Name: stream-chain
Rating: 67.2 (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

51%

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

57%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 body is highly actionable with extensive executable commands but suffers from verbosity and a monolithic structure with no progressive disclosure into reference files. Batch/destructive pipelines also lack validation checkpoints, capping workflow clarity.

Suggestions

Move the pipeline catalog, custom-pipeline configuration, and 'Examples Repository' into separate reference files (e.g., PIPELINES.md, EXAMPLES.md) and link to them from SKILL.md to enable progressive disclosure.

Add an explicit verification/validation step to each destructive pipeline (refactor, optimize, migration) — e.g., 'Verify refactored code passes tests and preserves behavior' as a required final step.

De-duplicate the run and pipeline options tables and trim the 'Conclusion'/'Related Skills' sections to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	The 564-line body is noticeably verbose: the run/pipeline options tables are duplicated, and the 'Examples Repository' and 'Conclusion' sections restate patterns already shown earlier, adding padding without new information.	2 / 5
Actionability	Dozens of copy-paste-ready `claude-flow stream-chain` commands with concrete prompts cover the common cases (analysis, refactor, test, optimize, security, migration), matching the fully-executable anchor.	5 / 5
Workflow Clarity	Pipeline and chain steps are clearly sequenced, but batch/destructive pipelines (refactor, optimize, migration) lack built-in validation or verification checkpoints; the guideline caps workflow clarity at 3 for such operations.	3 / 5
Progressive Disclosure	No bundle files exist and the 564-line body is a monolith with good headers but everything inlined; content like the full pipeline catalog and example library clearly belongs in separate referenced files.	3 / 5
	Total	13 / 20 Passed

Description

45%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 states a clear purpose but lacks concrete actions, a 'Use when…' trigger clause, and distinctive triggers, leaving it at the midpoint across most dimensions. Adding explicit trigger phrases and naming specific operations would lift specificity and completeness.

Suggestions

Add a 'Use when…' clause naming concrete triggers (e.g., 'Use when chaining agent outputs into a pipeline, transforming data across steps, or running sequential multi-agent workflows').

Replace the abstract 'chaining' with concrete actions (e.g., 'Routes each agent's output into the next step, transforms data between stages, and runs predefined analysis/refactor/test pipelines').

Include natural synonyms users might say ('data pipelines', 'agent handoffs', 'step-by-step workflows') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('multi-agent pipelines, data transformation, and sequential workflows') but the only action verb ('chaining') is abstract — no concrete operations like extract, fill, or merge, matching the anchor for minimal/generic actions.	2 / 5
Completeness	A clear 'what' is stated but the 'when' is entirely missing — there is no 'Use when…' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the guideline.	3 / 5
Trigger Term Quality	Relevant keywords ('multi-agent pipelines', 'data transformation', 'sequential workflows') are present but common user variations and synonyms are missing, with no natural trigger phrases like 'Use when…'.	3 / 5
Distinctiveness Conflict Risk	'Stream-JSON chaining' is a somewhat specific niche, but the framing around 'multi-agent pipelines' and 'sequential workflows' overlaps with general orchestration/workflow skills, so conflict risk remains.	3 / 5
	Total	11 / 20 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: 74d2a60

Reviewed: 3 days 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.