adding-models

Guide for adding new LLM models to Letta Code. Use when the user wants to add support for a new model, needs to know valid model handles, or wants to update model-specific compatibility behavior. Covers runtime catalog sources, CI test matrices, and handle validation.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./.skills/adding-models/SKILL.md

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 skill body with concrete commands and a clear step sequence. It is held at 4 across the board by minor trim opportunities, a missing test-failure feedback loop, and the absence of any external reference split.

Suggestions

Add an explicit feedback loop under Step 3: describe what a failed headless test looks like and the fix-and-rerun path (e.g., verify the handle against the catalog query, re-run the bun command).

Tighten the Cloud-mode warning by replacing the GPT-4o narrative with a one-line rule ('Never use GET /v1/models hosted rows to filter or fall back for the hosted catalog') to lift conciseness.

Specify the exact jq filter for matching BYOK rows to catalog metadata in Step 1 so the BYOK guidance is fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Mostly lean and table/code-driven with relevant domain gotchas (the GPT-4o anecdote, catalog-source distinctions) rather than basic-concept padding; a few prose passages such as the narrative warning could be trimmed, so it sits at 4 rather than 5.	4 / 5
Actionability	Provides executable curl+jq queries, a bun run test command with a concrete example, and a ci.yml snippet pinpointed 'around line 122'; minor gaps (no exact jq path for the BYOK metadata match) keep it just below 5.	4 / 5
Workflow Clarity	Clear 4-step sequence with the headless test in Step 3 acting as a validation checkpoint, but there is no explicit pass/fail feedback loop describing what to do if the test fails.	4 / 5
Progressive Disclosure	Single self-contained file (no references/scripts/assets bundles exist) with well-organized sections and no nested references; at ~104 lines it exceeds the simple-skill threshold and contains a couple of dense tables, so it does not reach 5.	4 / 5
	Total	16 / 20 Passed

Description

83%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 explicitly covers both what the skill does and when to use it, with concrete trigger phrases and a well-scoped niche. It could push specificity and trigger coverage to the top anchor with a few more natural synonyms and action verbs.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ('add support for a new model', 'needs to know valid model handles', 'update model-specific compatibility behavior') plus coverage areas; falls short of 5 because the 'Guide for…' framing is declarative rather than a pure multi-action verb list.	4 / 5
Completeness	Explicitly states both what ('Guide for adding new LLM models… Covers runtime catalog sources, CI test matrices, and handle validation') and when with concrete triggers ('Use when the user wants to add support for a new model, needs to know valid model handles, or wants to update model-specific compatibility behavior').	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('add support for a new model', 'valid model handles'); a few common synonyms like 'supported models' or 'model list' are missing, keeping it below 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche ('adding new LLM models to Letta Code') with distinctive triggers ('valid model handles', 'model-specific compatibility behavior'); minor overlap risk with a generic model-configuration skill keeps it just below 5.	4 / 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: letta-ai/letta-code
Path: .skills/adding-models/SKILL.md
Commit: 7a4337e

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.