Intro

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha 492f17636999 · 18 Oct 2026Report an issue or request a re-scan

• Publisheroliver-kriska GitHub userOwner of the repository this skill is read from
• Source folderoliver-kriska/claude-elixir-phoenix/plugins/elixir-phoenix/skills/introThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdict492f17636999A new audit runs when the source changes
• Repository statusNot archivedLast push 2 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Walk through the Elixir/Phoenix plugin commands, workflow, and features in 6 interactive sections. Use when a new user wants to learn what the plugin offers or needs a refresher on available commands.

---
name: intro
description: Walk through the Elixir/Phoenix plugin commands, workflow, and features in 6 interactive sections. Use when a new user wants to learn what the plugin offers or needs a refresher on available commands.
effort: low
argument-hint: "[--section N]"
---

# Plugin Introduction Tutorial

Interactive walkthrough of the Elixir/Phoenix plugin in 6 sections (~5 min).

## Arguments

- `$ARGUMENTS` may contain `--section N` to jump to a specific section (1-6)
- No arguments = start from Section 1

## Execution Flow

1. Read `${CLAUDE_SKILL_DIR}/references/tutorial-content.md` for all section content
2. Parse `$ARGUMENTS` for `--section N` flag (1-6)
3. If `--section N` specified, jump directly to that section
4. Otherwise start from Section 1

### Section Presentation Loop

For each section:

1. Present the section content completely — every paragraph, table, and code block from the reference file
   — as **visible response text emitted BEFORE the `AskUserQuestion` call**; content composed only in thinking is invisible to the user
2. After presenting, use `AskUserQuestion` with options:
   - If sections remain: "Next: [next section title]", "Skip to Cheat Sheet", "Stop here"
   - If on final section (6): no question needed, end with closing message

### Section Titles

| N | Title |
|---|-------|
| 1 | Welcome |
| 2 | Core Workflow Commands |
| 3 | Knowledge & Safety Net |
| 4 | Hooks & Behavioral Rules |
| 5 | Init, Review & Gaps |
| 6 | Cheat Sheet & Next Steps |

## Iron Laws

1. **ONE section at a time** — never dump all content at once
2. **User controls pace** — always offer to stop between sections
3. **Clean formatting** — use tables and code blocks, not walls of text
4. **NEVER skip the user's questions** — tutorial is interactive, not a monologue; if the user asks a question mid-section, answer it before continuing

## Closing Message

After Section 6 (or when user stops):

```
You're all set! Try `/phx:plan` with your next feature to see the workflow in action.
Run `/phx:intro --section N` anytime to revisit a specific section.
```

## Notes

- This runs in main conversation context (not a subagent)
- Reference file is readable since skill runs in user's session
- Keep tone welcoming but concise — developers don't want fluff

Excerpt, first 2,290 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

1. 2026-10-18
   ✓SAFE B 89 / 100

   first audit · source 492f17636999

Questions about Intro

• github.com/oliver-kriska/claude-elixir-phoenix/tree/main/plugins — the audited source at commit 492f17636999 and every finding aboveObserved · 18 Oct 2026

Spotted something wrong? Report a correction · Methodology