pinecone

Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

65%

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 comprehensive executable code, but it over-inlines content that should live in the existing reference, never signals that reference, and adds redundant padding. Destructive and batch operations lack validation checkpoints.

Suggestions

Link references/deployment.md from the body (e.g., a '## Deployment' section pointing to it) and move the duplicated hybrid/namespaces/filtering deep-dives out of SKILL.md to remove the overlap.

Add validation/verification steps before destructive and batch operations — e.g., confirm index stats or required IDs before `index.delete(delete_all=True)` and `pc.delete_index()`, with a re-check after batch upserts.

Trim redundant padding (the 'When to use' list that restates the description, and the Performance/Pricing tables) to tighten the token budget.

Dimension	Reasoning	Score
Conciseness	Mostly code-first and efficient, but the 'When to use' section restates the description, the 10-item 'Best practices' plus Performance/Pricing tables add padding Claude largely knows or could fetch, and references/deployment.md duplicates hybrid/namespaces/filtering content already inlined in the body.	2 / 3
Actionability	Provides fully executable, copy-paste-ready Python for every core operation (init, create index, upsert, query, filtering, namespaces, hybrid, LangChain/LlamaIndex, management, deletion) with real SDK calls and parameters, matching the executable-code anchor.	3 / 3
Workflow Clarity	Content is organized as independent reference operations rather than a sequenced workflow, and destructive/batch operations (delete_all, delete_index, batch upsert) carry no validation or verify-before-destroy checkpoints, which caps this dimension at 2 per the rubric.	2 / 3
Progressive Disclosure	A bundle file exists (references/deployment.md) but the body never links to it, and deployment/hybrid/namespace/filtering detail that belongs in a separate file is inlined instead, with the reference largely duplicating the body — matching the anchor for unsignaled references and content that should be separate kept inline.	2 / 3
	Total	9 / 12 Passed

Description

100%

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: concise, third-person, concrete capabilities, with an explicit 'Use for' trigger clause covering what and when. No vague fluff; it earns top marks across all four dimensions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities ("hybrid search (dense + sparse)", "metadata filtering", "namespaces", "auto-scaling"), matching the anchor for listing several specific actions rather than naming only a domain.	3 / 3
Completeness	Explicitly states what ("Managed vector database ... hybrid search ... metadata filtering, and namespaces") and when ("Use for production RAG, recommendation systems, or semantic search at scale"), satisfying both halves with an explicit trigger clause.	3 / 3
Trigger Term Quality	Includes natural terms a user would say ("production RAG", "recommendation systems", "semantic search at scale", "serverless") with good coverage rather than jargon-only phrasing.	3 / 3
Distinctiveness Conflict Risk	"Managed vector database" with RAG/recommendation/semantic-search triggers carves a clear niche unlikely to collide with other skills, matching the clear-niche anchor.	3 / 3
	Total	12 / 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: OpenLAIR/dr-claw
Path: skills/rag/pinecone/SKILL.md
Commit: 6da7f7c

Reviewed: about 7 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.