New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Phx Review

by oliver-kriska in oliver-kriska/claude-elixir-phoenix

Review changed Elixir/Phoenix code read-only. An agent skill from oliver-kriska/claude-elixir-phoenix.

MITAuto-check passedAI & LLM Engineering

Install Phx Review

skills CLI
$ npx skills add oliver-kriska/claude-elixir-phoenix --skill phx-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install oliver-kriska/claude-elixir-phoenix phx-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/oliver-kriska/claude-elixir-phoenix.git skills-src && mkdir -p .claude/skills && cp -r skills-src/targets/pi/skills/phx-review .claude/skills/phx-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
phx-review
GitHub stars
565
Token cost
~1.1k tokens
SKILL.md length
500 words
Files
7 (incl. references)
Skills in repo
109
Repo updated
First seen
Licence
MIT

At a glance

Review changed Elixir/Phoenix code read-only. An agent skill from oliver-kriska/claude-elixir-phoenix.

  • Works in 5 steps: Establish Scope → Load Requirements → Review by Concern → …
  • Tasks that involve LLM observability
  • SKILL.md covers Usage, Iron Laws, Workflow and References
  • Calls git and gh

What it does

Phx Review is an agent skill from oliver-kriska/claude-elixir-phoenix. Review changed Elixir/Phoenix code read-only. Check requirements, cite evidence, deduplicate findings, and return a severity-based verdict.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `references/agent-spawning.md`, `references/blocker-handling.md` and `references/conventions.md`).

It sits in AI & LLM Engineering, covering LLM observability. It works with Elixir. The repository describes itself as: Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with parallel research agents, execute… The licence is MIT.

When your agent uses it

  • Tasks that involve LLM observability

Example prompts

  • “/phx-review”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Establish Scope
  2. Load Requirements
  3. Review by Concern
  4. Verify Findings
  5. Report a Verdict

What it can do on your machine

Read from SKILL.md and the folder at commit 9767a82. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git and gh, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Phx Review loads about 1.1k tokens when it runs, and up to ~4.4k if it reads all its reference files. Until then it costs about 38 tokens; SKILL.md has 500 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from oliver-kriska/claude-elixir-phoenix at commit 9767a82, republished under its MIT licence (© oliver-kriska). 500 words, ~1,055 tokens.

Download SKILL.mdSave it as .claude/skills/phx-review/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
phx-review
description
Review changed Elixir/Phoenix code read-only. Check requirements, cite evidence, deduplicate findings, and return a severity-based verdict.

Review Elixir/Phoenix Code

Perform an evidence-based, read-only review of changed code. Find and explain issues; do not edit files, create tasks, or fix findings.

Usage

text
/skill:phx-review
/skill:phx-review test
/skill:phx-review security
/skill:phx-review .claude/plans/auth/plan.md
/skill:phx-review --no-requirements

Treat the text after the skill name as a focus area, issue identifier, or path to a plan/specification.

Iron Laws

  1. Review is read-only — inspect and report; never modify the worktree.
  2. Scope to changed code — distinguish new defects from pre-existing issues.
  3. Every finding needs evidence — cite a path and line, explain impact, and describe the concrete failure mode.
  4. Check requirements when available — unmet requirements affect the verdict.
  5. Deduplicate and prioritize — one root cause is one finding, with the highest justified severity.
  6. Do not require custom agents, hooks, MCP, or unavailable task APIs — use optional runtime capabilities only when present.

Workflow

1. Establish Scope

Determine the merge base or user-specified base, then inspect:

bash
git status --short
git diff --name-only <base>...HEAD
git diff --stat <base>...HEAD
git diff <base>...HEAD -- <changed-files>

Do not assume HEAD~5 is the correct base. Include uncommitted changes when the user asks to review the current worktree. Record the chosen scope in the result.

2. Load Requirements

Unless --no-requirements is set, look for an explicit plan/spec path, current conversation requirements, a branch or commit issue identifier, or the latest relevant plan. Use available integrations or gh issue view when configured; otherwise mark requirements NOT AVAILABLE and continue.

Read references/requirements-detection.md for detection order. Never let a missing Linear, GitHub, hook, or MCP integration block code review.

