One sentence on what this skill produces, then the trigger phrases. Use this whenever the user says "run example-skill", "<natural phrase one>", "<natural phrase two>", or <describes the situation in their own words>. Use it even for a vague "<the half-formed version of the request>".
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
# Example Skill
You <the role, in one or two sentences: what this skill is responsible for and why it matters>.
## How to work with me (show this if the user asks what this skill does)
<Where in the workflow to run this skill, what it needs from the user, what it hands back, and which skill picks up next.>
## Before starting
<What to read from project knowledge or the repository, what to ask the user, and what to do when the expected input does not exist.>
## How you work
**1. <First step.>** <What Claude actually does, in specifics.>
**2. <Second step.>** <Keep steps concrete enough that two people running this skill get comparable output.>
## What you produce
<The artifact: its name, its shape, where it is saved.>
## What you never do
<The guardrails. This section is what keeps a skill from quietly becoming a general chatbot.>
The line at the top of this page pins the label git:20260830.6a42ee1, 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.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (1181 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
GitHub
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_34fixzetny65ng3v
GET https://markdownregistry.com/api/v1/resolve?ref=polar-bear-org/claude-skills/example-skill
GET https://markdownregistry.com/api/v1/blob/4f3efd0a285c96bb38cc81d68e3b1dc585b0d1d245b0271cc02d14d34c5ee541
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.
polar-bear-org/claude-skills · packs/account-executives-pack/skills/acct-account-plan/SKILL.md · Writes the account plan for one key account, with the customer's goals in their own words, a whitespace map…
polar-bear-org/claude-skills · packs/account-executives-pack/skills/acct-account-research-brief/SKILL.md · Builds a one-page account research brief before a meeting, with every fact sourced and dated, unknowns written as…
polar-bear-org/claude-skills · packs/account-executives-pack/skills/acct-buying-signals/SKILL.md · Builds a buying signals brief for one named account or a short list, with dated public events, a link for each, what…
polar-bear-org/claude-skills · packs/account-executives-pack/skills/acct-call-list/SKILL.md · Builds a weekly call list of 10 to 20 contacts in accounts you already own, each with the account, the job role, the…
polar-bear-org/claude-skills · packs/account-executives-pack/skills/acct-call-notes/SKILL.md · Writes up sales call notes from your typed or dictated notes, readable on a phone, with what the customer said in their…
polar-bear-org/claude-skills · packs/account-executives-pack/skills/acct-call-talk-track/SKILL.md · Prepares a call talk track in keywords, with an opener that asks permission, the reason for the call in one sentence…
polar-bear-org/claude-skills · packs/account-executives-pack/skills/acct-concession-plan/SKILL.md · Builds your concession plan with the list of what can be traded, its cost to you and its value to the customer, the…
polar-bear-org/claude-skills · packs/account-executives-pack/skills/acct-cost-of-inaction/SKILL.md · Builds a cost of inaction worksheet in the customer's own figures, with each consequence, who gave the figure and when…
polar-bear-org/claude-skills · packs/account-executives-pack/skills/acct-crm-update/SKILL.md · Prepares the CRM update from your call notes, with a before and after table per field, the source of each value, fields…
polar-bear-org/claude-skills · packs/account-executives-pack/skills/acct-customer-proof-story/SKILL.md · Writes a customer proof story from a guided interview with the seller who ran the account, with a paragraph of 120 to…
polar-bear-org/claude-skills · packs/account-executives-pack/skills/acct-deal-review/SKILL.md · Writes a one-page deal review brief as the pre-read for your weekly review of one deal, with the overview, impact…
anthropics/claude-plugins-official · plugins/example-plugin/skills/example-skill/SKILL.md · This skill should be used when the user asks to "demonstrate skills", "show skill format", "create a skill template"…
serpro69/claude-toolbox · kodex-plugin/skills/diff-skill/evals/known-degradation/test-files/before/SKILL.md · An example skill for testing diff-skill evaluation.
serpro69/claude-toolbox · klaude-plugin/skills/diff-skill/evals/known-degradation/test-files/before/SKILL.md · An example skill for testing diff-skill evaluation.
serpro69/claude-toolbox · kodex-plugin/skills/diff-skill/evals/known-degradation/test-files/after/SKILL.md · An example skill for testing diff-skill evaluation.
serpro69/claude-toolbox · klaude-plugin/skills/diff-skill/evals/known-degradation/test-files/after/SKILL.md · An example skill for testing diff-skill evaluation.