CtrlK
BlogDocsLog inGet started
Tessl Logo

letta-guide

Read the official Letta documentation (docs.letta.com) through its cached, ETag-checked fetch route. Load before ANY docs.letta.com retrieval — answering how Letta works, what Letta (or you) can do, setting up providers, models, channels, skills, memory, schedules, permissions, self-hosting, pricing, or billing, AND looking up Letta API, Agent SDK, or Letta Code reference while writing code. Do not use fetch_webpage or web_search on docs.letta.com; this skill's helper is the docs route. Never answer Letta product questions from memory alone.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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, actionable guide with a clear sequenced workflow, real bundle script reference, and explicit error-handling fallback. It is efficient and mostly lean, with only minor verbosity and a few abstract spots preventing top marks.

DimensionReasoningScore

Conciseness

The body is lean and largely assumes Claude's competence (numbered route, hard rules, caching notes) with executable commands rather than concept explanations; a few justificatory sentences (e.g. "Users lose trust fastest when an agent confidently invents product details") could be trimmed, so it sits just below 5.

4 / 5

Actionability

Provides concrete, copy-paste-ready commands ("node <SKILL_DIR>/scripts/fetch-letta-docs.mjs", the "--docs-url" example) and specific URLs (Discord, GitHub issues, status page); the script file exists in the bundle. Minor abstraction like "Read the outline ... to pick the best page URL" keeps it from a 5.

4 / 5

Workflow Clarity

A clear numbered "Source route (in order)" with an explicit failure/fallback chain (direct fetch -> fetch_webpage fallback -> disclose unreachable) and hard rules; this is a read-only skill so the destructive/batch cap does not apply, but there is no true validate->fix->retry loop, holding it at 4 rather than 5.

4 / 5

Progressive Disclosure

Well-organized into clear sections (Source route, Hard rules, Support escalation, Caching) with a single one-level-deep bundle reference (scripts/fetch-letta-docs.mjs) that is real and clearly signaled; the Caching section inlines some helper internals that arguably belong in the script, a minor organization gap versus 5.

4 / 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, explicit description that clearly states both capability and trigger conditions with comprehensive, natural keyword coverage and a distinct Letta-specific niche. The only minor weakness is that the action vocabulary is narrow (read/fetch) even though the topical coverage is broad.

DimensionReasoningScore

Specificity

Names the concrete action ("Read the official Letta documentation ... through its cached, ETag-checked fetch route") plus a comprehensive list of covered topics (providers, models, channels, skills, memory, schedules, permissions, self-hosting, pricing, billing, API, Agent SDK, Letta Code), but the underlying verbs are few (read/fetch), leaving minor coverage gaps versus a 5.

4 / 5

Completeness

Explicitly answers both what ("Read the official Letta documentation ... through its cached, ETag-checked fetch route") and when ("Load before ANY docs.letta.com retrieval — answering ... AND looking up ... while writing code") with concrete trigger phrases, matching the 5 anchor.

5 / 5

Trigger Term Quality

Natural trigger phrases users would say are well covered ("answering how Letta works", "setting up providers, models, channels", "pricing, or billing", "looking up Letta API, Agent SDK, or Letta Code reference while writing code", "docs.letta.com"), with good synonym coverage; a few colloquial variants (e.g. "Letta docs") are absent, keeping it just below 5.

4 / 5

Distinctiveness Conflict Risk

A clear Letta-only niche with distinct triggers (docs.letta.com, Letta API/Agent SDK/Letta Code) and an explicit disambiguator ("Do not use fetch_webpage or web_search on docs.letta.com"), giving minimal conflict risk with other skills.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
letta-ai/letta-code
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.