messaging-agents

Send messages to other agents on your server. Use when you need to communicate with, query, or delegate tasks to another agent.

Quality

80%

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

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 highly actionable, well-structured skill body that gives copy-paste-ready commands and Letta-specific details Claude would not already know. Conciseness and progressive disclosure are good but have minor room to improve via trimming and splitting reference material into bundle files.

Dimension	Reasoning	Score
Conciseness	Efficiently focused on Letta-specific operational details Claude would not know (CLI flags, environment routing, hidden conversations); minor instances of repetition across arguments tables and examples could be trimmed.	4 / 5
Actionability	Copy-paste-ready CLI commands with real env vars ($LETTA_AGENT_ID), explicit arguments tables, worked examples, and sample JSON responses cover the common cases fully.	5 / 5
Workflow Clarity	Flows are clearly organized into sequenced sections (find agent, start/continue conversation, discover environments) with no destructive operations requiring validation; reads more as a reference than an explicitly checkpointed workflow.	4 / 5
Progressive Disclosure	Well-organized sections with one-level-deep, clearly signaled references to related skills (finding-agents, searching-messages); all content is inline in a ~190-line file with no bundle files, so there is room to split deeper reference material out.	4 / 5
	Total	17 / 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.

A strong, well-structured description that clearly answers both what the skill does and when to use it with natural trigger phrases. Main weakness is second-person voice, which the rubric penalizes, and slightly generic action verbs.

Dimension	Reasoning	Score
Specificity	Lists several action verbs ('Send messages', 'communicate with', 'query', 'delegate tasks') but most are generic intents rather than concrete capabilities, landing at base 4; reduced by 1 for second-person voice ('your server', 'you need').	3 / 5
Completeness	Explicitly states what ('Send messages to other agents on your server') and when ('Use when you need to communicate with, query, or delegate tasks to another agent') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases users would say ('send messages to other agents', 'communicate with', 'query', 'delegate tasks to another agent') give good coverage, though a few synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Clear agent-to-agent messaging niche with distinct triggers, but 'delegate tasks to another agent' creates minor overlap risk with subagent/Agent-tool delegation skills.	4 / 5
	Total	16 / 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: letta-ai/letta-code
Path: src/skills/builtin/messaging-agents/SKILL.md
Commit: 051b47f

Reviewed: 2 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.