Dependency Changes logo

Dependency Changes

Community
UnpaidAttention
dependency-changes

Add, upgrade, or migrate third-party dependencies safely — read the changelog for the exact version jump, isolate the change, run full verification, and keep rollback ready. Trigger this when the task involves bumping a package version, adding a new dependency, replacing one library with another, resolving a dependency vulnerability, or a lockfile update. Do NOT trigger for using an already-installed dependency in application code (that's normal implementation), or for deciding WHETHER a new dependency is warranted (use architecture-decisions' dependency sub-decision) — this skill is about executing the change without breakage.

Overview

PublisherUnpaidAttention
Repositoryfable5-methodology
Skill namedependency-changes
Stars
94
Forks
21
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by UnpaidAttention on GitHub. Read the source before you install it.

Installation

Install the Dependency Changes AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/UnpaidAttention/fable5-methodology/tree/main/skills/dependency-changes
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/UnpaidAttention/fable5-methodology.git /tmp/fable5-methodology
mkdir -p .claude/skills
cp -r /tmp/fable5-methodology/skills/dependency-changes .claude/skills/dependency-changes
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dependency Changes in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Dependency Changes on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Dependency Changes is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Dependency Changes

A dependency change is a change to code you didn't write and didn't review, arriving with its own bugs and behavior shifts. Treat every bump as a code change requiring verification, never as routine housekeeping.

Step 1: Know exactly what version moves where

  1. Read the lockfile for the CURRENT installed version — not the manifest range, the actual resolved version. That's your "from".
  2. Determine the "to" and classify the jump by semver: patch (x.y.Z), minor (x.Y.z), or major (X.y.z). Major jumps carry breaking changes by definition — budget accordingly.
  3. Note transitive impact: does this bump drag peer/transitive dependencies with it? npm ls <pkg> / cargo tree -i / pip show reveals who else is affected.

Step 2: Read the changelog for the SPECIFIC range

  1. Read the CHANGELOG / release notes for every version between from and to — not just the target. Bugs and breaking changes accumulate across the intermediate releases you're skipping.
  2. For a major jump, find the migration guide. Search the notes for "BREAKING", "removed", "deprecated", "renamed". List each breaking item that touches an API your code actually uses (grep your code for the symbols).
  3. This is version-sensitive external knowledge — do not rely on training memory of the library's API (see the research-and-verification skill). Read the notes for the real versions, fetched this session.

Step 3: Isolate the change

  1. One dependency change per commit/branch. Never bundle a version bump with feature work — when something breaks, you must know whether it was the bump or your code, and a mixed diff destroys that signal.
  2. If bumping several dependencies, do them one at a time with a full verification between each. A batch bump that fails gives you N suspects; sequential bumps give you one.
  3. Record the pre-change lockfile state (it's your rollback target — commit it or copy it).

Step 4: Apply and adapt

  1. Update the manifest, regenerate the lockfile with the project's tool (npm install, cargo update -p, uv lock / pip-compile) — never hand-edit a lockfile.
  2. Address each breaking item found in Step 2: update call sites for renamed/removed APIs, migrate deprecated usage. Grep to find every site; don't fix only the ones you remember.
  3. If the new version needs a config or peer-dependency change, do it in the same commit.

Step 5: Full verification (broader than usual)

A dependency touches code paths your unit tests may not cover directly. Escalate breadth:

  1. Reinstall from the lockfile clean (rm -rf node_modules && npm ci, fresh venv) — confirm it resolves and installs reproducibly, not just on your incremental state.
  2. Build + full test suite + lint + type-check. Type errors after a bump often ARE the breaking changes surfacing — read them, don't suppress them.
  3. Run the app / a smoke path — some breakages (behavioral, not type-level) only appear at runtime.
  4. Re-run the security audit (npm audit etc.) — confirm a security-motivated bump actually cleared the advisory, and didn't introduce a new one.

Step 6: Rollback readiness

If verification fails and the fix isn't quick: revert to the recorded lockfile state (Step 3), confirm green is restored, and report — "bump X 2.x→3.x blocked: it removes Y which the auth module depends on; needs migrating Y→Z first (est. N sites). Staying on 2.x meanwhile." A clean revert plus a clear blocker report beats a half-migrated broken tree.

Worked example

Task: "Upgrade axios to fix the CVE."

  1. Lockfile: current 0.27.2. Target: latest 1.x clearing the advisory → 1.7.x. Major jump.
  2. Changelog 0.27→1.0: BREAKING — default export/interceptor changes, axios.get error shape changed. Grep code: 14 call sites, 2 use the changed error shape.
  3. Isolated branch chore/axios-1.x; lockfile copied as rollback target.
  4. npm install axios@^1.7; update the 2 error-handling sites; grep confirms the other 12 are compatible.
  5. npm ci clean → build → full suite → RED: one test asserted the old error.response path; it's testing real behavior that changed → update the assertion (legitimate — the contract changed), NOT silenced. Green. Smoke: live request works. npm audit → advisory cleared, none introduced.
  6. Commit alone: chore: upgrade axios 0.27→1.7 (fixes CVE-XXXX; migrate error handling).

Done when

The exact version range's changelog was read and every breaking item touching your code addressed; the change is isolated to its own commit; a clean reinstall + full build/test/lint/ smoke passes; a security-motivated bump is confirmed to clear the advisory; and the rollback target is recorded so a failed bump can be cleanly reverted with a blocker report.

Frequently asked questions

What does the Dependency Changes AI skill do?

Add, upgrade, or migrate third-party dependencies safely — read the changelog for the exact version jump, isolate the change, run full verification, and keep rollback ready. Trigger this when the task involves bumping a package version, adding a new dependency, replacing one library with another, resolving a dependency vulnerability, or a lockfile update. Do NOT trigger for using an already-installed dependency in application code (that's normal implementation), or for deciding WHETHER a new dependency is warranted (use architecture-decisions' dependency sub-decision) — this skill is about...

Why use Dependency Changes on TypingMind?

Because you install it once and use it with any model. Dependency Changes is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Dependency Changes in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/UnpaidAttention/fable5-methodology/tree/main/skills/dependency-changes. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Dependency Changes?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Dependency Changes?

As many as you like. As long as a model supports skills, you can use Dependency Changes with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Dependency Changes AI skill free?

It is published on GitHub by UnpaidAttention. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