Social Engagement Audit

Social media engagement audit and optimization plan. Analyze your engagement rate, identify what's working and what's not, and get a specific action plan to...

Security Scan

The skill's code and instructions are coherent with a prompt-based engagement audit (it generates advice from a local agent), but there are a few operational omissions and privacy considerations you should be aware of before running it.

Purpose & Capability

The skill claims to produce a social media engagement audit and the included analyze.sh constructs a detailed prompt and asks an agent to generate the report — this matches the stated purpose. However, the skill does not connect to any social platform APIs or verify metrics; it produces audits only from the user-supplied textual description. If you expected automatic data collection from Instagram/Twitter/etc., this skill does not do that.

Instruction Scope

SKILL.md and analyze.sh keep to the audit task and do not attempt to read system files or network secrets. The script does invoke an external agent (openclaw agent --local ...) and uses python3 to parse JSON; those invocations are not declared in the skill metadata. The script will send whatever you pass as INPUT to the agent — so any sensitive account details you include will be sent to whichever model/service the openclaw agent is configured to use.

Install Mechanism

There is no install spec (instruction-only plus a small shell script). No downloads or archive extraction are present, so nothing is written to disk beyond the included files. This is a low-risk install posture.

Credentials

The skill declares no required environment variables, credentials, or config paths, and the code does not read any additional env vars. That is proportional for a prompt-based audit that relies on user-supplied text.

Persistence & Privilege

always is false and the skill does not request persistent system-wide privileges or attempt to modify other skills. It requires the agent CLI at runtime but does not install itself as always-enabled.

Assessment

This skill generates audits by sending your input to an OpenClaw agent via the openclaw CLI; it does not fetch real account data from social platforms. Before using it: (1) review and confirm you have the openclaw CLI and python3 on the host, since analyze.sh calls both (the skill metadata did not list these binaries); (2) avoid pasting sensitive credentials or private data into the INPUT because the data will be sent to whatever model/service your openclaw agent is configured to use; (3) if you expect automated data retrieval from social networks, this skill doesn't do that — you'd need a version that uses official APIs and appropriate credentials; (4) run the script in a controlled environment first (or inspect/modify it) if you are unsure about where the agent sends data.

Diagnose why your engagement is low and get a concrete plan to fix it.

Usage

engagement audit: Instagram account fitness niche 2.1% engagement rate
social audit: LinkedIn page B2B software, 500 followers, 10 likes per post
account audit: TikTok creator food niche, 10K followers, 200 average views
engagement rate: analyze my Twitter account tech content, 1K followers

What You Get

1. Engagement Rate Diagnosis — how you compare to benchmarks
2. Top 5 Engagement Killers — specific things dragging you down
3. Content Autopsy — what type of posts are underperforming and why
4. Algorithm Alignment Check — are you fighting or working with the algorithm
5. 30-Day Fix Plan — specific weekly actions to double engagement
6. Quick Wins — 3 things to change today for immediate impact