Tessl • The management layer for AI agent skills

SkillPublic

chunking-strategy

Provides optimal chunking strategies in RAG systems and document processing pipelines. Use when building retrieval-augmented generation systems, vector databases, or processing large documents that require breaking into semantically meaningful segments for embeddings and search.

Quality

78%

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 ./plugins/developer-kit-ai/skills/chunking-strategy/SKILL.md

The canonical home for this skill is giuseppe-trisciuoglio/developer-kit

Quality

Content

65%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 well-structured skill with strong progressive disclosure (verified reference files) and solid executable examples. The main weaknesses are repetitive best-practice sections that restate known tradeoffs and a validation workflow that stays conceptual rather than providing an executable verify-fix-retry loop.

Suggestions

Trim 'Best Practices > Core Principles' and 'Constraints and Warnings' to remove guidance already implied by the strategy levels and known to Claude, restoring token efficiency.

Replace the high-level 'Validate semantic coherence of chunks' step with a concrete, runnable validation command or code snippet plus an if-fail-then-retry loop.

Define or inline the helper functions used in the semantic-chunking example (split_into_sentences, generate_embeddings) so the example is fully executable.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tight strategy descriptions, but sections like 'Best Practices > Core Principles' and 'Constraints and Warnings' repeat guidance already covered in the instructions and overlap with what Claude already knows about chunking tradeoffs.	3 / 5
Actionability	Three concrete, executable Python examples cover common cases and parameters (chunk_size, similarity_threshold) are specified; minor gaps such as undefined helper functions (split_into_sentences, generate_embeddings) keep it from fully copy-paste ready.	4 / 5
Workflow Clarity	The pipeline lists sequenced steps (pre-process, select parameters, process and validate, evaluate) with an explicit validation step, but it is a batch/destructive-adjacent operation and the validation/checkpoint guidance is high-level ('Validate semantic coherence') rather than an executable verify-then-proceed feedback loop, capping it at 3.	3 / 5
Progressive Disclosure	SKILL.md is a concise overview with well-signaled, one-level-deep markdown links to eight real reference files (all verified present), with clear per-file annotations in the References section enabling easy navigation.	5 / 5
	Total	15 / 20 Passed

Description

83%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 clear, third-person description that covers both what the skill does and when to use it, with concrete RAG-specific trigger terms. Minor gaps in action enumeration and synonym coverage keep it just below perfect.

Suggestions

List 3-4 discrete concrete actions (e.g., 'split, segment, and embed documents') instead of a single capability phrase to lift specificity.

Add common synonyms and concrete triggers like 'embeddings pipeline', 'text splitting', or specific file types users mention.

Dimension	Reasoning	Score
Specificity	Names the domain (RAG, document processing) and several concrete actions ('chunking strategies', 'breaking large documents', 'semantically meaningful segments', 'embeddings and search'), though phrased more as capability than a tight list of discrete actions.	4 / 5
Completeness	Explicitly answers 'what' ('Provides optimal chunking strategies...') and 'when' ('Use when building retrieval-augmented generation systems, vector databases, or processing large documents...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases ('retrieval-augmented generation', 'RAG systems', 'vector databases', 'processing large documents') but omits common synonyms/extensions like 'embeddings pipeline' or file-type triggers.	4 / 5
Distinctiveness Conflict Risk	RAG/chunking niche is fairly distinct and unlikely to fire for unrelated skills, but the broad 'processing large documents' framing has minor overlap with general document-handling skills.	4 / 5
	Total	17 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/developer-kit
Path: plugins/developer-kit-ai/skills/chunking-strategy/SKILL.md
Revision: 810297c

Reviewed: 24 days ago

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.

chunking-strategy

Table of Contents

Is this your skill?