Name: llm-provider
Rating: 77.60000000000001 (1 reviews)
Author: caliber-ai-org

llm-provider

Adds a new LLM provider implementing LLMProvider interface with call() and stream() methods. Integrates with provider factory in src/llm/index.ts, config detection in src/llm/config.ts, and error handling via tracking and recovery. Use when adding a new model backend, integrating a third-party LLM API, or extending LLM platform support. Do NOT use for fixing bugs in existing providers, modifying existing provider behavior, or changing the LLMProvider interface.

Quality

96%

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

The canonical home for this skill is llm-provider in caliber-ai-org/ai-setup

Quality

Content

92%Weight 40%Scale 1-3

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

Highly actionable and well-sequenced content with strong validation checkpoints, written for a competent reader. The only gap is progressive disclosure: everything lives in one large file that could offload examples and the full code template to reference files.

Suggestions

Move the full provider class code template and the Examples section into reference files (e.g. references/template.ts, references/examples.md) and link to them one level deep, leaving SKILL.md as a tighter overview.

Split Common Issues into a reference doc and keep only the highest-frequency pitfalls inline to reduce SKILL.md length.

Add a short 'When to follow each step' note so Claude can skip steps that don't apply to its provider type (e.g. seat-based vs API-key providers) without reading every step.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence with no concept primers, and packs concrete code, specific file:line pointers, and terse cause/fix entries. For a genuinely complex multi-file integration the length is justified and every section earns its place rather than padding.	3 / 3
Actionability	Provides fully executable TypeScript class templates with imports and signatures, copy-paste-ready switch cases, concrete commands ('npx tsc --noEmit', 'npm run test'), and precise insertion points (Line 9, Line 17, Line 59, Line 115).	3 / 3
Workflow Clarity	Seven clearly sequenced Steps each followed by an explicit 'Verify:' checkpoint (typecheck/test commands), with a lock-step warning in Critical and a Common Issues feedback section for error recovery.	3 / 3
Progressive Disclosure	No bundle files exist and the whole skill is a single ~240-line SKILL.md; full code templates, Examples, and Common Issues are all inline rather than split into one-level-deep references, which the rubric treats as 'content that should be separate is inline'.	2 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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: concrete actions, natural trigger terms, explicit what/when guidance, and a negative-scope clause that sharply bounds the skill. It is written in third person and is concise rather than padded.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'implementing LLMProvider interface with call() and stream() methods' and 'Integrates with provider factory in src/llm/index.ts, config detection in src/llm/config.ts', naming specific files and methods rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Adds a new LLM provider...') and when ('Use when adding a new model backend...'), plus a 'Do NOT use for...' negative-scope clause, satisfying both halves with explicit triggers.	3 / 3
Trigger Term Quality	Natural trigger phrases users would say are present: 'adding a new model backend', 'integrating a third-party LLM API', 'extending LLM platform support', with good coverage of the common ways such a request would be phrased.	3 / 3
Distinctiveness Conflict Risk	Has a clear niche (adding a NEW provider) and an explicit exclusion list ('Do NOT use for fixing bugs in existing providers, modifying existing provider behavior, or changing the LLMProvider interface'), making it unlikely to trigger for adjacent tasks.	3 / 3
	Total	12 / 12 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: caliber-ai-org/ai-setup
Path: .agents/skills/llm-provider/SKILL.md
Commit: 7950921

Reviewed: 12 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.