Name: stream-chain
Rating: 71.2 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

stream-chain

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

1.00x

Quality

57%

Does it follow best practices?

Impact

100%

1.00x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/stream-chain/SKILL.md

The canonical home for this skill is stream-chain in ruvnet/agentic-flow

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 content is highly actionable with abundant executable commands and examples, but it is verbose and repetitive across ~555 lines, lacks explicit validation checkpoints in the chain workflow, and is monolithic with no progressive disclosure into bundle files.

Suggestions

Cut redundant content: the run syntax, option tables, and example chains each appear multiple times; consolidate to one canonical example per concept and remove the restating 'Examples Repository' and 'Conclusion' sections.

Add an explicit validation/retry checkpoint pattern for chain execution (e.g., check each step's exit status and re-run or debug on failure) rather than leaving verification as an optional user-added prompt.

Split the large pipeline catalog and examples into separate reference files (e.g., PIPELINES.md, EXAMPLES.md) and link to them from a concise overview to enable progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is accurate and avoids explaining basics Claude already knows, but at ~555 lines it is heavily padded: the run syntax, option tables, and example chains recur multiple times, and the 'Examples Repository' and 'Conclusion' restate material already shown.	2 / 3
Actionability	It provides many concrete, copy-pasteable `claude-flow stream-chain run ...` commands with real prompts, full option/defaults tables, a worked context-flow diagram, and a complete custom-pipeline config JSON example.	3 / 3
Workflow Clarity	Multi-step chains are clearly sequenced and the 'How Context Flows' section shows data propagation, but there are no explicit validation checkpoints or error-recovery feedback loops in the execution path; verification is only suggested as an optional user-added prompt.	2 / 3
Progressive Disclosure	There are no bundle files and the skill is a single 555-line monolithic document; while headers organize it well, content such as the pipeline catalog and examples repository is inline that could be split into separate referenced files.	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 clear, third-person noun phrase that names its domain, but it lacks explicit action verbs and any 'Use when...' trigger, leaving the 'when to use it' implicit. Trigger terms are partly natural but include jargon and could overlap with orchestration skills.

Suggestions

Lead with concrete action verbs (e.g., 'Execute, chain, and orchestrate multi-agent prompt pipelines...') instead of a pure noun phrase.

Add an explicit 'Use when...' clause naming natural triggers a user would say (e.g., 'Use when you need to chain agent outputs into a pipeline, run sequential multi-step workflows, or transform data across stages').

Replace jargon like 'Stream-JSON chaining' with phrasing users naturally say to reduce overlap with generic orchestration/swarm skills.

Dimension	Reasoning	Score
Specificity	Names a concrete domain ('Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows') but is a noun phrase with no explicit verbs describing the actions the skill performs, so it falls short of listing multiple concrete actions.	2 / 3
Completeness	It states what the skill does but contains no 'Use when...' clause or equivalent explicit trigger guidance, so the 'when' is missing rather than stated.	2 / 3
Trigger Term Quality	'multi-agent pipelines', 'data transformation', and 'sequential workflows' are reasonable terms, but 'Stream-JSON chaining' is technical jargon a user would rarely say, and common variations like 'pipeline', 'workflow', or 'chain agents' are only partially covered.	2 / 3
Distinctiveness Conflict Risk	The streaming/chaining niche is somewhat specific, but 'multi-agent pipelines' and 'sequential workflows' overlap broadly with general orchestration and swarm skills, so conflict risk remains.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 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	14 / 16 Passed

Repository: ruvnet/ruvector
Path: .claude/skills/stream-chain/SKILL.md
Commit: 6a6c39e

Reviewed: about 13 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.