chunking-embeddings

Chunking, embeddings, and RAG pipeline integration

Quality

57%

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

Fix and improve this skill with Tessl

tessl review fix ./.ai-rulez/skills/chunking-embeddings/SKILL.md

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 a dense, well-structured reference with strong concrete pointers and copy-paste commands, but it stops short of a complete executable example, omits validation checkpoints in its pipeline, and keeps all content inline with no progressive disclosure to reference files. It is solid but could be tightened into a runnable workflow plus split-out details.

Suggestions

Add one complete, runnable end-to-end example (e.g. a Rust snippet calling extract -> chunk -> embed_chunks) so the pipeline is copy-paste executable.

Insert explicit validation checkpoints in the RAG pipeline (e.g. verify ONNX Runtime loaded, verify non-empty chunks before embedding, confirm embedding dimensions) with a fix-and-retry loop.

Move the model-selection and preset tables into a reference file (e.g. references/embedding-models.md) referenced one level deep from the overview to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is a lean reference of tables, file paths, config fields, and model IDs that assumes Claude's competence and avoids explaining what chunking/RAG/embeddings are, so every token largely earns its place.	3 / 3
Actionability	It gives concrete file locations, copy-paste install commands, a TOML feature block, presets, and real function signatures, but there is no complete end-to-end executable code example; the pipeline is shown via signatures rather than runnable code.	2 / 3
Workflow Clarity	The RAG Integration Pattern is a clear 4-step sequence (Extract, Chunk, Embed, Output), but it lacks explicit validation checkpoints for the batch embedding operation, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Sections are well organized, but the ~110-line body is monolithic with no bundle files or one-level-deep reference splits, so content that could be separated (model/preset tables) is inline rather than progressively disclosed.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 a concise noun phrase that clearly identifies its domain but omits any verb-based actions and any explicit "when to use" trigger. It is competent but generic in form. Adding concrete actions and a "Use when..." clause would raise specificity, completeness, and trigger quality.

Suggestions

Add concrete verbs/actions, e.g. "Splits text into chunks, generates embeddings with FastEmbed, and integrates into RAG pipelines."

Append an explicit trigger clause: "Use when building RAG pipelines, generating vector embeddings, or chunking documents for retrieval."

Include natural keyword variations like "text splitting", "vector search", and "semantic search" to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The phrase names a concrete domain ("Chunking, embeddings, and RAG pipeline integration") but uses no verb actions, only nominal terms, so it names the domain and some implied actions without being comprehensive.	2 / 3
Completeness	It conveys what the skill does but has no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	"chunking", "embeddings", and "RAG" are relevant keywords a technical user might say, but common variations (text splitting, vector search, semantic search) and explicit trigger phrasing are missing.	2 / 3
Distinctiveness Conflict Risk	The RAG/chunking/embeddings niche is fairly distinct, but without explicit distinct triggers it could still overlap with broader RAG or vector-DB skills.	2 / 3
	Total	8 / 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: xberg-io/xberg
Path: .ai-rulez/skills/chunking-embeddings/SKILL.md
Commit: db74878

Reviewed: 1 day 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.