3. Review by Concern

Select only concerns relevant to the diff:

  • Elixir/Phoenix correctness and idioms;
  • Ecto queries, changesets, transactions, migrations, and N+1 risks;
  • LiveView lifecycle, reconnect, forms, streams, and assigns;
  • authentication, authorization, secrets, and input handling;
  • Oban idempotency, retries, uniqueness, and transaction boundaries;
  • tests, regressions, and verification gaps;
  • deployment/runtime configuration when those files changed.

Native Pi subagents may run independent read-only concern tracks in parallel. Use generic subagents with the complete diff scope and return findings to this session; do not depend on separately installed named agents. If subagents are unavailable or unnecessary, run every selected concern sequentially here. A sequential review is fully valid.

Show full SKILL.md (165 more words)Show less
4. Verify Findings

For each candidate:

  1. Confirm it is in changed code or label it PRE-EXISTING.
  2. Trace the actual runtime or data-flow consequence.
  3. Check nearby tests and requirements.
  4. Remove style-only noise and speculative concerns.
  5. Merge duplicates under the clearest root cause.

Run targeted read-only verification when it materially changes confidence. Do not alter files or suppress failures. If a check cannot run, report that clearly.

5. Report a Verdict

Return one verdict:

  • PASS
  • PASS WITH WARNINGS
  • REQUIRES CHANGES
  • BLOCKED

List findings in descending severity as BLOCKER, WARNING, or SUGGESTION. Each finding must include path:line, evidence, impact, and the smallest appropriate correction. Add requirements coverage before findings; any UNMET requirement requires REQUIRES CHANGES.

If there are no findings, say so explicitly and list residual risks or checks not run. Stop after presenting the review. Suggest /skill:phx-triage, /skill:phx-plan, or /skill:phx-compound as optional next steps without invoking them automatically.

References

  • references/requirements-detection.md — requirements source and coverage rules
  • references/agent-spawning.md — Pi concern selection and optional parallelism

© oliver-kriska, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (references) in targets/pi/skills/phx-review of oliver-kriska/claude-elixir-phoenix.

  • SKILL.md
  • references/agent-spawning.md
  • references/blocker-handling.md
  • references/conventions.md
  • references/example-review.md
  • references/requirements-detection.md
  • references/review-template.md

Open the folder on GitHubat commit 9767a82

Compare with similar skills

Phx Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Phx Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Phx Review this skilloliver-kriska/claude-elixir-phoenix565—~1.1kAutomated safety check: PassMIT
Elixir Architectmaxim-ist/elixir-architect145—~7.6kAutomated safety check: PassMIT
Phoenix Frameworkpodlove/radiator136—~562Automated safety check: PassMIT
Elixir Expertpass-agent/loomkin1811 repos~796Automated safety check: PassMIT
Usage Rulesbradleygolden/claude-marketplace-elixir176—~4.9kAutomated safety check: NotesMIT
Elixir Prodavila7/claude-code-templates33k8 repos~486Automated safety check: PassMIT

Similar skills

  • Elixir Architect

    maxim-ist/elixir-architect

    A skill your agent uses when designing or architecting Elixir/Phoenix applications, creating comprehensive project documentation, planning OTP supervision trees, defining domain models with Ash…

    145 GitHub stars~7.6k tokensUpdated 10 mo ago
    AI & LLM EngineeringAuto-check passed

  • Phoenix Framework

    podlove/radiator

    Use this skill working with Phoenix Framework. An agent skill from podlove/radiator.

    136 GitHub stars~562 tokensUpdated 16 days ago
    AI & LLM EngineeringAuto-check passed

  • Elixir Expert

    pass-agent/loomkin

    Expert in Elixir, Phoenix Framework, and OTP. An agent skill from pass-agent/loomkin.

    181 GitHub starsUsed in 1 repo~796 tokens
    AI & LLM EngineeringAuto-check passed

  • Usage Rules

    bradleygolden/claude-marketplace-elixir

    Search for package-specific usage rules and best practices from Elixir packages.

    176 GitHub stars~4.9k tokensUpdated 9 mo ago
    AI & LLM EngineeringAuto-check: notes

  • Elixir Pro

    davila7/claude-code-templates

    Write idiomatic Elixir code with OTP patterns, supervision trees, and Phoenix LiveView.

