stream-chain

Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows

1.00x

Quality

30%

Does it follow best practices?

Impact

100%

1.00x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/stream-chain/SKILL.md

Quality

Discovery

32%

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 specific technology domain (Stream-JSON) and lists high-level use cases, but remains too abstract to clearly communicate concrete capabilities. It completely lacks a 'Use when...' clause, making it difficult for Claude to know when to select this skill. The terms used are more technical jargon than natural user language.

Suggestions

Add an explicit 'Use when...' clause with trigger scenarios, e.g., 'Use when the user needs to chain JSON-based operations, build multi-step agent pipelines, or stream structured data between processing stages.'

List specific concrete actions instead of abstract categories, e.g., 'Chains Stream-JSON operations to pipe structured data between agents, transform JSON payloads between pipeline stages, and orchestrate sequential multi-step workflows.'

Include natural user-facing keywords and file/format references like 'JSON streaming', '.json', 'pipeline orchestration', 'agent chaining' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (Stream-JSON, multi-agent pipelines) and some actions (chaining, data transformation, sequential workflows), but these are fairly abstract and don't list concrete specific actions like 'parse JSON streams', 'route messages between agents', etc.	2 / 3
Completeness	Provides a partial 'what' (chaining for pipelines, transformation, workflows) but completely lacks any 'when' clause or explicit trigger guidance. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also weak, so this scores a 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'multi-agent pipelines', 'data transformation', 'sequential workflows', and 'Stream-JSON', but these are somewhat technical. Missing common user-facing terms like 'JSON streaming', 'pipe data', 'chain tasks', or 'workflow automation'.	2 / 3
Distinctiveness Conflict Risk	'Stream-JSON' is somewhat distinctive as a specific technology/format, but 'data transformation' and 'sequential workflows' are very broad terms that could overlap with many other skills involving data processing or workflow orchestration.	2 / 3
	Total	7 / 12 Passed

Implementation

27%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is excessively verbose, repeating the same pattern (passing sequential prompts to a CLI) dozens of times with minor variations. While the CLI syntax is concrete and copy-paste ready, the document lacks validation/error-recovery workflows and is entirely monolithic despite being long enough to warrant splitting into multiple files. The content could be reduced by 70%+ while improving clarity.

Suggestions

Reduce to ~80-100 lines: keep Quick Start, one custom chain example, the pipeline list with one-line descriptions, the config JSON format, and key options. Move detailed examples and use cases to a separate EXAMPLES.md.

Add validation and error-recovery steps: what does a failed step look like? How do you retry a single step? What happens to context when a step fails? These are critical for a multi-step pipeline tool.

Split content into separate files: PIPELINES.md for detailed pipeline descriptions, EXAMPLES.md for the examples repository, and keep SKILL.md as a concise overview with clear links.

Remove the Conclusion section, Performance Characteristics (unverifiable claims), and redundant examples that all demonstrate the same CLI pattern with different prompt strings.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~350+ lines. Massive redundancy: the same concept (chaining prompts) is shown in dozens of near-identical examples. Sections like 'Conclusion', 'Performance Characteristics', 'Related Skills', and extensive 'Use Cases' bullet lists add little value. Explains obvious concepts like what sequential processing means. The entire document could be reduced to ~80 lines without losing actionable content.	1 / 3
Actionability	Provides concrete CLI commands that are copy-paste ready, which is good. However, the commands are all variations of the same pattern (passing string prompts), and there's no executable code showing how to programmatically interact with the system, handle errors, or process outputs. The JSON config example is concrete but untestable without knowing the tool's actual behavior. Many examples are aspirational rather than verified.	2 / 3
Workflow Clarity	Pipeline steps are listed clearly (e.g., 1. Structure Analysis, 2. Issue Detection, 3. Recommendations), and the context flow diagram is helpful. However, there are no validation checkpoints or feedback loops for error recovery. The troubleshooting section is minimal and reactive rather than integrated into workflows. For a tool that chains multiple agent steps with potential failures at each stage, missing validation/retry guidance is a significant gap.	2 / 3
Progressive Disclosure	Monolithic wall of text with no bundle files to reference. Everything is inlined in a single massive document. The 'Related Skills' section references other skills but provides no links. Content like the full predefined pipeline descriptions, advanced use cases, and examples repository could easily be split into separate files. The document would benefit enormously from being an overview that points to detailed references.	1 / 3
	Total	6 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (564 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: ruvnet/ruvector
Commit: c2089c4

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.