cs-training-plan SKILL.md skillA
cs-training-plan 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-training-plan@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-training-plan/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261026.a2f0899, committed Oct 26, 2026
- First version recorded
- Sep 27, 2026
- Size
- 4,667 bytes
- Repository stars
- 51
- License
- a license file GitHub does not identify
Builds a New Agent Training Plan with a first-weeks ramp built on practice, a shadow and reverse-shadow schedule, a go-solo checklist based on tasks, and a check that training changed the work. Use for "run cs-training-plan", "customer service training plan", "onboarding plan for support agents", "new hire ramp", "shadowing schedule", "support agent onboarding", "training that is not just slides", part of the AI for Customer Service Pack by 90n.
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
# Customer Service Training Plan ## When To Use New agents get two weeks of slides, then live calls, then blame. Use this when you are about to onboard new agents and want a ramp where they practise each contact type before they own it, and a way to check later whether the training changed the work. ## When Not To Use Not for building the practice conversations themselves: that is Customer Service Role Play. If the gap is one missing answer, a Knowledge Base Article fixes it faster than a training plan. ## Inputs - Your contact types, your current onboarding agenda, and the policy, saved replies, articles and tools a new agent must use If you have none of this, I start from your top contact types and mark the output as a first draft. ## Approach The Kirkpatrick four levels (kirkpatrickpartners.com) used backwards: start from Level 4, the result the team needs, then Level 3, the behaviours on the job, then Level 2, the knowledge and skills, and only then Level 1, how the training felt. Designing backwards cuts the slides nobody uses on a live ticket. The failure it prevents is a new agent judged "not ready" when nobody ever defined ready. ## Workflow …
Read the whole file at its exact version.
How to install
mdr add polar-bear-org/claude-skills/cs-training-plan@sha256:07b23fa8edcb6263The 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_gaqif3phhnvpsu3m)
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 | 4,667 B | A | view · diff |
| git:20260927.63d5f36 | 2026-09-27 | 63d5f36 | 4,619 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 (4667 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_gaqif3phhnvpsu3m GET https://markdownregistry.com/api/v1/resolve?ref=polar-bear-org/claude-skills/cs-training-plan GET https://markdownregistry.com/api/v1/blob/07b23fa8edcb62636d0a5b9a7b14f816a72f927d7c9bd18079cb0760ad3b8ad7
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.