Is the Plugin Dev Workflow skill free?

Yes. The skill itself is free from oliver-kriska/claude-elixir-phoenix. SkillProof publishes the install command and an independent test verdict at no cost.

Does Plugin Dev Workflow work with Claude Code?

We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Cloned the repo and executed the skill's core commands. Representative task: score a SKILL.md. BASELINE (naive `python3 lab/eval/scorer.py plugins/elixir-phoenix/skills/verify/SKILL.md`) crashed with ModuleNotFoundError: No module named 'lab'. SKILL-followed (`python3 -m lab.eval.scorer `, as the skill mandates) succeeded and returned composite 1.0 with full dimension breakdown — the -m instruction prevents a real failure. Verified Makefile/scorer.py/CLAUDE.md exist, make targets (help/eval/test/eval-all/ci) present, and the '51 skills + 26 agents' claim matches exactly. Minor oversell: References lists lab/findings/interesting.jsonl, which does not exist in the repo. No security smells.

What is the Plugin Dev Workflow SkillProof Score?

8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.

How do I install Plugin Dev Workflow?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Plugin Dev Workflow with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Plugin Dev Workflow

Contributor workflow for the Elixir/Phoenix plugin repo: eval, lint, test before commit

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

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.4/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 0e94133

Cloned the repo and executed the skill's core commands. Representative task: score a SKILL.md. BASELINE (naive `python3 lab/eval/scorer.py plugins/elixir-phoenix/skills/verify/SKILL.md`) crashed with ModuleNotFoundError: No module named 'lab'. SKILL-followed (`python3 -m lab.eval.scorer <same path>`, as the skill mandates) succeeded and returned composite 1.0 with full dimension breakdown — the -m instruction prevents a real failure. Verified Makefile/scorer.py/CLAUDE.md exist, make targets (help/eval/test/eval-all/ci) present, and the '51 skills + 26 agents' claim matches exactly. Minor oversell: References lists lab/findings/interesting.jsonl, which does not exist in the repo. No security smells.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 4/5

What Plugin Dev Workflow does

A repo-internal contributor workflow guide for the oliver-kriska/claude-elixir-phoenix plugin. It tells you which make targets and scorer commands to run (make eval, make test, python3 -m lab.eval.scorer) when editing that repo's skills, agents, hooks, or eval framework, and enforces the -m module invocation and pre-commit checklist. Triggers when modifying files under plugins/elixir-phoenix/, lab/eval/, or lab/autoresearch/ inside a clone of that repo.

How to install Plugin Dev Workflow

git clone --depth 1 https://github.com/oliver-kriska/claude-elixir-phoenix.git /tmp/plugin-dev-workflow-src
mkdir -p ~/.claude/skills
cp -R /tmp/plugin-dev-workflow-src/.claude/skills/plugin-dev-workflow ~/.claude/skills/plugin-dev-workflow
# Repo-internal contributor skill: only useful when working INSIDE a clone of
# oliver-kriska/claude-elixir-phoenix. Its commands (make eval, make test,
# python3 -m lab.eval.scorer <path>) require that repo's Makefile + Python eval
# framework as the current working directory. No extra pip deps needed to run the scorer.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Plugin Dev Workflow

/plugin-dev-workflow Contributor workflow for the Elixir/Phoenix plugin repo: eval, lint, test before commit

It also activates on plain-language prompts like these:

Add a new skill to this plugin repo
Modify this agent and make sure eval still passes
Update a hook in plugins/elixir-phoenix

Frequently asked questions

Is the Plugin Dev Workflow skill free?: Yes. The skill itself is free from oliver-kriska/claude-elixir-phoenix. SkillProof publishes the install command and an independent test verdict at no cost.
Does Plugin Dev Workflow work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Cloned the repo and executed the skill's core commands. Representative task: score a SKILL.md. BASELINE (naive `python3 lab/eval/scorer.py plugins/elixir-phoenix/skills/verify/SKILL.md`) crashed with ModuleNotFoundError: No module named 'lab'. SKILL-followed (`python3 -m lab.eval.scorer <same path>`, as the skill mandates) succeeded and returned composite 1.0 with full dimension breakdown — the -m instruction prevents a real failure. Verified Makefile/scorer.py/CLAUDE.md exist, make targets (help/eval/test/eval-all/ci) present, and the '51 skills + 26 agents' claim matches exactly. Minor oversell: References lists lab/findings/interesting.jsonl, which does not exist in the repo. No security smells.
What is the Plugin Dev Workflow SkillProof Score?: 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install Plugin Dev Workflow?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Plugin Dev Workflow with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.