Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Moderation & Safety Playbook Skill · gtmagents | DecimalAI

sales supportby gtmagents

Moderation & Safety Playbook Skill

gtmagents/moderation-safety-playbook

Source gtmagents/gtm-agents ↗License Apache-2.0

Guidelines and workflows for community moderation, trust & safety, and escalation.

SkillScore86Maintained

Automatic

Support pack

Last verified 8/23/2026

What it changes

Passed 19 of 22 test cases with the skill, and 15 of 22 without it.

Without skill68%

With skill86%

Checks it passed that the model alone missed

Includes sample responses, explicit tone guidance, and decision trees within the moderator guide.
Establishes graduated enforcement tiers corresponding to the severity and repetition of infractions.
Identifies legal, security, PR, and executive sponsors as target stakeholders for severe escalations.

and 1 more in the full report

4 fixed15 passed either way3 still failing0 broke

Pass-rate lift: +18 pp
Tokens: +9%
Agent turns: 0%
Response time: -2%

Model gemini-3.6-flashMeasured 8/23/2026v119 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/gtmagents-moderation-safety-playbook/SKILL.md https://app.decimal.ai/s/gtmagents-moderation-safety-playbook/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add gtmagents-moderation-safety-playbook, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/gtmagents-moderation-safety-playbook/ and pins it in .decimal/skills.lock

decimalai skills add gtmagents-moderation-safety-playbook

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/gtmagents-moderation-safety-playbook/SKILL.md https://app.decimal.ai/s/gtmagents-moderation-safety-playbook/SKILL.md

Raw file: /s/gtmagents-moderation-safety-playbook/SKILL.md ↗ · machine-readable summary at /s/gtmagents-moderation-safety-playbook.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

We are setting up our moderation software stack. Engineers suggested relying exclusively on automated regex filters without human oversight software. What core operational tooling components should be implemented for the moderation team?

What was checked, without and with the skill
Checked	Without skill	With skill
Specifies implementing moderation dashboards alongside keyword lists, automation rules, and user reporting forms.	Missed	Passed

case-07 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md25 linessingle file

Moderation & Safety Playbook Skill

When to Use

Launching or scaling moderated forums, chats, or live events.
Training moderators, ambassadors, or vendors on policies.
Handling escalations, abuse reports, or crisis communications.

Framework

Policy Matrix – code of conduct, content types, enforcement tiers, regional considerations.
Workflow – intake → triage → resolution → follow-up, with SLAs and ownership.
Tooling – moderation dashboards, keyword lists, automation rules, reporting forms.
Escalation Ladder – when to engage legal, security, PR, or executive sponsors.
Post-Incident Review – retrospectives, comms templates, improvements.

Templates

Moderator guide with sample responses, tone guidance, and decision trees.
Incident log + scoreboard for tracking volume, severity, MTTR.
Crisis comms outline for public/partner updates.

Tips

Publish a transparent policy summary so members know expectations.
Rotate moderators to reduce burnout; provide mental health resources.
Pair with launch-community-activation-series for real-time event safety coverage.

Track record

Benchmark

19 / 22

test cases passed, vs 15 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

gtmagents / gtm-agents

plugins/community-building/skills/moderation-safety-playbook/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Moderation & Safety Playbook Skill

When to Use

Framework

Templates

Tips

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills