CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

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-built operational skill: executable commands dominate, the workflow is sequenced with a real verification step, and troubleshooting is included. The main gaps are the abstract Step 2 guidance (changes live outside this repo) and the undefined 'validation script' referenced in Common Issues.

Suggestions

Name or inline the 'validation script' referenced in Common Issues, or replace that mention with the concrete curl command that lists valid handles.

Give Step 2 a concrete checkpoint or example of where a hosted preset or pi-ai model entry lives, even though the change is server-side, so the step is actionable rather than purely directional.

Consider moving the agent-source catalog table and provider-prefix list into a references/ file to keep SKILL.md a lean overview with one-level-deep pointers.

DimensionReasoningScore

Conciseness

The body is dense and command-first with almost no padding of concepts Claude already knows, but a few sentences could be trimmed ('These inputs are deliberately different:' preamble, the GPT-4o selector anecdote), matching the 'efficient with minor over-explanation' anchor 4 rather than the lean anchor 5.

4 / 5

Actionability

Mostly copy-paste-ready: concrete curl|jq queries, a real headless test command with an example model, and a CI matrix snippet with a line-number hint. Falls short of 5 because Step 2 offers only abstract direction ('Add the model at the source that owns it') and Common Issues references an unnamed 'validation script' with no path or command.

4 / 5

Workflow Clarity

Four clearly sequenced steps with an explicit verification checkpoint in Step 3 (headless smoke-test prompt) and error-recovery guidance in Common Issues. Not a destructive or batch operation, so no cap applies; it misses anchor 5 only because Step 2 lacks a concrete checkpoint.

4 / 5

Progressive Disclosure

The single self-contained body is well organized (Quick Reference, Workflow, Toolset Detection, Common Issues) with a key-files map into the repo. It sits at anchor 4 rather than 5 because the agent-source catalog table and provider-prefix detail are inline reference material that could be split into a separate file, and no one-level-deep reference files exist.

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 description: third-person, concise, with an explicit multi-clause 'Use when...' trigger and a concrete coverage list. Only weakness is a few missing natural synonyms and coverage of the body's toolset-detection topic.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('add support for a new model', 'update model-specific compatibility behavior', 'runtime catalog sources, CI test matrices, and handle validation') but omits areas the body covers, such as toolset selection, leaving minor gaps that fall short of the comprehensive anchor 5.

4 / 5

Completeness

Explicitly answers both: the what ('Guide for adding new LLM models to Letta Code... Covers runtime catalog sources, CI test matrices, and handle validation') and the when ('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') with three concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases like 'add support for a new model' and 'valid model handles' match what a user would actually say, but common synonyms such as 'model ID', 'new provider', or 'model list' are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

A clear niche is staked out ('adding new LLM models to Letta Code') with distinct triggers like 'model handles' and 'model-specific compatibility behavior', making it unlikely to fire for unrelated 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.

Validation — 16 / 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.