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

61%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.

The content is well-structured and dense with concrete configuration detail, but it stops short of executable code and omits validation checkpoints for its batch/embedding operations. It reads as a capable reference overview rather than a runbook.

Suggestions

Add one short executable snippet for the core pipeline (extract -> chunk -> embed) so the guidance is copy-paste ready.

Insert an explicit validation/verification step in the RAG pipeline (e.g. check chunk count, confirm embedding dimensions, verify non-empty vectors) before the 'Output' step.

Tighten the 'Critical Rules' section to avoid restating strategy/preset detail already covered above.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient — tables and bullet lists convey config fields, presets, and models compactly — with only minor restatement between the strategy/preset sections and the 'Critical Rules' list.	4 / 5
Actionability	It gives concrete field names, presets, model identifiers, and install commands, but provides no executable code (only struct-field references and prose patterns), leaving the actual call sites to be inferred.	3 / 5
Workflow Clarity	The four-step Extract->Chunk->Embed->Output pipeline is clearly sequenced, but batch and ingestion operations lack any validation/verification checkpoint, which caps workflow clarity at 3 for batch/destructive work.	3 / 5
Progressive Disclosure	Sections are well-organized with clearly signaled 'Location' pointers and a Related Skills list; content is appropriately partitioned inline, and no bundle files are needed for a skill of this size, leaving only minor organization gaps.	4 / 5
	Total	14 / 20 Passed

Description

53%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.

The description identifies a coherent technical niche but reads as a topic list rather than a capability statement, omitting action verbs and any explicit trigger guidance. It is serviceable but would benefit from naming concrete actions and a 'Use when...' clause.

Suggestions

Add explicit action verbs, e.g. 'Split text into chunks, generate embeddings with FastEmbed, and wire them into a RAG pipeline.'

Append a 'Use when...' clause naming natural user triggers like 'text splitting', 'vector search', 'semantic search', or 'building a RAG pipeline'.

Add common synonyms/file references (e.g. 'embeddings', 'vector store ingestion') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names three concrete domains ('Chunking, embeddings, and RAG pipeline integration') but uses no action verbs, leaving the actual operations unspecified — more concrete than a single generic noun but not a list of specific actions.	3 / 5
Completeness	The 'what' is present (chunking, embeddings, RAG integration) but there is no 'Use when...' or equivalent explicit 'when' trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	'chunking', 'embeddings', and 'RAG' are relevant domain terms, but natural user phrasings and synonyms (e.g. 'text splitting', 'vector search', 'semantic search') are missing.	3 / 5
Distinctiveness Conflict Risk	'RAG pipeline integration' anchors a clear niche distinct from generic extraction skills, though 'chunking'/'embeddings' could overlap with adjacent pipeline skills, giving minor conflict risk.	4 / 5
	Total	13 / 20 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: 0a60357

Reviewed: about 12 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.