pinme-llm

Use this skill when a PinMe project (Worker TypeScript) needs to call OpenRouter-backed LLM APIs, including models, chat/completions, streaming, or OpenRouter web search. Guides AI to generate correct Worker TS code.

Quality

88%

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

Quality

Content

77%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.

The content is highly actionable with executable code and a clear error model, and the per-call workflow is well sequenced. It is somewhat verbose due to repeated boilerplate and overlapping examples, and the ~350-line monolith could benefit from splitting reference detail into a bundle file.

Suggestions

Consolidate the repeated baseUrl/auth-header boilerplate and the overlapping callLLM, callOpenRouterJSON, and usage examples into a single canonical pattern to reduce redundancy.

Move the detailed HTTP error table and full worker example code into a references/ file (e.g. REFERENCE.md) so SKILL.md stays a lean overview, improving progressive disclosure.

Keep the extractPinmeOpenRouterError helper as the single error-handling reference and have the streaming and frontend consumer examples reference it rather than re-stating the pattern.

Dimension	Reasoning	Score
Conciseness	The body is dense with executable code and concrete error tables with no concept over-explanation, but it includes redundant boilerplate (the baseUrl default and auth header block repeat across several snippets) and overlapping full examples (callLLM, callOpenRouterJSON, and the usage example) that could be tightened.	2 / 3
Actionability	Provides complete, copy-paste-ready TypeScript functions (listModels, callLLM, handleChatStream, extractPinmeOpenRouterError, callOpenRouterJSON) with specific endpoints, auth headers, and a full HTTP error table.	3 / 3
Workflow Clarity	Each endpoint section follows a clear fetch -> resp.ok check -> error-extract / parse sequence, with an explicit layered error-recovery fallback in extractPinmeOpenRouterError; the single-action per-call flow is unambiguous.	3 / 3
Progressive Disclosure	The skill is a single ~350-line monolithic file with no bundle files; section headers organize it well, but substantial reference detail and full example code are inline where a separate reference file could reduce SKILL.md size.	2 / 3
	Total	10 / 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.

The description is specific, uses natural trigger terms, and clearly states both what the skill does and when to use it, with a distinct, low-conflict niche. Third-person voice is used throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("models, chat/completions, streaming, or OpenRouter web search" and "generate correct Worker TS code") rather than vague language, matching the score-3 anchor.	3 / 3
Completeness	Explicitly answers both what (call OpenRouter-backed LLM APIs, generate Worker TS code) and when via the clear "Use this skill when a PinMe project... needs to call..." trigger clause.	3 / 3
Trigger Term Quality	Includes natural terms a developer would actually say ("OpenRouter-backed LLM APIs", "chat/completions", "streaming", "web search", "Worker TypeScript"), giving good coverage of likely trigger phrases.	3 / 3
Distinctiveness Conflict Risk	Tightly scoped to the PinMe platform's OpenRouter proxy in Worker TypeScript, a clear niche unlikely to trigger for unrelated skills.	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: glitternetwork/pinme
Path: skills/pinme-llm/SKILL.md
Commit: 7822b05

Reviewed: 25 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.