Content Repurposer
ReviewAudited by ClawScan on May 10, 2026.
Overview
This skill does not appear to steal data or post for you, but its scripts return canned demo text instead of truly repurposing your content, so users should review it carefully.
Before installing, understand that the included scripts appear to be demo scaffolding rather than a working content repurposer. Verify any generated text carefully, declare/install required tools like jq if you use the scripts, and avoid feeding private drafts or sensitive brand details until the implementation is corrected and reviewed.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A user could believe the output is adapted from their article or transcript and publish content that is generic, inaccurate, or unrelated to the source.
The skill is advertised as transforming the user's source content, but this script, and the other platform scripts, output canned mock responses rather than using the constructed prompt or input content.
# In a real scenario, this would be `clawdbot llm ...` ... # Let's create a mock response ... MOCK_RESPONSE="I'm building a skill to repurpose content..."
Do not treat the output as ready to publish until the scripts actually call a reviewed generation path and the generated drafts are checked against the source.
The skill may fail or behave differently depending on what local tools are installed, and users may not notice those requirements before running it.
The registry metadata declares no required binaries and no install spec, but the scripts require jq and may use curl/html2text, pbcopy, or clawdbot. This is not malicious, but the dependency contract is incomplete.
OUTPUT_DIR=$(jq -r '.output.directory' "$CONFIG_FILE") ... CONTENT=$(curl -sL "$SOURCE_INPUT" | html2text) # requires html2text
Declare required and optional binaries in metadata or setup instructions, and document the exact tools used for URL fetching, output creation, and clipboard copying.
Running the script can contact a URL, create files in the configured output directory, and overwrite the clipboard on supported systems.
The main script can fetch user-provided URLs, write output files, and copy generated content to the clipboard. These actions fit the content-repurposing purpose but are local and network side effects users should expect.
CONTENT=$(clawdbot web_fetch --url "$SOURCE_INPUT" --extractMode text) ... echo "$RESULT" > "$OUTPUT_FILE" ... cat "$FILE_TO_COPY" | pbcopy
Review URL inputs, output paths, and the copy_to_clipboard setting before running, especially when working with private drafts.
Brand/profile settings and generated content-related files may remain on disk after use.
The skill persists local configuration and a log file under the user's home directory. This is expected setup behavior, but it can include voice, brand, and CTA information used in future generations.
mkdir -p "$REPURPOSE_DIR" ... cp "$SKILL_DIR/config.example.json" "$REPURPOSE_DIR/config.json" ... echo '{"repurposings":[]}' > "$REPURPOSE_DIR/repurpose-log.json"Avoid putting sensitive personal or business information in the config unless you are comfortable storing it locally, and delete the config/output directories if no longer needed.