CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agentmemory-config

Set up and diagnose local agentmemory, including MCP, environment variables, ports, and feature flags. Use when getting started, checking a connection, enabling a feature, configuring auth, or explaining why a feature is off by default.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 largely excellent, actionable configuration guide with concrete commands and a clear check-first diagnostic workflow. Its main weaknesses are a dangling REFERENCE.md reference (the file is absent from the bundle), some duplicated gating explanations, and an overstuffed step 4 in the connection workflow.

Suggestions

Ship REFERENCE.md alongside SKILL.md (or inline the recognized-variable list) so the 'full recognized-variable list' pointer in the Reference section resolves to a real file in the bundle.

Split step 4 of the connection checklist into separate sub-steps for auth secret resolution, custom ports, and the HTTPS/loopback rule so each concern is individually actionable.

State the LLM-provider gating once (in Defaults worth knowing) and trim the redundant restatement in the Optional richer memory section to save tokens.

DimensionReasoningScore

Conciseness

The body is dense with tool-specific facts and assumes competence (no explanations of what MCP or env vars are), but the LLM-provider gating is stated twice ("A provider key in the environment does nothing until AGENTMEMORY_LLM_PROVIDER names that provider" and again under Defaults) and step 4 is a run-on paragraph, so it is efficient with minor trimming possible rather than fully lean.

4 / 5

Actionability

Guidance is fully executable: concrete commands (`agentmemory status`, `node dist/cli.mjs status`, `agentmemory connect codex --with-hooks`, `--port <N>`), exact variable names and values, a copy-paste `env` block, and the `agentmemory://status` resource cover the common configuration and diagnostic cases.

5 / 5

Workflow Clarity

"Check the connection first" gives a clear numbered diagnostic sequence with a validation-first step, an explicit failure branch ("If it fails, check Node.js 20+ and `agentmemory status`"), and a decision point for duplicate connections; step 4 crams auth, ports, and HTTPS rules into one paragraph, leaving minor sequencing gaps versus the 5-anchor.

4 / 5

Progressive Disclosure

Sections are well organized and the variable list is appropriately deferred rather than inlined, but the primary deferred target "The full recognized-variable list lives in REFERENCE.md" is dangling — no REFERENCE.md or references/ directory exists in the bundle, so the flagged deep content is unreachable; that is more than the 4-anchor's 'minor organization gaps'.

3 / 5

Total

16

/

20

Passed

Description

87%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 description: third-person voice, explicit 'what' and 'when' clauses, natural trigger phrases, and a clearly named tool niche. Keyword coverage could add a few common variants like 'troubleshoot' or 'not connecting', and the action list could be marginally more granular.

DimensionReasoningScore

Specificity

"Set up and diagnose local agentmemory, including MCP, environment variables, ports, and feature flags" lists several concrete action areas (setup, diagnosis, MCP, env vars, ports, flags), matching the 4-anchor's 'several specific actions; minor gaps' rather than the 5-anchor's comprehensive catalogue of concrete actions.

4 / 5

Completeness

It explicitly answers both 'what' ("Set up and diagnose local agentmemory, including MCP, environment variables, ports, and feature flags") and 'when' ("Use when getting started, checking a connection, enabling a feature, configuring auth, or explaining why a feature is off by default") with concrete trigger phrases, matching the 5-anchor exactly.

5 / 5

Trigger Term Quality

"getting started, checking a connection, enabling a feature, configuring auth" are natural phrases a user would say, giving good keyword coverage; a few natural variants (e.g., 'troubleshoot', 'not connecting', 'debug') are missing, so it sits between the 4 and 5 anchors.

4 / 5

Distinctiveness Conflict Risk

Naming the specific tool "agentmemory" with tool-specific triggers (MCP connection, feature flags, agentmemory auth) creates a clear niche with minimal conflict risk against other skills, matching the 5-anchor.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

rohitg00/agentmemory

Path

plugin/skills/agentmemory-config/SKILL.md

Reviewed

Table of Contents

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.