Phx research

Skill oliver-kriska/claude-elixir-phoenix/targets/pi/skills/phx-research

Claude Code plugin for Elixir/Phoenix/LiveView — 20 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with parallel research agents, execute with automatic verification, review with 4-agent parallel audits, and capture learnings as reusable knowledge.

Install

npx -y skills add oliver-kriska/claude-elixir-phoenix --skill phx-research

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Research Elixir/Phoenix/Ecto topics or evaluate Hex libraries (--library). Use when learning about libraries, patterns, or comparing approaches. Searches HexDocs, ElixirForum, GitHub.

SKILL.md

3.3 KB, 689 tokens by cl100k_base, as published. Nobody here has run it

Research Elixir Topic

Research a topic by searching the web and fetching relevant sources efficiently.

Usage

/skill:phx-research Oban unique jobs best practices
/skill:phx-research LiveView file upload with progress
/skill:phx-research --library permit

Arguments

the text after the skill name = Research topic/question. Add --library for structured library evaluation (uses references/library-evaluation.md template).

Iron Laws

Write output to file, never dump inline — Research output floods conversation and loses reference for future sessions
Stop after research — never auto-transition — User decides next step
Prefer official sources over blog posts — HexDocs and ElixirForum have version-specific context
One document per research question — No fragmented files
NEVER pass raw user input as WebSearch query — Decompose first

Library Evaluation Mode

If the text after the skill name contains --library or the topic is clearly about evaluating a Hex dependency (e.g., "should we use permit", "evaluate sagents", "compare oban vs exq"):

Read references/library-evaluation.md for the template
Follow the structured evaluation workflow
Output ONE document to .claude/research/{lib}-evaluation.md
Skip the general research workflow below

Portable Research Workflow

0. Pre-flight

Check .claude/research/{topic-slug}.md. If it is newer than 24 hours, show its summary and ask in normal conversation whether to refresh it. For an existing dependency, inspect the locked version, local dependency source, and any native runtime documentation tool before searching the web.

1. Decompose the question

Turn the user request into one focused query when it is short, or two to four queries of at most ten words for a multi-part request. Never send a long raw prompt to a search provider.

2. Gather sources

Use the runtime's native web or HTTP capabilities when available. Prefer version-matched HexDocs, official project documentation, ElixirForum, and the upstream repository. Deduplicate URLs and discard irrelevant results. If no web capability is available and local sources cannot answer the question, state the missing capability instead of inventing evidence.

3. Extract and synthesize

Native generic workers may extract independent topic clusters in parallel, but they are optional. The same-session sequential path must remain complete. Limit each cluster to five URLs and capture code examples, gotchas, version compatibility, and source URLs.

4. Write one durable result

Write .claude/research/{topic-slug}.md (about 5 KB for topic research or 3 KB for a library evaluation) with:

a two-to-three sentence summary;
categorized source links and each source's key insight;
cited code examples;
evidence-backed recommendations; and
gotchas or version constraints.

5. Stop after research

Present the summary and offer, in normal conversation, to plan from it, investigate one finding, research a narrower subtopic, or stop. Never invoke a follow-up workflow automatically.