Preflight

Pre-publish audience reaction check. Run any content (tweet, launch copy, pricing page, announcement, blog post) through diverse AI personas before publishin...

Security Scan

The skill's code, persona library, and runtime instructions are coherent with its stated purpose (pre-publish persona-based checks); no unexpected credentials or installers are requested — but review how/where the model requests are sent before running on sensitive content.

Purpose & Capability

The name/description (pre-publish persona checks) matches the included assets: SKILL.md, a personas library, and a Python runner that sends the content to an LLM and aggregates persona responses. Required tools (python openai client) are proportional to the task.

Instruction Scope

SKILL.md instructs the agent to read a project personas file if present and to run quick checks when used autonomously. The script performs only the described actions (send content to an LLM, parse responses). However, the script issues HTTP requests to a configurable base_url (default http://localhost:11434/v1). If that base_url is set to a remote/untrusted host, published content could be sent off-host — so confirm the endpoint before enabling autonomous or pipeline runs.

Install Mechanism

There is no install spec (instruction-only skill). The included Python script depends on the openai Python package; this is reasonable and low-risk compared to remote downloads or arbitrary installers.

Credentials

The skill declares no required environment variables or credentials. The script hardcodes api_key='ollama' when constructing the OpenAI client (a placeholder value) and does not read secrets from the environment. This is unusual but not evidence of credential exfiltration; nonetheless verify client configuration before sending sensitive content to any external endpoint.

Persistence & Privilege

The skill does not request 'always' presence and uses default autonomous-invocation behavior. It does not attempt to modify other skills or system-wide settings. Normal privileges for a tool that can be run in pipelines.

Assessment

This skill appears to do what it says: run content through persona-based LLM checks. Before installing or enabling autonomous runs, do the following: (1) Confirm the model endpoint (base_url) is a trusted host — the script defaults to localhost but is configurable; pointing it at a remote server would transmit your content off-host. (2) If you will test sensitive or private copy, run the tool locally (keep base_url as localhost) or inspect logs to ensure no unintended outbound endpoints. (3) Note the script requires the Python 'openai' package — install only from trusted sources. (4) If you plan to enable automated/cron/pipeline invocation, make sure you understand when and what content will be auto-submitted to the LLM service. Finally, review the full script on disk (the provided snippet appears truncated in this review) to confirm there are no hidden remote endpoints or telemetry before running in production.

Pre-publish content through simulated audience personas. Get a verdict before you ship.

Workflow

Given content the user wants to publish, run it through audience personas and return a verdict.

1. Load Personas

Check for preflight-personas.md in the project root. If it exists, use those personas. Otherwise use the defaults in references/personas.md.

For quick checks, use 4 personas: The Scroller, The Skeptic, The Ready Buyer, The Amplifier. For thorough checks, use all 8.

2. Evaluate

For each persona, adopt that persona fully and evaluate the content by answering:

1. FIRST REACTION (1-2 sentences): Gut reaction in the first 3 seconds
2. WOULD YOU ENGAGE? (yes/no + why): Would you like, comment, click, or reply?
3. WOULD YOU SHARE? (yes/no + why): Would you send this to someone or repost it?
4. ONE REWRITE (1-2 sentences): One change to make this work better for this persona

Be blunt, specific, and honest. No hedging. Stay in character.

3. Score

Count engagement and share signals across all personas:

• Engage rate: % of personas who would engage
• Share rate: % of personas who would share

4. Verdict

• 🟢 SHIP IT — 50%+ would share. Publish as-is.
• 🟡 REVISE — engaging but not shareable. Read the rewrites, apply the best one, optionally re-run.
• 🟠 RETHINK — mixed signals. The message itself may be wrong, not just the wording.
• 🔴 KILL IT — not landing. Don't publish. Rethink the approach.

5. Output

Present results as:

PREFLIGHT: [verdict]
Engage: X/Y personas | Share: X/Y personas

[For each persona, one line summary of reaction + their rewrite suggestion]

If patterns emerge across personas (e.g., "3 of 4 want to see an image"), call that out as the top actionable insight.

Keep output brief. The user wants a decision, not an essay.

Customization

See references/personas.md for the default persona library and instructions for creating project-specific personas.

Integration

This skill works as a step in any publishing workflow. When used autonomously (heartbeats, cron, content pipelines), run the quick check (4 personas) by default. Use the full 8 when the user explicitly asks for a thorough preflight.