add-model

Add a new LLM model to apps/sim/providers/models.ts with specs verified against the provider's live API docs (no hallucination)

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/add-model/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a well-sequenced, validation-rich workflow tailored to this codebase. Its main weaknesses are mild redundancy between the hard rules and anti-patterns, and a monolithic single-file structure that could benefit from reference files.

Suggestions

Move the Consumption Matrix and provider-doc URL table into a reference file (e.g. references/consumption-matrix.md) and link to it, keeping SKILL.md as a lean overview.

Trim the 'Anti-patterns' section or fold it into the relevant steps to remove overlap with the 'Hard rules' block.

Consider extracting the verification-report template into a references file so the workflow step stays concise.

Dimension	Reasoning	Score
Conciseness	The body is dense with codebase-specific knowledge and avoids explaining general concepts, but the 'Anti-patterns' section recaps the hard rules and some guidance repeats across 'Hard rules' and the later steps, so it could be tightened.	2 / 3
Actionability	It provides an executable TS entry template, concrete `rg` grep commands, an exact WebFetch prompt, a provider-doc URL table, and a copy-paste verification report format.	3 / 3
Workflow Clarity	Six steps are clearly sequenced with explicit validation checkpoints and feedback loops: lint-fail→fix→rerun, two-source pricing cross-check, and ask-the-user before proceeding on any unverified field.	3 / 3
Progressive Disclosure	All content lives in one ~223-line SKILL.md with no reference files; sections are well-organized but the Consumption Matrix, provider URL table, and anti-patterns could be split into separate reference files for a clearer overview.	2 / 3
	Total	10 / 12 Passed

Description

57%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concrete and clearly distinct, but it omits an explicit 'when to use' trigger clause and lists only one primary action. Adding trigger phrasing and a couple of natural variations would lift the weaker dimensions.

Suggestions

Append a 'Use when...' trigger clause, e.g. 'Use when adding or registering a new LLM model in models.ts, or when the user asks to add a provider model with verified pricing/specs.'

Include natural trigger variations users might say ('add a model', 'register a new LLM', 'add pricing for a model') to improve trigger-term coverage.

Optionally surface one more concrete action (e.g. 'set capability flags the provider actually consumes') to reach multiple specific actions.

Dimension	Reasoning	Score
Specificity	It names one concrete action with a precise target ('Add a new LLM model to apps/sim/providers/models.ts') plus a verification method, but does not list multiple distinct concrete actions as the anchor-3 example does.	2 / 3
Completeness	It clearly states what the skill does but lacks any 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	'Add a new LLM model' and 'provider' are natural terms a user would say, but the method clause ('specs verified against the provider's live API docs (no hallucination)') is technical and no common variations are covered.	2 / 3
Distinctiveness Conflict Risk	The description targets a specific codebase file and a verification-backed task, giving it a clear niche unlikely to trigger the wrong skill.	3 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: simstudioai/sim
Path: .agents/skills/add-model/SKILL.md
Commit: 6f514c1

Reviewed: about 16 hours 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.