agentleFS
motao123motao123/dev-workflow-kit/change-impact-analysis/SKILL.md

change-impact-analysis

Skill1 starsChanged 5 months agoMITView on GitHub

Use when the main question is what a proposed or partial change will affect across code, interfaces, configs, tests, docs, consumers, and rollout surfaces. This skill maps blast radius before implementation, merge, or release.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the key uncertainty is breadth of impact rather than how to write the code.

    line 9
  2. Distinctive:

    Use this skill when:

    line 13
  3. Distinctive:

    Do not use this skill for root-cause debugging or for deciding the internal structure of a refactor.

    line 20
  4. Very specific:

    use planning if scope needs to be re-sliced

    line 44
  5. Very specific:

    use ship-readiness or release-rollout-strategy when impact affects release shape

    line 46

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Change Impact Analysis

Use this skill when the key uncertainty is breadth of impact rather than how to write the code.

Trigger Conditions

Use this skill when:

  • a change may affect multiple modules, consumers, or environments
  • the team needs to know what else must be updated before implementation
  • API, schema, config, docs, tests, or rollout surfaces may be touched indirectly
  • the user asks what could break if a change goes in
  • release risk depends on understanding downstream effects first

Do not use this skill for root-cause debugging or for deciding the internal structure of a refactor.

Workflow

  1. Identify the proposed or in-progress change.
  2. Map directly touched files, modules, contracts, configs, and consumers.
  3. Identify likely indirect effects and regression zones.
  4. Separate must-check surfaces from lower-risk surfaces.
  5. Recommend verification focus and rollout cautions.
  6. Hand off to the next workflow step.

Output

For non-trivial work, provide:

  • impacted surfaces
  • direct vs indirect consequences
  • likely regression zones
  • verification focus areas
  • rollout or migration cautions
  • recommended next action

Coordination

After impact analysis:

  • use planning if scope needs to be re-sliced
  • move into the active implementation workflow for execution
  • use ship-readiness or release-rollout-strategy when impact affects release shape

Invocation Examples

  • "Use change-impact-analysis to show what else this schema change could affect."
  • "Use change-impact-analysis before implementation so we know which tests, docs, and clients are in scope."
  • "Use change-impact-analysis to identify the likely regression zones for this config change."

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.