Deps Update logo

Deps Update

Community
oliver-kriska
deps-update

Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (/phx:investigate).

Overview

Publisheroliver-kriska
Repositoryclaude-elixir-phoenix
Skill namedeps-update
Stars
555
Forks
40
Bundled files
4
LicenseMIT
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.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by oliver-kriska on GitHub. Read the source before you install it.

Installation

Install the Deps Update 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.
  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/oliver-kriska/claude-elixir-phoenix.git /tmp/claude-elixir-phoenix
mkdir -p .claude/skills
cp -r /tmp/claude-elixir-phoenix/plugins/elixir-phoenix/skills/deps-update .claude/skills/deps-update
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Deps Update 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 Deps Update 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 Deps Update 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 Update (Freshness)

Inventory → update → fix breaks → grouped PRs. This is the only MUTATING deps skill: it edits mix.exs, mix.lock, and source. Security scanning stays in /phx:deps-audit; the vet ledger stays in /phx:deps-vet.

Usage

/phx:deps-update                       # inventory + interactive scope pick
/phx:deps-update --scope patch         # bundle all patch bumps, one PR
/phx:deps-update --pkg phoenix_live_view   # one package (+ coupled group)
/phx:deps-update --dry-run             # inventory only, no changes

Iron Laws

  1. NEVER cross a major version without an explicit mix.exs editmix deps.update stays within requirements. Edit the constraint first; add override: true only when mix hex.outdated <pkg> shows a transitive consumer blocking. One major per PR
  2. ALWAYS snapshot the changelog delta BEFORE updating — capture deps/<pkg>/CHANGELOG.md, then delta via mix hex.package diff. Never update blind
  3. NEVER claim an update is safe without verification — run /phx:verify (compile --warnings-as-errors + test). "Compiles" ≠ "works"
  4. ALWAYS move coupled packages together — Phoenix core, Ecto, Ash, Oban, telemetry families update in the SAME step/commit (see ${CLAUDE_SKILL_DIR}/references/coupled-groups.md)
  5. NEVER commit a partial bumpmix.lock + mix.exs edits + (for Phoenix-family) assets/package-lock.json in ONE commit
  6. HAND OFF security to /phx:deps-audit — run it on the lock diff before any PR; don't reimplement audit rules
  7. hex.outdated exit 1 is normal — it means "deps are outdated", not failure. Capture with || true

Workflow

Phase 0: Discover

Read mix.exs: deps list, umbrella (apps_path:), git/path deps, private orgs (organization:/repo: in tuples), Phoenix/Ash presence. Create scratch dir .claude/deps-update/{YYYY-MM-DD}/.

Phase 1: Inventory

mix hex.outdated --all || true — parse the text table (no JSON exists; see ${CLAUDE_SKILL_DIR}/references/update-mechanics.md). Classify each row patch/minor/major by semver delta; Update not possible = blocked major (mix.exs constraint). Write inventory.md to scratch. Render grouped table: Patch / Minor / Major / Blocked / Git-deps (manual). --dry-run stops here.

Phase 2: Scope (AskUserQuestion)

Present groups with counts and risk. Default recommendation: "Patches (N) — low risk, bundle into one PR". --scope/--pkg flags skip the prompt. When ≥2 members of a coupled group are outdated, force them into one step even under a narrower scope.

Phase 3: Per-Package Update Loop

For each selected package, in coupled-group order:

  1. Snapshot deps/<pkg>/CHANGELOG.mdscratch/before/
  2. Update — patch/minor: mix deps.update <pkg> [coupled...]; major: edit mix.exs constraint (+ override: true if needed), then mix deps.update <pkg>
  3. git diff mix.lock → the REAL {pkg, old, new} set (hex.outdated says what could change; the lock diff says what did)
  4. Changelog delta: mix hex.package diff <pkg> <old>..<new> — keep the CHANGELOG hunk. Empty → gh api repos/{o}/{r}/releases fallback → compare-URL note (see ${CLAUDE_SKILL_DIR}/references/changelog-sources.md)
  5. Write scratch/{pkg}-{old}-{new}.md
  6. Phoenix-family in the diff + assets/package.json exists → npm install --prefix assets, stage assets/package-lock.json with the same commit

Phase 4: Verify

Run /phx:verify. On failure → Phase 5; else Phase 6.

Phase 5: Breaking-Change Fixes

Read the changelog deltas for "breaking"/"removed"/"deprecated" + the compile/test errors. Fix source (apply the sibling-file check). Re-verify.

Phase 6: Security Handoff

Run /phx:deps-audit on the working mix.lock diff (its Mode B default). BLOCK findings → surface and offer /phx:deps-vet <pkg> <ver> for accepted risks. Never skip this before a PR.

Phase 7: Group, Commit, PR

Apply the splitting strategy (${CLAUDE_SKILL_DIR}/references/pr-strategy.md): patches bundled, minors by area, majors solo, coupled groups always together. PR bodies cite the changelog excerpt, the https://diff.hex.pm/diff/<pkg>/<old>..<new> link, verification result, and the deps-audit risk band. Stage lock + mix.exs + package-lock together.

Integration

text
/phx:deps-update (mutating) → /phx:deps-audit (security, Mode B)
        │                              │ BLOCK → /phx:deps-vet (ledger)
        └→ /phx:verify (gate) → grouped commits / PRs

References

  • ${CLAUDE_SKILL_DIR}/references/update-mechanics.md — hex.outdated parsing, update vs unlock+get, majors, lock-diff
  • ${CLAUDE_SKILL_DIR}/references/changelog-sources.md — hex.package diff, gh fallbacks, private orgs
  • ${CLAUDE_SKILL_DIR}/references/coupled-groups.md — must-move-together groups + edge cases
  • ${CLAUDE_SKILL_DIR}/references/pr-strategy.md — grouping rules, area buckets, PR template, scratch layout

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Deps Update AI skill do?

Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (/phx:investigate).

Why use Deps Update on TypingMind?

Because you install it once and use it with any model. Deps Update 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 Deps Update in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/oliver-kriska/claude-elixir-phoenix/tree/main/plugins/elixir-phoenix/skills/deps-update. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Deps Update?

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 Deps Update?

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

Is the Deps Update AI skill free?

Yes. It is published on GitHub by oliver-kriska under the MIT license. 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 👇