ClawHub ban appeals
Reviews ClawHub account-ban appeals and prepares evidence-backed moderation decisions
- Repository
- openclaw/clawhub
- Stars
- 9,546
- Licence
- MIT
- Files
- 1 file
What it does
This is an instruction file that tells an AI agent how to review an appeal from a ClawHub user whose account was banned or held. It guides the agent to confirm the exact account state, separate bans from moderation holds and blocked releases, check the evidence behind a decision, and recommend uphold, restore, request more evidence, or escalate. It also routes validated scanner mistakes to a separate ClawScan reporting process and keeps those actions apart from the account decision.
Great for
- ClawHub moderators or staff who handle account appeals and need a consistent review checklist
- Maintainers building agent workflows around the ClawHub moderation process
Skip it if
- Public users trying to get their own ban lifted: the skill grants no authority to restore accounts or send emails, and it is written for authorized staff working through Admin
- Anyone expecting a fully automated decision: the file says restoration and final calls must stay with an authorized moderator
Try asking
- “Review this ClawHub ban appeal for account handle X and tell me whether the ban is an account action or a moderation hold”
- “Check whether the scanner findings relied on in this appeal match the submitted artifact version”
- “Draft an evidence summary and recommendation for this appeal, without executing any unban”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
clawhub-ban-appeals.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip clawhub-ban-appeals.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip clawhub-ban-appeals.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Provide the exact account handle or id and the existing appeal reference before starting, since the skill requires them
- Expect the agent to prepare commands and drafts for approval rather than acting directly; confirm who holds moderation authority first
- Read the linked moderation and ClawScan files alongside this one, because they set the rules for any action taken
What's inside
- SKILL.md
Redistributed unmodified from openclaw/clawhub under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-11-02. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.