cs-abusive-customer-policy SKILL.md skillA
cs-abusive-customer-policy from polar-bear-org/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add polar-bear-org/claude-skills/cs-abusive-customer-policy@git:20261026.a2f0899Pins git:20261026.a2f0899 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- polar-bear-org/claude-skills
- Path
packs/ai-for-customer-service-pack/skills/cs-abusive-customer-policy/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261026.a2f0899, committed Oct 26, 2026
- First version recorded
- Sep 27, 2026
- Size
- 6,251 bytes
- Repository stars
- 51
- License
- a license file GitHub does not identify
Writes an abusive contact policy with warning, final warning and end-contact steps, a script for each step by channel, a supervisor backup rule with a time limit and an incident log. Use for "run cs-abusive-customer-policy", "abusive customer policy", "customer is swearing at me", "can I hang up on an abusive customer", "customer threatened our agent", "end the chat with a rude customer", "zero tolerance policy for abuse", "script for ending an abusive call", part of the AI for Customer…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Abusive Customer Policy ## When To Use Customers yell, swear or threaten, and no rule lets the agent end the contact, so people sit through it because they fear being blamed. Use it when a lead wants one written rule for when to stop, who backs the agent up, and what gets logged. The question it answers: at what point does this contact end, and who carries it from there? ## When Not To Use If the customer is angry but not abusive, and the contact can still be saved, run De-escalation Playbook instead. If the team is worn down by the volume of hard contacts rather than one incident, Workload and Recovery Rules fits better. ## Inputs - Your channels (phone, chat, email, social, in person) and any current rule or habit for rude contacts. - Two or three recent incidents, described in your own words with names removed. - Who can back an agent up on each shift, and any existing reporting route for incidents. If you have none of this, I start from phone and chat, the three steps and a blank log, and mark the output as a first draft. ## Approach …
Read the whole file at its exact version.
How to install
mdr add polar-bear-org/claude-skills/cs-abusive-customer-policy@sha256:8715f0fdcd45d8e6The line at the top of this page pins the label git:20261026.a2f0899, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_wyssaxfempf2rbcj)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 27, 2026 and Oct 26, 2026, about one every 29 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261026.a2f0899 latest | 2026-10-26 | a2f0899 | 6,251 B | A | view · diff |
| git:20260927.63d5f36 | 2026-09-27 | 63d5f36 | 6,203 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6251 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
polar-bear-org/claude-skills · 51 stars · license a license file GitHub does not identify · pushed 2026-10-26 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_wyssaxfempf2rbcj GET https://markdownregistry.com/api/v1/resolve?ref=polar-bear-org/claude-skills/cs-abusive-customer-policy GET https://markdownregistry.com/api/v1/blob/8715f0fdcd45d8e66b38aa796846dc35d1d4c5975be29840470741029163e364
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.