEATURES.md`) or top-level package. Use when about to refactor, rename, or delete something in a repo you don't own — "what breaks if I change `validateUser`", "who calls this", "is this safe to remove", "where is this used", "blast radius", "impact analysis". This is the CONVERGENT pre-change risk skill — for "what is this repo?" use exploring-codebases; for "where is X?" use searching-codebases.

Use this Skill: https://skilld.dev/gh/oaustegard/claude-skills/assessing-impact

This session only. Nothing lands on disk.

CHANGELOG.md

≈102 tokens on demand. Your agent reads this file only when SKILL.md points to it.

assessing-impact - Changelog

All notable changes to the assessing-impact skill are documented in this file. The format is based on Keep a Changelog.

[0.1.1] - 2026-04-26

Other

  • assessing-impact: add README, bump to 0.1.1 (#582)

[0.1.0] - 2026-04-26

Other

  • assessing-impact: new skill for pre-change blast-radius reports (closes #578) (#581)

Source: SKILL.md on GitHub

1 warning9d3 checks · Risk MEDIUM
  • Gen Agent Trust Hub9d

    This skill analyzes codebase impact by walking AST trees and scanning text. It contains dynamic loading mechanisms to import its core engine from a peer skill and processes source code snippets that could potentially host indirect prompt injections.

  • Socket9d

    No alerts

  • Snyk9d

    Risk: LOW · No issues

Signed by skilld at 4b31e7d. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 months ago
metadata
{
  "version": "0.1.1"
}

README badge

README badge for oaustegard/claude-skills/assessing-impact