stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows
60
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
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 technical domain but relies heavily on jargon without explaining concrete actions or providing explicit usage triggers. It lacks the 'Use when...' clause critical for Claude to select this skill appropriately, and the terminology may not match how users naturally phrase requests.
Suggestions
Add a 'Use when...' clause with natural trigger phrases like 'chain multiple agents', 'streaming JSON', 'orchestrate tasks', or 'pipeline data between steps'.
Replace or supplement 'Stream-JSON chaining' with concrete actions such as 'routes data between agents', 'transforms streaming JSON', or 'orchestrates sequential task execution'.
Include common user phrasings and file/format references like 'JSONL', 'streaming responses', or 'agent coordination' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (multi-agent pipelines, data transformation, sequential workflows) and mentions 'Stream-JSON chaining' as a technique, but lacks concrete actions like 'parse', 'transform', 'route', or 'aggregate'. | 2 / 3 |
Completeness | Describes what it does at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance. The 'when' is entirely missing. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'multi-agent', 'pipelines', 'data transformation', and 'workflows', but uses technical jargon ('Stream-JSON chaining') that users are unlikely to naturally say. Missing common variations like 'chain tasks', 'orchestrate', or 'streaming data'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Multi-agent pipelines' and 'sequential workflows' are somewhat specific, but 'data transformation' is very broad and could overlap with many other skills. The Stream-JSON focus provides some distinction but isn't clearly scoped. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides excellent actionable guidance with clear, executable commands and comprehensive examples. However, it's overly long for a SKILL.md overview, mixing quick-start content with exhaustive reference material that should be in separate files. The workflow clarity would benefit from explicit validation checkpoints integrated into examples rather than relegated to a best practices section.
Suggestions
Move detailed pipeline definitions, advanced use cases, and examples repository to separate reference files (e.g., PIPELINES.md, EXAMPLES.md) and link from a concise overview
Integrate validation steps directly into workflow examples (e.g., 'Verify output before proceeding to next step') rather than only mentioning them in best practices
Remove the 'Conclusion' section and 'Performance Characteristics' (specific numbers like '50MB per active chain' are likely inaccurate and add noise)
Add explicit error handling guidance within chain examples showing what to do when a step fails
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately verbose with some unnecessary sections like 'Conclusion' that summarize what Claude already read, and 'Performance Characteristics' with specific numbers that may not be accurate. However, most content is useful reference material. | 2 / 3 |
Actionability | Provides fully executable bash commands throughout, with clear syntax examples, option tables, and copy-paste ready code blocks. The JSON configuration example is complete and usable. | 3 / 3 |
Workflow Clarity | Steps are listed clearly for each pipeline, but validation/verification is only mentioned in best practices rather than integrated into the workflow examples. Missing explicit feedback loops for error recovery in the main workflow sections. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but the document is monolithic at ~400 lines. References to 'Related Skills' exist but are vague pointers without actual file links. Much content (like all pipeline examples) could be split into separate reference files. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%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 | |
- Reviewed
Table of Contents
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.