← Search

Amplitude Taxonomy Guardian
Data 🧪 Install ran in our test sandbox · Nov 11, 2026 📌 Pinned version: commit c4bcb5f
Install test only, on the date shown. This does not guarantee the code is safe.
⚙ Needs: an Amplitude account with a tracking plan…

Amplitude Taxonomy Guardian

Keep your Amplitude tracking plan consistent — audit, naming, schemas, and governance workflow

At a glance
What
Keep your Amplitude tracking plan consistent — audit, naming, schemas, and governance workflow
Cost
Free
Needs
an Amplitude account with a tracking plan; the Amplitude MCP server configured (the skill reads and updates taxonomy metadata through it); write access to the plan if I want governance actions carried out rather than only audited. No API key is needed to install the skill itself — installing it is only files, and nothing runs during installation.
Install
Copy the installer prompt below into your Muse — your agent does the rest.

Version:

Quick answer

Amplitude Taxonomy Guardian is a free Muse skill that keeps Amplitude tracking plan consistent as it evolves, covering verifying or establishing the connection, auditing tracking for counts, naming, and schema, and creating or updating branches and events. It manages schema validation so breaking changes surface before they ship, and requires the Amplitude MCP server and a plan with write access.

⌁

Install

Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit c4bcb5f

Before you start: tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead. Prerequisites: an Amplitude account with a tracking plan; the Amplitude MCP server configured (the skill reads and updates taxonomy metadata through it); write access to the plan if I want governance actions carried out rather than only audited. No API key is needed to install the skill itself — installing it is only files, and nothing runs during installation. Install "Amplitude Taxonomy Guardian" for me. It is the source of truth for my Amplitude event taxonomy: creating, validating, auditing and scoring tracking plans, naming conventions and property standards, safe metadata operations, phased deprecation procedures, and AI-readiness guidance. Its newest capability is auditing a plan or a branch against my own standard: it reads my naming conventions from Data → Settings (the eventNC and propertyNC settings) and my AI Context (project-level text overrides org-level), applies the sources in a fixed order — settings first, then AI Context, then a convention my taxonomy already follows consistently, then the skill's own standards — and audits names and metadata against that standard. Source: https://raw.githubusercontent.com/amplitude/mcp-marketplace/c4bcb5feff54cf3332290ee0071a2def2b1f149d/plugins/amplitude/skills/taxonomy/SKILL.md (the skill is the whole plugins/amplitude/skills/taxonomy/ folder at that commit) Pinned version: install the code at commit c4bcb5feff54cf3332290ee0071a2def2b1f149d exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. Updated October 16, 2026: Skill Harbor regenerated this install prompt from the current upstream file. What changed since the version the previous prompt described (at commit e61691f8): the skill can now check a tracking plan or branch against the customer's own standard — new "Whose Standard Applies" and "Auditing Against the Customer's Standard" sections define where that standard is read from (the Data → Settings naming conventions, eventNC and propertyNC, and the AI Context, project level overriding org level) and the order in which the sources apply; reading and analysis remain autonomous and decisive, and the metadata-write and deprecation procedures are now spelled out in this file itself rather than delegated to a separate governance skill. 1. Download the whole plugins/amplitude/skills/taxonomy/ folder at the pinned commit — SKILL.md and every file it contains — into a temporary folder. 2. Compare SKILL.md with the fingerprint from Skill Harbor's review of October 16, 2026: - SKILL.md: SHA-256 0dc5f4de8e5f135d30a1f281fd9907ed29c6b73137d7e4b1015444e491571956 If it does not match, it changed since the review: do not install it yet — tell me what you found and let me decide. 3. Read SKILL.md and tell me in plain words: what the skill does when used, which services it connects to, whether it reads or sends any personal information or keys, and anything that seems unusual. Nothing is sent anywhere during installation itself. 4. When I say yes, copy the whole folder's contents into my skills folder, in a folder named "taxonomy", keeping every subfolder as it is. 5. Check the copy with no network calls (valid frontmatter, files in place) and tell me what was installed, where, and what is left for me to do (for example: configure the Amplitude MCP server, and make sure my project's naming settings and AI Context are in place if I want audits against my own standard). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Rules: only touch the temporary folder and the install target. If something seems off, stop and ask me. Never print or paste a secret value.

🔒 Security, provenance and what this touches
🧭 What this touches
Based on the install prompt we scanned, this skill does not run commands, make third-party network calls, install packages, write files, or ask for API keys.
Install prompt analysis · 2026-10-13
🔒 Security and provenance
📌 Pinned version: commit c4bcb5f · 2026-10-16
🧪 Install ran in our test sandbox · Nov 11, 2026
👁 Observed during the install test · Nov 11, 2026 : no network contact
🔎 Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Wanna be extra careful?

The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?

How to check a skill before installing →

✓

Verification certificate

Dated facts about what was checked for this listing, and how. This is not a safety certification.

Pinned version
c4bcb5f · 2026-10-16
Sandbox install test
Install ran in our test sandbox · Nov 11, 2026
Creator identity
Not verified
Fingerprint watch
Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Install prompt analysis
2026-10-13 : No commands, network calls, packages, file writes or API keys detected.

Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify

?

Questions

How do I install a skill?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill 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 skill before installing it.