AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Media Idea

skill-minara-ai-media-agent-media-idea · by Minara-AI

|

No reviews yet
0 installs
8 views
0.0% view→install

Install

$ agentstack add skill-minara-ai-media-agent-media-idea

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-minara-ai-media-agent-media-idea)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
4mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Media Idea? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

/media-idea — Brainstorming & Ideation

Brainstorm your next piece of content and produce a structured brief.

Step 1: Understand the User's Direction

Use AskUserQuestion to explore:

Question 1: "What topic or area are you thinking about? It can be vague — we'll sharpen it together."

Question 2: "Who's the audience?"

  • A) Developers (general)
  • B) Beginners learning to code
  • C) Senior engineers / architects
  • D) Specific community (describe)

Question 3: "What's the goal of this piece?"

  • A) Teach something (tutorial, how-to)
  • B) Share an opinion or insight
  • C) Announce something (project, release)
  • D) Tell a story (case study, post-mortem)

Step 2: Research (Optional)

If the user's topic would benefit from current context, offer to search:

"Want me to look up what's being discussed about this topic right now? I can search for recent articles and discussions to help find a unique angle."

If yes, use WebSearch with 2-3 queries:

  • " blog post 2026"
  • " developer tutorial"
  • " common mistakes"

Summarize findings: what angles are already covered, where there's a gap.

Step 3: Generate Ideas

Based on the user's input and research, propose 3-5 content ideas. For each:

  • Title (compelling, specific)
  • Angle (what makes this different from existing content)
  • Format (tutorial, opinion piece, case study, listicle)
  • Estimated length (short: 500-1000 words, medium: 1000-2000, long: 2000+)

Use AskUserQuestion: "Which of these speaks to you? Or describe something different."

Step 4: Develop the Chosen Idea

For the selected idea, propose a detailed outline:

  • Hook (opening sentence/paragraph that grabs attention)
  • Sections (4-7 sections with one-line descriptions)
  • Key takeaway (what the reader leaves with)
  • Call to action (what the reader should do next)

Use AskUserQuestion: "How does this outline look?"

  • A) Looks good, save the brief
  • B) Adjust the outline (describe changes)
  • C) Start over with a different idea

Step 5: Select Target Platforms

Check which adapters are configured:

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: $display"
done

Use AskUserQuestion: "Which platforms should we publish to?" Show configured platforms with multi-select.

Step 6: Save the Brief

Create the post directory and save the brief:

SLUG=$(echo "" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g' | sed 's/--*/-/g' | sed 's/^-//' | sed 's/-$//')
DATE=$(date +%Y-%m-%d)
POST_DIR="content/posts/${DATE}-${SLUG}"
mkdir -p "$POST_DIR/assets" "$POST_DIR/variants"

Write brief.yaml:

title: ""
angle: ""
format: ""
audience: ""
goal: ""
length: ""
platforms: []

outline:
  hook: ""
  sections:
    - title: ""
      description: ""
    - title: ""
      description: ""
  takeaway: ""
  cta: ""

created: 

Step 7: Summary

Brief saved for "":

  Post directory: content/posts/-/
  Format: 
  Target platforms: 
  Sections: 

Next: run /media-write to start writing, or /media for the full workflow.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.