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

75%

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

88%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.

The body is a strong, highly actionable workflow with explicit validation and feedback loops, executable code/commands, and a mandatory verification report. Main improvement is mild conciseness trimming and potentially splitting the large lookup tables into a reference file.

Suggestions

Trim redundancy between 'Hard rules', 'Your Task', and 'Anti-patterns' — several points (live-fetch-or-refuse, two-source pricing, hosted-billing risk) are restated two or three times.

Consider moving the provider URL lookup table and Consumption Matrix into a references/ file (e.g. PROVIDERS.md, CAPABILITY-MATRIX.md) and linking from SKILL.md to improve progressive disclosure toward 5.

The 'What to do if you cannot find a source' section overlaps heavily with Step 6 and the Hard rules; consolidate to a single source-of-truth block.

Dimension	Reasoning	Score
Conciseness	The body is dense but largely repo-specific knowledge Claude does not already know (consumption matrix, provider URLs, CI checks); it assumes competence and avoids explaining generic concepts, with only minor redundancy between Hard rules, Your Task, and Anti-patterns.	4 / 5
Actionability	Provides a copy-paste TS entry template, exact rg/bun commands, a precise WebFetch prompt, and a mandatory verification-report format — fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	Steps 1-6 are explicitly sequenced with validation checkpoints (lint must pass, two-source pricing rule, ask user on single-source/UNVERIFIED rows, agent-stream-docs:check) and feedback loops, so the destructive/batch cap does not apply.	5 / 5
Progressive Disclosure	No bundle files exist, so all content is inline, but it is well-organized into clear sections (Hard rules, Task, Steps 1-6, Anti-patterns); the consumption-matrix and provider-URL tables could arguably be split out but are tightly coupled to the workflow.	4 / 5
	Total	18 / 20 Passed

Description

62%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.

The description is concrete and highly distinct, naming a specific file and verification discipline, but it omits any explicit 'when to use' trigger guidance and has limited keyword variation. Adding a 'Use when...' clause would lift completeness and trigger-term quality.

Suggestions

Append a 'Use when...' clause, e.g. 'Use when adding or updating an LLM model entry in the providers catalog, or when the user asks to register a new model/provider spec.'

Broaden natural trigger terms to include synonyms users actually say ('register a model', 'add a provider model', 'update model pricing/specs', '.ts models entry').

Optionally list 2-3 concrete sub-actions (fetch live docs, cross-check pricing, insert entry matching sibling pattern) to push specificity from 4 toward 5.

Dimension	Reasoning	Score
Specificity	Names a concrete target file (apps/sim/providers/models.ts) and a concrete verification method (live API docs, no hallucination), but is essentially one primary action with a quality constraint rather than a list of several actions.	4 / 5
Completeness	The 'what' is explicit and specific, but there is no 'Use when...' or equivalent trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	The natural phrase 'Add a new LLM model' is present, but coverage is thin — no synonyms, file extensions, or common variations, and the rest is technical jargon (a repo path).	3 / 5
Distinctiveness Conflict Risk	The task is narrowly scoped to one codebase file and one operation, giving it a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	15 / 20 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: 981be93

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.