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 technical domain (Stream-JSON chaining) but remains too abstract in describing concrete capabilities and completely lacks explicit trigger guidance ('Use when...'). The terms used are a mix of somewhat distinctive ('Stream-JSON', 'multi-agent pipelines') and overly generic ('data transformation', 'sequential workflows'), making it moderately useful for skill selection but prone to both missed matches and false positives.

Suggestions

Add an explicit 'Use when...' clause with trigger scenarios, e.g., 'Use when the user needs to chain JSON streams between agents, build multi-step data pipelines, or orchestrate sequential processing workflows.'

List specific concrete actions the skill performs, e.g., 'Parses streaming JSON, chains agent inputs/outputs, transforms data between pipeline stages, handles sequential task orchestration.'

Include natural language variations users might say, such as 'JSON streaming', 'agent orchestration', 'pipeline chaining', or 'stream processing'.

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', 'chain agent outputs', or 'transform data between pipeline stages'.	2 / 3
Completeness	Provides a partial 'what' (Stream-JSON chaining for pipelines and transformation) but completely lacks a 'when' clause or any explicit trigger guidance. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2, and the 'what' itself is also weak, warranting a 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'multi-agent pipelines', 'data transformation', and 'sequential workflows', but misses common natural language variations users might say such as 'JSON streaming', 'pipeline orchestration', 'agent chaining', 'workflow automation', or 'stream processing'.	2 / 3
Distinctiveness Conflict Risk	'Stream-JSON' is somewhat distinctive as a specific technology/pattern, but 'data transformation' and 'sequential workflows' are very broad terms that could overlap with many other skills involving data processing or workflow management.	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 (bash CLI invocations with string prompts) dozens of times without adding new information. While the commands are concrete and copy-paste ready, the document would be far more effective at 1/3 its current length. The lack of progressive disclosure (everything inline, no external references) and absence of validation/error-recovery workflows for multi-step pipelines are significant weaknesses.

Suggestions

Cut content by 60-70%: consolidate the many near-identical bash examples into 2-3 representative ones, remove the Conclusion section, and eliminate redundant 'Use Cases' bullet lists for each pipeline.

Extract pipeline reference details (all 4 pipeline descriptions, custom pipeline config format, performance characteristics) into a separate REFERENCE.md and link to it from the main skill.

Add explicit validation checkpoints: show expected output for at least one chain step, demonstrate how to verify a step succeeded before proceeding, and provide a concrete error-recovery example beyond 'use --debug'.

Remove sections that explain concepts Claude already knows (e.g., 'Sequential Processing: Each step builds on previous results') and the 'Related Skills' section that has no actual links.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~350+ lines. Massive redundancy: the same concepts are shown 5-6 times with slight variations (e.g., multiple nearly identical bash 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.	1 / 3
Actionability	Provides concrete CLI commands that are copy-paste ready, and the JSON config format is specific. However, all examples are CLI invocations with string prompts—there's no way to verify correctness, no expected output shown, and the 'How Context Flows' section uses illustrative pseudocode rather than actual output. The custom pipeline JSON config is the most actionable element.	2 / 3
Workflow Clarity	Pipeline steps are listed clearly (e.g., 1. Structure Analysis, 2. Issue Detection, 3. Recommendations), and the best practices section mentions verification steps. However, there are no explicit validation checkpoints or error recovery feedback loops—troubleshooting is relegated to a brief section at the end with only surface-level advice like 'increase timeout' or 'use --debug'.	2 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files. Everything is inlined—the custom pipeline config, all examples, all pipeline descriptions, advanced use cases, troubleshooting, and performance characteristics. The 'Related Skills' section mentions other files but provides no links. Content that should be in separate reference files (e.g., pipeline details, examples repository) is all crammed into one document.	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/agentic-flow
Commit: 8db2712

Reviewed: 26 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.