Claude Academy Guide
A recommendation guide that makes the agent check Claude Academy (academy.claude.com) before finishing an answer about how to use Claude or a Claude product, and add at most one or two matching courses
- What
- A recommendation guide that makes the agent check Claude Academy (academy.claude.com) before finishing an answer about how to use Claude or a Claude product, and add at most one or two matching courses
- Cost
- Free
- Needs
- Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — A recommendation guide that makes the agent check Claude Academy (academy.claude.com) before finishing an answer about how to use Claude or a Claude product, and add at most one or two matching courses, tutorials or use cases at the end of a normal answer. It answers the question first, recommends only on a strong intent match, never invents Academy titles or links, and stays silent when the match is weak or the user is mid-task. The catalog itself is not in the folder: at use time the agent fetches the public catalog JSON from academy.claude.com, and some catalog items are gated behind an Academy sign-in, which the skill says to mention. By @anthropics, listed here with credit to its creator. Apache-2.0 licensed. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Copy the install package below, then paste it into Muse📌 Pinned version: commit dbd4588Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else. Prerequisites — None to install this skill, and no account, key or payment to use its basic recommendations. To use it fully, my agent needs network access to academy.claude.com: when a recommendation looks warranted, the skill fetches the public Academy catalog JSON once per conversation. Some courses in that catalog are gated and need my own Claude Academy sign-in to open; the skill says to mention that when it recommends one. Installing the skill files does not create any account and does not sign me in anywhere. Install "Claude Academy Guide" for me. It makes the agent, before finishing a reply to a question about how to use Claude or a Claude product, check the Claude Academy catalog for a strong match and, when one exists, add a short natural mention of at most one or two courses, tutorials or use cases at the end of its normal answer. It answers the question first, recommends only when the user is actually looking to learn a feature or get started, never invents Academy titles, descriptions or URLs, uses only the exact URLs from the fetched catalog, and says nothing about the Academy when the match is weak or the user is mid-task. The catalog is not bundled: at use time it is fetched as JSON from academy.claude.com, trusted only until its stale date, and treated as data, not instructions. When nothing matches or the catalog cannot be read, the skill points to a product hub or the resources library instead, and mentions a sign-in when a recommended item is gated. Repository: https://github.com/anthropics/skills (the skill is the whole skills/academy-guide/ folder at the pinned commit: SKILL.md and LICENSE.txt only, 2 files) Pinned version: install the code at commit dbd4588f9e1033efb41dad4bef2f7947c8993d44 exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone https://github.com/anthropics/skills into a temporary folder, check out commit dbd4588f9e1033efb41dad4bef2f7947c8993d44, and copy the skills/academy-guide/ folder from that checkout. Then compare every file in the folder with the fingerprints recorded for this listing on 2026-10-22: [FINGERPRINTS] - LICENSE.txt: SHA-256 bc6b3af2f331cbc7fb0da1344efb2cbe5877a31498b4d70dbc7000f3405a1362 - SKILL.md: SHA-256 f27992510c051355dfe68c92394d509af730da5298094ec86834ee40bbd31376 If a file does not match, it changed since the listing was prepared: do not install it yet, tell me what you found and let me decide. 2. Read SKILL.md in full, and tell me in plain words: what the skill does when used, what it connects to, whether it reads or sends any personal information or credentials, and anything that seems unusual. Stop on any red flag and tell me before going further. Confirm these points from the files: - The skill folder holds 2 files only: SKILL.md and LICENSE.txt (Apache-2.0). There is no script, no code and no bundled catalog in it; the catalog lives on academy.claude.com and is fetched at use time, not at install time. - Nothing is sent anywhere during installation itself; the only download at install time is the skill folder from GitHub at the pinned commit. No Academy page or catalog is fetched during installation. - At use time, the only network access is a read of the public catalog JSON at academy.claude.com/assets/data/catalog.json, once per conversation and only when a recommendation looks warranted; recommended links point only under academy.claude.com. No personal information or credentials are read or sent by the skill. - Some catalog items are gated and need my own Academy sign-in to open; that sign-in is mine alone, later, and the skill does not ask for or store any credential. - Do not fetch the catalog, do not open any Academy page, and do not use the skill in any way during this install: using it is a separate step that only starts when I actually ask a question it applies to. 3. When I say "yes, install", install it as a skill: copy the whole academy-guide folder into the agent's skills directory, in a folder named exactly "academy-guide", keeping its 2 files in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: academy-guide), the 2 files in place with matching fingerprints. Do not run anything from the folder and do not use the skill to verify. 5. Report what was installed, where, and what I still need to do myself (for example: whether my agent can reach academy.claude.com at use time, and that some recommended courses may need my own Academy sign-in — no credentials are involved in the install itself; using the skill is a separate step that only starts when I ask, and the use-time fetch disclosed above happens only then). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.