install-memu

Install or uninstall memU for whatever agent you are — identify your host, print its packaged guide, and follow it to wire (or unwire) both seams (record and inject). Use when the user asks to install, set up, integrate, remove, or uninstall memU.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable routing skill: concrete commands, defined placeholders, a mandatory fixed report template, verify gates, and a symmetric uninstall path. The main gaps are minor prose that could be trimmed and validation steps that are delegated to the external guide rather than inlined.

Suggestions

Trim reassurance phrasing like "is harmless to run on a personal machine" — Claude can run the documented commands without the safety framing.

Inline at least one example verify-gate command (e.g. a representative `<your-binary> config show` or status check) so the validation checkpoint is concrete rather than only referenced inside the packaged guide.

Consider briefly noting that the assets/ and scripts/db.py bundle files are not used by this routing step, or remove them from the skill bundle, so reviewers don't expect them to be referenced.

Dimension	Reasoning	Score
Conciseness	Mostly lean and operational — commands, error symptoms, and the --upgrade/uv rationale earn their place — with only minor trimmable reassurance such as "harmless to run on a personal machine" and a few elaborated phrases.	4 / 5
Actionability	Fully executable throughout: concrete commands (`pip install --upgrade memu-cli`, `memu-agent detect`, `<your-binary> docs install`, `retrieve`, `remove-instruction`) with every `<...>` placeholder explicitly defined, plus a copy-paste-ready report template.	5 / 5
Workflow Clarity	Clear three-step sequence with an explicit verify-gate mandate ("do not proceed past a failing one") and stale-build error recovery, though the actual validation commands live in the per-host guide rather than being inlined here.	4 / 5
Progressive Disclosure	Well-organized into Step 1/2/3 and Uninstall sections, routing to one-level-deep packaged guides via `<your-binary> docs install`; the local bundle (assets/, scripts/db.py) is not referenced by this routing skill, which is appropriate but keeps it just short of a clean 5.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that concretely names the actions, gives comprehensive natural trigger synonyms for both install and uninstall, and cleanly separates what from when. It is distinct to the memU product with negligible conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "identify your host", "print its packaged guide", "follow it to wire (or unwire) both seams (record and inject)" — covering both install and uninstall comprehensively.	5 / 5
Completeness	Explicitly states what the skill does (install/uninstall, identify host, print and follow the packaged guide) and when to use it, with concrete trigger phrases — both halves fully answered.	5 / 5
Trigger Term Quality	"Use when the user asks to install, set up, integrate, remove, or uninstall memU" supplies the natural synonyms users would actually say for both directions (install/set up/integrate; remove/uninstall).	5 / 5
Distinctiveness Conflict Risk	Targets a single named product (memU) with a clear install/uninstall niche and product-specific triggers, so overlap with other skills is minimal.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: NevaMind-AI/memU
Path: SKILL.md
Commit: 2c050bc

Reviewed: 17 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.