stream-chain

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

Quality

48%

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 ./.agents/skills/stream-chain/SKILL.md

Quality

Content

52%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 strong on concrete, executable commands and clear context-flow explanation, but it is heavily padded with triplicated examples and filler sections, and it crams everything into one file instead of splitting examples and config references into bundle files. Corrupted '$'-for-'/' characters in several paths also hurt accuracy.

Suggestions

Cut the duplicated 'Pipeline Examples', 'Examples Repository', and 'Conclusion' sections — each repeats commands already shown in the syntax sections — and trim 'Performance Characteristics'/'Related Skills' filler.

Split the example collections and the custom-pipeline JSON definitions into reference files (e.g., references/examples.md, references/pipelines.json) with clearly signaled one-level-deep links from SKILL.md.

Fix the corrupted separators ('.claude-flow$config.json', 'Success$failure', 'critical$high$medium$low', '.claude-flow$memory$stream-chain/') so paths and value lists are actually correct, and add a brief checkpoint step for inspecting per-step success before proceeding.

Dimension	Reasoning	Score
Conciseness	The ~560-line body is noticeably padded: the four pipeline commands appear verbatim in both the 'Available Pipelines' and 'Pipeline Examples' sections, the 'Examples Repository' repeats the same run patterns a third time, and sections like 'Conclusion', 'Related Skills', and 'Performance Characteristics' add marketing filler ('battle-tested', 'powerful modes'). It is not a 1 because it does not explain concepts Claude already knows — the redundancy is duplication rather than education — but several sections are pure padding.	2 / 5
Actionability	Commands are concrete and copy-paste ready ('claude-flow stream-chain run "Analyze codebase structure" ...'), with option tables showing defaults and a complete JSON config format for custom pipelines. It is not a 5 because of corrupted path separators — '.claude-flow$config.json', 'Success$failure', 'critical$high$medium$low', '.claude-flow$memory$stream-chain/' use '$' where '/' belongs — so some guidance as written is wrong or non-executable.	4 / 5
Workflow Clarity	The 'How Context Flows' section concretely shows what each step receives, prompt ordering guidance ('Logical Progression') and troubleshooting steps are given, and chains are non-destructive so heavy validation is not required. It is not a 5 because there are no explicit checkpoints for verifying a step's output succeeded before proceeding (e.g., checking the per-step success/failure output the doc mentions), leaving validation implicit.	4 / 5
Progressive Disclosure	The skill is one monolithic SKILL.md with no bundle files; large blocks that clearly belong in separate references — the 'Examples Repository', 'Advanced Use Cases', and the custom pipeline JSON definitions — are all inlined, mirroring the anchor 'content that clearly belongs in separate files is inlined'. It is not a 3 because there are no references at all to signal, and the sheer volume of inlined example content goes beyond an organization quibble.	2 / 5
	Total	12 / 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 clearly names the domain and mechanism but stops there: no trigger clause, no concrete actions, and buzzword-heavy application areas. It would benefit most from an explicit 'Use when...' clause and concrete capability verbs.

Suggestions

Add an explicit trigger clause, e.g. 'Use when chaining agent outputs into sequential pipelines, building multi-step data transformation workflows, or when the user asks to pass one step's output into the next.'

Replace generic phrases like 'data transformation' and 'sequential workflows' with concrete actions, e.g. 'Runs prompt sequences where each step receives the previous step's output; provides predefined analysis, refactor, test, and optimize pipelines.'

Include natural user synonyms (e.g., 'chain prompts', 'pipeline steps', 'output into next step') to improve trigger-term coverage and distinctiveness from generic workflow skills.

Dimension	Reasoning	Score
Specificity	The description "Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows" names the domain (stream-JSON chaining) but the rest is generic application-area listing rather than concrete actions — nothing like 'extracts' or 'fills'. It is not a 3 because there is no concrete, specific action verb beyond 'chaining'; the phrase reads as domain-plus-buzzwords ('multi-agent pipelines', 'sequential workflows'), matching 'Names the domain but actions are minimal or generic'.	2 / 5
Completeness	The 'what' is stated reasonably clearly (stream-JSON chaining for pipelines and sequential workflows), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the 'what' is clear rather than vague, and not a 4 because 'when' is entirely absent rather than merely under-specified.	3 / 5
Trigger Term Quality	Keywords like 'chaining', 'pipeline', 'multi-agent', 'data transformation', 'sequential workflows' are terms a user might plausibly say, giving some relevant coverage. It is not a 4 because common variations, synonyms, and concrete artifacts (e.g., 'workflow steps', 'chain prompts together', 'stream output into next step') are missing, and no natural trigger phrasing is included.	3 / 5
Distinctiveness Conflict Risk	'Stream-JSON chaining' is a somewhat distinctive mechanism name, but 'multi-agent pipelines', 'data transformation', and 'sequential workflows' are broad terms that overlap with general orchestration, workflow, and data-processing skills. It is not a 4 because without trigger phrases the boundary against those related skills is not drawn, and not a 2 because the stream-JSON chaining mechanism does give it some identity.	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/ruflo
Path: .agents/skills/stream-chain/SKILL.md
Commit: b14c79e

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.