claude-mem-install

Use this when setting up claude-mem on Cursor: local or remote worker, local host-login observer or remote cmem.ai inference.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

87%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.

The content is lean, executable, and well-structured for a single-purpose install skill, with copy-paste commands and exact configuration values. Its main gap is the absence of an explicit verify/health-check step after install, which the rubric caps at 3 for risky workflows.

Suggestions

Add a short verification step after each install command (e.g., confirm the worker process/MCP responds) to provide a validation checkpoint.

Clarify the decision flow between local vs remote and provider selection with a one-line 'choose X if Y' guide so Claude picks the right mode deterministically.

Note the expected result of a successful install (e.g., which MCP servers become available) so Claude can confirm success.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with no preamble or padding; dense parentheticals are earned technical specifics rather than over-explanation.	5 / 5
Actionability	Two copy-paste-ready `npx claude-mem install` commands with concrete flags, plus exact env-var names and URLs, cover the common local and remote cases.	5 / 5
Workflow Clarity	Local and remote modes are clearly sequenced with a safety directive, but there is no explicit post-install validation/verification checkpoint, which caps a risky install workflow at 3.	3 / 5
Progressive Disclosure	Under 50 lines, single-purpose, with clear Local worker / Remote worker sections and no need for external references; well-organized throughout.	5 / 5
	Total	18 / 20 Passed

Description

78%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.

The description is concise, third-person, and clearly scopes a distinct niche with an explicit "Use when" trigger and concrete mode enumeration. It is strong overall but stops just short of the most comprehensive examples on action specificity and trigger-term variety.

Suggestions

Add 1-2 concrete action verbs (e.g., 'installs hooks, registers the claude-mem MCP server, and wires Cursor') to lift specificity toward a 5.

Include a natural synonym or file/extension cue users might say (e.g., 'claude-mem MCP', '.mcp.json') to broaden trigger-term coverage.

Tighten the what/when pairing by restating the core action once explicitly before enumerating modes.

Dimension	Reasoning	Score
Specificity	"setting up claude-mem on Cursor" plus enumerated modes (local/remote worker, host-login observer, remote cmem.ai inference) names several concrete setup actions with only minor coverage gaps.	4 / 5
Completeness	It explicitly answers both what ("setting up claude-mem on Cursor" with its modes) and when ("Use this when setting up..."), though the what could be more fully spelled out.	4 / 5
Trigger Term Quality	Natural terms a user would say ("claude-mem", "Cursor", "cmem.ai") are present and relevant, but synonym/extension variety is thin compared to the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Tightly scoped to a named product and IDE with distinct mode triggers, giving it a clear niche with minimal overlap risk.	5 / 5
	Total	17 / 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: thedotmack/claude-mem
Path: claude-mem-cursor/skills/install/SKILL.md
Commit: d8bc975

Reviewed: 4 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.