ClawHub

Douyin Comment Auto Reply

v0.1.0

Douyin comment operations workflow for your own account videos. Use when the user wants to collect, classify, draft, review, or semi-automate replies to comm...

⭐ 0· 60·0 current·0 all-time
byKoi@jinhuadeng
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match included scripts and SKILL.md: batch drafting and browser-based reply execution for the user's own Douyin videos. No unrelated credentials, binaries, or config paths are requested.
ℹ
Instruction Scope
SKILL.md remains scoped to the user's own account and provides guardrails (dry-run, force-review, skip high-risk types). It instructs browser automation against the Douyin creator page and to generate drafts first — this is expected. Operators must follow the documented safeguards (dry-run, selectors, manual review) to avoid accidentally replying to the wrong comments or performing undesirable mass actions.
ℹ
Install Mechanism
There is no install spec; the skill is instruction+scripts only. The browser executor relies on running 'npx -y agent-browser' by default at runtime, which will fetch and run code from the npm registry. That is a reasonable choice for a browser automation executor but carries the usual risks of fetching remote packages at runtime; verify the agent-browser package/source before production use.
✓
Credentials
No environment variables, credentials, or config paths are requested. The scripts operate on local CSV/JSON files and a user-provided Douyin URL/selectors — this is proportionate to the stated functionality.
✓
Persistence & Privilege
Skill is not marked always:true and does not attempt to modify other skills or global agent config. It writes local sent-log files for audit, which is appropriate for reply automation.
Assessment
This skill appears to do what it says: batch-classify comments and optionally drive browser automation to post replies. Before running any real-send automation: (1) always run --dry-run and verify selectors on the Douyin page; (2) review the generated drafts and keep manual review for price/support/skepticism; (3) be aware the executor runs 'npx -y agent-browser' by default — inspect/verify that package or provide a trusted --browser-cmd; (4) note the scripts use subprocess.run(shell=True) for invoking agent-browser; avoid passing untrusted values into --browser-cmd or session-name to prevent injection risks; (5) keep backups of your comment exports and review the sent-log output to audit what was sent. If you need higher assurance, ask the author for provenance of the agent-browser tool or adapt the executor to call a vetted local automation binary instead of npx.

Like a lobster shell, security has layers — review code before you run it.

latestvk97e5xqqv7h1ne3r7k997j1gan844f6a

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments