Install
$ agentstack add skill-jeremylongworth-source-agentskills-community-moderation-brief ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Community Moderation Brief
Core Workflow
- Identify the item, channel, policy or rule context, audience impact,
visibility, prior action, decision owner, and deadline.
- Summarize the issue without overstating intent, motive, identity, or rule
violation.
- Classify the moderation question: reply, hold, hide, remove, escalate,
document, educate, or no action.
- Draft options with rationale, likely tradeoffs, missing context, and required
approvals.
- Route legal, safety, sponsor, customer support, platform policy, privacy,
child safety, harassment, doxxing, and crisis items to a human reviewer.
- Keep moderation and community systems read-only unless the user approves a
specific action.
Decision Guidance
- Use "hold for review" when facts, policy, consent, or severity are unclear.
- Use "reply draft" when a calm, public or private response can resolve the
issue without implying a policy decision.
- Use "remove or restrict for review" only as a recommendation, not an action.
- Use "escalate" when the item involves safety, legal, platform, sponsor,
privacy, payments, minors, threats, harassment, or reputational risk.
- Use "document" when a recurring pattern may require a future policy or FAQ.
Safety Rules
- This is review support, not legal, crisis, platform enforcement, or trust and
safety advice.
- Do not send replies, remove content, ban users, mute users, approve members,
change roles, report accounts, or update rules without explicit approval.
- Do not invent policy terms, violations, user intent, private facts, platform
requirements, screenshots, prior warnings, or relationship history.
- Separate public response drafts, private/internal notes, moderation rationale,
missing context, and approval owner.
Deliverable Shape
For a moderation brief, provide:
- Issue summary
- Evidence provided
- Policy or rule context
- Risk classification
- Options and rationale
- Recommended next step
- Missing context
- Review owner
- Approval status
References
- Read
references/community-moderation-brief-checklist.mdwhen drafting
moderation, escalation, or boundary review packets.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: jeremylongworth-source
- Source: jeremylongworth-source/AgentSkills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.