media-setup

name	media-setup
description	Interactive wizard to configure platform connections, API keys, and dependencies for media-agent. Detects available tools, walks through setup for each platform, tests connections, and writes config files. Run this before any other media-agent skill.
allowed-tools	["Bash","Read","Write","Edit","AskUserQuestion","Grep","Glob"]

/media-setup — Platform Configuration Wizard

Configure your media-agent installation. This skill detects available tools, walks you through API key setup for each platform, tests connections, and writes the config files.

Prerequisites

Before starting, read the shared library files:

• Read lib/adapter-discovery.md for how adapters work
• Read lib/manifest-ops.md for manifest format

Step 1: Detect Environment

Check for required and optional tools:

echo "=== media-agent Setup ==="
echo ""

# Required
echo "Checking dependencies..."
which git >/dev/null 2>&1 && echo "  [OK] git" || echo "  [MISSING] git — required"
which python3 >/dev/null 2>&1 && echo "  [OK] python3" || echo "  [MISSING] python3 — required for YAML parsing"
which curl >/dev/null 2>&1 && echo "  [OK] curl" || echo "  [MISSING] curl — required for API calls"

# Optional
echo ""
echo "Optional tools:"
which convert >/dev/null 2>&1 && echo "  [OK] ImageMagick" || echo "  [MISSING] ImageMagick — needed for image resizing (brew install imagemagick)"
which gh >/dev/null 2>&1 && echo "  [OK] GitHub CLI" || echo "  [MISSING] GitHub CLI — optional, for GitHub Pages"

If python3 or curl is missing, stop and tell the user how to install them.

If ImageMagick is missing, warn the user but continue — it's only needed for /media-image.

Step 2: Discover Available Adapters

echo ""
echo "Available platform adapters:"
for adapter in adapters/*/; do
  name=$(basename "$adapter")
  display=$(python3 -c "import yaml; print(yaml.safe_load(open('${adapter}adapter.yaml'))['display_name'])" 2>/dev/null || echo "$name")
  auth_type=$(python3 -c "import yaml; print(yaml.safe_load(open('${adapter}adapter.yaml'))['auth_type'])" 2>/dev/null || echo "unknown")
  echo "  - $display ($auth_type)"
done

Step 3: Configure Each Platform

Use AskUserQuestion to ask which platforms the user wants to configure. Then for each selected platform:

GitHub Pages (auth_type: git_push)

Ask the user:

1. "What is the local path to your GitHub Pages repository?" (e.g., ~/myblog)
2. "Which branch do you publish from?" (default: main)
3. "What is your site URL?" (e.g., https://username.github.io)
4. "What directory are posts in?" (default: _posts)

Verify the repo exists:

[ -d "<repo_path>/.git" ] && echo "OK: Git repo found" || echo "ERROR: Not a git repo"

Dev.to (auth_type: api_key)

Ask the user for their Dev.to API key. They can get one at https://dev.to/settings/extensions.

Test the connection:

RESPONSE=$(curl -s -o /dev/null -w "%{http_code}" \
  -H "api-key: <API_KEY>" \
  "https://dev.to/api/users/me")
[ "$RESPONSE" = "200" ] && echo "OK: Dev.to connected" || echo "ERROR: Auth failed (HTTP $RESPONSE)"

Hashnode (auth_type: api_key)

Ask the user for:

1. Their Hashnode API key (from https://hashnode.com/settings/developer)
2. Their publication ID (from their blog dashboard URL)

Test the connection:

RESPONSE=$(curl -s -w "\n%{http_code}" \
  -X POST "https://gql.hashnode.com" \
  -H "Authorization: <API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{"query":"{ me { username } }"}')

Step 4: Configure Image Generation (Optional)

Ask if the user wants to set up image generation.

If yes, ask for their OpenAI API key (for DALL-E 3).

Test:

RESPONSE=$(curl -s -o /dev/null -w "%{http_code}" \
  -H "Authorization: Bearer <API_KEY>" \
  "https://api.openai.com/v1/models")
[ "$RESPONSE" = "200" ] && echo "OK: OpenAI connected" || echo "ERROR: Auth failed"

Step 5: Configure Writing Voice (Optional)

Ask the user if they want to set up their personal writing style.

