CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

72

Quality

90%

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

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

SKILL.md
Quality
Evals
Security

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.

A highly actionable, well-sequenced procedural skill with copy-paste code and explicit per-step validation checkpoints. It is concise for its density, though some content (Examples, Common Issues) is inlined rather than split into reference files.

DimensionReasoningScore

Conciseness

Dense and assumes TypeScript/interface competence without padding; however the Common Issues section repeats guidance already in the Critical section (trackUsage, model param), so minor trimming is possible.

4 / 5

Actionability

Provides a full copy-paste class implementation, exact edit locations (line numbers), and executable verification commands ('npx tsc --noEmit', 'npm run test -- src/llm/__tests__/...') covering the common cases.

5 / 5

Workflow Clarity

Steps 1-7 are clearly sequenced and each ends with an explicit 'Verify:' checkpoint, while the Common Issues section supplies feedback loops for error recovery (e.g. 'Unknown provider' cause/fix).

5 / 5

Progressive Disclosure

Well-organized into Critical, Instructions, Examples, and Common Issues sections with no nested references, but everything (~240 lines) is inlined in a single file with no bundle files or one-level-deep references that could offload the Examples/Common Issues detail.

4 / 5

Total

18

/

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, third-person description that explicitly states capabilities, trigger conditions, and exclusions. Concrete method names and file anchors make it highly specific and distinct from neighboring skills.

DimensionReasoningScore

Specificity

Names concrete actions — 'implementing LLMProvider interface with call() and stream() methods', 'provider factory', 'config detection', 'error handling via tracking and recovery' — but 'tracking and recovery' is slightly abstract, leaving minor gaps vs the comprehensive anchor 5.

4 / 5

Completeness

Explicitly answers both what ('Adds a new LLM provider implementing LLMProvider interface with call() and stream() methods') and when ('Use when adding a new model backend...'), with concrete trigger phrases.

5 / 5

Trigger Term Quality

'Use when adding a new model backend, integrating a third-party LLM API, or extending LLM platform support' gives good natural-term coverage, though a few common variations (e.g. 'LLM integration', 'new API provider') are missing.

4 / 5

Distinctiveness Conflict Risk

A clear niche (adding new providers) with explicit negative boundary — 'Do NOT use for fixing bugs in existing providers, modifying existing provider behavior, or changing the LLMProvider interface' — minimizes conflict risk.

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
caliber-ai-org/ai-setup
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.