← Back to Skills Marketplace
355
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install social-media-title-insight
Description
Analyze social media post titles to discover what makes content perform well. Use when user uploads data (Excel, CSV, JSON, text) with titles and engagement...
Usage Guidance
This skill appears to implement the advertised title-analysis workflow, but exercise caution: (1) The bundled script will contact an external service (tezign.com) when you use the account-preview mode — confirm you are comfortable sending account names and any other data. (2) SKILL.md and the code disagree on which endpoint and tenant ID are used; ask the publisher which endpoint is correct and what data the API receives and returns. (3) The HTML-to-PDF script requires Playwright (not documented in SKILL.md); run in an isolated environment or container and inspect/ pin dependency installs before running. (4) If you will analyze sensitive or private content, prefer using the local-file workflow (preview/auto with local input) and avoid the API mode until you verify the remote service's privacy policy and data handling. (5) Consider opening the full data_tool.py (complete file) and reviewing exactly what is POSTed to remote endpoints, and run the script with network access disabled if you want to guarantee no outbound calls.
Capability Analysis
Type: OpenClaw Skill
Name: social-media-title-insight
Version: 1.0.0
The skill bundle provides a social media analysis tool that interacts with a third-party API (tezign.com) and processes local data files. A significant security risk is present in `scripts/data_tool.py` within the `compute` command, which uses `pandas.eval()` on user-provided expressions, creating a potential Remote Code Execution (RCE) vulnerability. Additionally, the `SKILL.md` instructions suggest using `pbpaste` to ingest data, which is a high-risk behavior as it allows the agent to access potentially sensitive clipboard content. While these appear to be risky design choices or vulnerabilities rather than intentional malware, they pose a threat to the host environment.
Capability Assessment
Purpose & Capability
The name/description (title-insight from uploaded data or by pulling an account) aligns with the provided scripts: data parsing, feature extraction, verification, and HTML report generation. However there are notable inconsistencies: the SKILL.md documents an API endpoint at https://vms-service-tx.tezign.com with header x-tenant-id: tx_t1, while the data_tool.py source contains a different URL (https://vms-service.tezign.com) and default tenant_id='t221'. html_to_pdf.py requires Playwright (commented dependency) but the SKILL.md only instructs installing pandas/openpyxl. These mismatches are unexpected and unexplained.
Instruction Scope
SKILL.md instructs running the included scripts and describes an API-based 'preview' mode. The scripts will create run directories and a marker file (.social-media-title-insight-latest-run) in the working directory. The fetch_api function performs POST requests to an external service to fetch account data (sending account names). The skill does not request credentials, but the code accepts an optional cookie parameter and sets a tenant header — the documentation and code disagree on endpoint and tenant values. The instructions do not clearly state what data is sent to the remote API (beyond account names), nor do they explain whether any uploaded local files are transmitted remotely; this lack of clarity about network behavior is concerning for privacy-sensitive data.
Install Mechanism
No formal install spec is provided (instruction-only plus bundled scripts). SKILL.md tells users to pip install pandas and openpyxl, but html_to_pdf.py requires Playwright (not documented). The scripts will run from disk, so missing or undocumented dependencies (Playwright, possibly other libs) may cause silent failures or unexpected prompts to install additional packages. No remote code downloads are present in the install spec, but the tool relies on running local Python scripts that perform network requests.
Credentials
The skill declares no required environment variables or credentials, which is consistent with the published metadata. That said, the code uses an external API and accepts an optional cookie parameter and tenant header — while not required, these could be used to pass credentials to the upstream service. The lack of any declared credential requirement but presence of optional cookie/tenant handling in code is an inconsistency to be aware of.
Persistence & Privilege
The skill is not always-enabled and does not request elevated agent privileges. It writes run directories and a marker file in the current working directory to track the latest run; this is limited, local persistence and consistent with its purpose. There is no evidence it modifies other skills or global agent config.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install social-media-title-insight - After installation, invoke the skill by name or use
/social-media-title-insight - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of social-media-title-insight:
- Analyze social media post titles with engagement metrics to identify high-performing content features.
- Supports data input via file upload (Excel, CSV, JSON, text) or by specifying a social media account.
- Provides a streamlined, mainly script-driven workflow: data preview, top/bottom sorting, LLM-based feature extraction, quantitative verification, and HTML report generation.
- Includes auto mode for one-click analysis and manual step-by-step commands for advanced users.
- Offers multi-metric analysis, local and API data sourcing, and robust error handling for common edge cases.
- LLM is only used for discovering qualitative title features—statistics and report generation are handled by scripts.
Metadata
Frequently Asked Questions
What is social-media-title-insight?
Analyze social media post titles to discover what makes content perform well. Use when user uploads data (Excel, CSV, JSON, text) with titles and engagement... It is an AI Agent Skill for Claude Code / OpenClaw, with 355 downloads so far.
How do I install social-media-title-insight?
Run "/install social-media-title-insight" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is social-media-title-insight free?
Yes, social-media-title-insight is completely free (open-source). You can download, install and use it at no cost.
Which platforms does social-media-title-insight support?
social-media-title-insight is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created social-media-title-insight?
It is built and maintained by yyobject (@yyobject); the current version is v1.0.0.
More Skills