Use AskUserQuestion: "Want to set up your writing voice? This helps the system match your personal style instead of sounding like AI."

• A) Yes, paste writing samples
• B) Yes, describe my style manually
• C) Skip for now

Option A: Writing samples

Ask the user to paste 2-3 paragraphs of their own writing (blog posts, READMEs, tweets, etc.).

Use AskUserQuestion: "Paste a writing sample — anything you've written that sounds like you. Blog post, README, email, tweet thread, 公众号文章 — all work. (Paste one now, I'll ask for more after.)"

Collect 1-3 samples. For each, extract voice traits:

• Average sentence length (short/medium/long)
• Vocabulary level (academic/technical/conversational/casual)
• Humor presence (none/dry/occasional/frequent)
• Default perspective (first_person/second_person/third_person)
• Formality (formal/neutral/informal)
• Language patterns (e.g., uses rhetorical questions, starts with anecdotes, uses 口语化 Chinese)

Show the extracted traits to the user for confirmation:

Based on your samples, here's your voice profile:
  sentence_length: short
  vocabulary: conversational
  humor: dry
  perspective: first_person
  formality: informal

Does this look right? I can adjust any of these.

Option B: Manual style description

Use AskUserQuestion to walk through each trait:

1. "How long are your typical sentences?" (short and punchy / medium / long and flowing)
2. "What's your vocabulary like?" (academic / technical jargon / conversational / casual slang)
3. "Do you use humor in your writing?" (never / dry/subtle / sometimes / a lot)
4. "What perspective do you write from?" (I/我 first person / you/你 second person / third person)
5. "How formal is your tone?" (formal / neutral / informal/casual)

Write voice.yaml

Write the voice config to content/config/voice.yaml:

# Generated by /media-setup
samples:
  - |
    <pasted sample 1>
  - |
    <pasted sample 2>

traits:
  sentence_length: <extracted or chosen>
  vocabulary: <extracted or chosen>
  humor: <extracted or chosen>
  perspective: <extracted or chosen>
  formality: <extracted or chosen>

Tell the user: "Voice profile saved. The writing skills will match this style automatically. You can update it anytime by editing content/config/voice.yaml or running /media-setup again."

Step 6: Write Config Files

Write credentials to .env (gitignored):

cat > .env << EOF
# Generated by /media-setup on $(date -u +%Y-%m-%dT%H:%M:%SZ)
DEVTO_API_KEY=<value>
HASHNODE_API_KEY=<value>
HASHNODE_PUBLICATION_ID=<value>
OPENAI_API_KEY=<value>
EOF
chmod 600 .env

Write platform config to content/config/platforms.yaml (non-sensitive, git-tracked):

# Generated by /media-setup
github_pages:
  repo_path: "<path>"
  branch: "<branch>"
  site_url: "<url>"
  posts_dir: "<dir>"

platforms:
  - devto
  - hashnode
  - github-pages

Step 7: Configure git-lfs (Optional)

If the user expects to publish many posts with images:

which git-lfs >/dev/null 2>&1 && echo "[OK] git-lfs available" || echo "[INFO] git-lfs not installed — recommended for repos with >50 posts"

If git-lfs is available, offer to configure it:

git lfs install
git lfs track "content/**/assets/*.png"
git lfs track "content/**/assets/*.jpg"
git add .gitattributes

Step 8: Summary

Print a summary of what was configured:

=== media-agent configured! ===

Platforms:
  [OK] GitHub Pages → https://username.github.io
  [OK] Dev.to → connected as @username
  [OK] Hashnode → connected to publication xyz

Image generation:
  [OK] OpenAI DALL-E 3

Writing voice:
  [OK] Voice profile configured (informal, conversational, first person)

Next steps:
  - Run /media-idea to brainstorm your first post
  - Run /media to start the full guided workflow
  - Or write markdown manually and use /media-publish