letta-guide

Answer questions about Letta itself from the official documentation. Use whenever the user asks how Letta works, what Letta (or you) can do, or how to set up or configure providers, models, channels, skills, memory, schedules, permissions, self-hosting, pricing, or billing — any "how do I…" or "can Letta…" question about the Letta product. Fetch the docs before answering; never answer Letta product questions from memory alone.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

81%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 tight, actionable skill body that sequences a fetch-then-read workflow with explicit validation and fallback escalation, and references a real bundled helper rather than inlining heavy detail. Minor trimming and a clearer overview framing would lift it further.

Suggestions

Consider collapsing or tightening the 'Hard rules' and 'Support escalation' sections, which repeat some 'never invent / always fetch' guidance already implied by the source route.

Add a one-line overview or 'Quick start' framing at the top of the body so the reader immediately grasps the fetch-then-answer intent before the detailed source route.

Where <SKILL_DIR> appears, note that it is resolved by the runtime so Claude knows the commands are directly runnable without substitution.

Dimension	Reasoning	Score
Conciseness	Lean and free of concept over-explanation, assuming Claude's competence; a few rules and escalation lines could be trimmed slightly, keeping it just below the perfectly lean 5 anchor.	4 / 5
Actionability	Provides concrete, executable commands (the fetch-letta-docs.mjs invocations with flags) plus specific fallback steps; the <SKILL_DIR> placeholder and reliance on a helper leave a minor gap versus fully copy-paste-ready code.	4 / 5
Workflow Clarity	A clearly sequenced source route with explicit validation checkpoints (ETag verification, 'read the returned docs path before running for another URL') and a feedback/escalation loop for failed retrieval, matching the top anchor.	5 / 5
Progressive Disclosure	Well-organized sections with a single one-level-deep reference to a real bundled script (confirmed present in ./scripts/); lacks an explicit overview/quick-start framing that would push it to a 5.	4 / 5
	Total	17 / 20 Passed

Description

91%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 pairs an explicit action statement with a concrete 'Use whenever' trigger and a broad catalog of volatile domains. It clearly answers both what and when and carves out a distinct niche with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Answer questions about Letta itself', 'how to set up or configure providers, models, channels, skills, memory, schedules, permissions') with only minor gaps; not quite the comprehensive multi-action list of a 5.	4 / 5
Completeness	Explicitly answers both what ('Answer questions about Letta itself from the official documentation') and when ('Use whenever the user asks how Letta works…') with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrasing including the exact user phrasings ('how do I…', 'can Letta…') plus an enumerated catalog of volatile topics users would name, matching the top anchor's synonym coverage.	5 / 5
Distinctiveness Conflict Risk	Scoped tightly to the Letta product with a niche trigger set, making conflict with other skills minimal; matches the clear-niche anchor.	5 / 5
	Total	19 / 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/letta-guide/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.