    33k GitHub starsUsed in 8 repos~486 tokens
    AI & LLM EngineeringAuto-check passed

  • Phoenix

    ericrisco/rsc-harness

    A skill your agent uses when building an Elixir web app with Phoenix — contexts, Ecto schemas, changesets and migrations, LiveView, channels and PubSub, the generators, and the boundary between…

    180 GitHub stars~2.9k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check: notes

More from oliver-kriska/claude-elixir-phoenix

All 109 skills in this repo

  • Codex Ab

    oliver-kriska/claude-elixir-phoenix

    Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict.

    565 GitHub stars~977 tokensUpdated 5 days ago
    Auto-check passed

  • Audit

    oliver-kriska/claude-elixir-phoenix

    Project health audit and health check — architecture, performance, tests, dependencies, code quality.

    565 GitHub stars~2k tokensUpdated 5 days ago
    Auto-check passed

  • Compound Docs

    oliver-kriska/claude-elixir-phoenix

    Searchable Elixir/Phoenix/Ecto solution documentation system with; Use when consulting past solutions…

    565 GitHub stars~528 tokensUpdated 5 days ago
    Auto-check passed

  • Compound Docs

    oliver-kriska/claude-elixir-phoenix

    Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter.

    565 GitHub stars~547 tokensUpdated 5 days ago
    Auto-check passed

  • Deploy

    oliver-kriska/claude-elixir-phoenix

    Elixir/Phoenix deployment patterns — Dockerfile, fly.toml, runtime.exs, mix release, rel/ overlays.

    565 GitHub stars~1.1k tokensUpdated 5 days ago
    Auto-check passed

  • Deps Update

    oliver-kriska/claude-elixir-phoenix

    Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo).

    565 GitHub stars~1.4k tokensUpdated 5 days ago
    Auto-check passed

Works with

Categories

Questions about Phx Review

What does Phx Review do?

Review changed Elixir/Phoenix code read-only. An agent skill from oliver-kriska/claude-elixir-phoenix. Phx Review is an agent skill from oliver-kriska/claude-elixir-phoenix. Review changed Elixir/Phoenix code read-only.

When should I use Phx Review?

Phx Review fits situations like: tasks that involve LLM observability.

How do I install Phx Review in Claude Code?

Run `npx skills add oliver-kriska/claude-elixir-phoenix --skill phx-review -a claude-code`. Or copy the skill folder (targets/pi/skills/phx-review in oliver-kriska/claude-elixir-phoenix) into .claude/skills/phx-review in your project. Claude Code loads it when a task matches its description.

How do I install Phx Review in Codex?

Run `npx skills add oliver-kriska/claude-elixir-phoenix --skill phx-review -a codex`. Or copy the skill folder (targets/pi/skills/phx-review in oliver-kriska/claude-elixir-phoenix) into .agents/skills/phx-review in your project. Codex loads it when a task matches its description.

Can I use Phx Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add oliver-kriska/claude-elixir-phoenix --skill phx-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/phx-review, .gemini/skills/phx-review, .github/skills/phx-review and .opencode/skills/phx-review in your project.

What does Phx Review need to run?

Going by SKILL.md and its folder, Phx Review needs the command-line tools its instructions call (git and gh).

Does Phx Review access the network?

SKILL.md contains no URLs. Its commands use git and gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Phx Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Phx Review use?

Phx Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Phx Review use?

About 1.1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.4k tokens, read only when the agent opens those files.

What are the alternatives to Phx Review?

Skills that share tags, products or a category with Phx Review: Elixir Architect (maxim-ist/elixir-architect, 145 stars), Phoenix Framework (podlove/radiator, 136 stars), Elixir Expert (pass-agent/loomkin, 181 stars) and Usage Rules (bradleygolden/claude-marketplace-elixir, 176 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Phx Review?

oliver-kriska (a GitHub user) maintains it in oliver-kriska/claude-elixir-phoenix, which has 565 GitHub stars. The repository holds 109 skills in this directory. The repository was last updated on October 5, 2026.

Source: oliver-kriska/claude-elixir-phoenix on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.