agentsclimarketplace
Sign in

Fetcher llm streaming

Skill Ahoo-Wang/skills/sources/fetcher/skills/fetcher-llm-streaming

Use when consuming Server-Sent Events, LLM token streams, OpenAI-style streaming chat responses, Fetcher eventstream helpers, response prototype extensions, stream termination detection, result extractors, or ReadableStream async iteration.From its SKILL.md

Install
npx -y skills add Ahoo-Wang/skills --skill fetcher-llm-streaming

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.9 KB, 335 tokens by cl100k_base, as published. Nobody here has run it

fetcher-llm-streaming

Use This Skill When

  • The task involves SSE, EventSource-style data, streaming responses, or token-by-token UI updates.
  • The task mentions eventStream, jsonEventStream, textEventStream, or ReadableStreamAsyncIterable.
  • The task needs OpenAI-style completion chunks or DONE termination handling.
  • The task needs a decorator result extractor for streaming endpoints.

Workflow

  1. Import @ahoo-wang/fetcher-eventstream for side-effect prototype helpers when using Response extensions.
  2. Use standalone conversion functions when prototype mutation is undesirable.
  3. Handle stream conversion errors explicitly with EventStreamConvertError.
  4. Detect termination with the package helper instead of ad hoc string checks.
  5. Load references/api.md for pipeline details, OpenAI streaming examples, and UI update patterns.

Key Practices

  • Keep parsing, termination detection, and UI state updates as separate steps.
  • Use async iteration over streams to avoid buffering full responses in memory.
  • When pairing with decorators, configure result extractors at the endpoint boundary.

References

  • references/api.md: Detailed package API, examples, and edge-case guidance. Load it only when the task needs prototype extensions, standalone stream functions, SSE structures, termination handling, OpenAI streaming examples, and React UI update snippets.

Related Skills

  • $fetcher-openai-client: Use for higher-level OpenAI chat client setup.
  • $fetcher-decorator-service: Use when the streaming endpoint is declared with decorators.
  • $fetcher-react-hooks: Use when streaming data drives React state.

What ships with it: 2 files

7.0 KB alongside SKILL.md

agents/

references/

Gives 0 of the 12 instructions most context ai engineering skills give in 335 tokens

Counted across 1,193 of the 1,976 authors here whose files we hold, read 2026-08-07

  • Dispatch a fresh implementer subagent per taskin 48 of 1193, across 19 files
  • Dispatch a final code reviewer after all tasksin 33 of 1193, across 8 files
  • Provide full task text to the subagentin 30 of 1193, across 9 files
  • Review spec compliance before code qualityin 27 of 1193, across 10 files
  • Make the hook script executablein 26 of 1193, across 8 files
  • Re-snapshot after navigation or DOM changesin 25 of 1193, across 19 files
  • Read files before editing themin 22 of 1193, across 11 files
  • Answer subagent questions before proceedingin 22 of 1193, across 7 files
  • Mark task complete in TodoWrite after approvalin 22 of 1193, across 6 files
  • Merge hook into existing settingsin 21 of 1193, across 3 files
  • Ask if installation is global or projectin 20 of 1193, across 2 files
  • Copy the hook script to target locationin 20 of 1193, across 2 files

Said here and by no other author read

  • import the fetcher eventstream package
  • use standalone functions to avoid prototype mutation
  • handle stream conversion errors explicitly
  • use the package helper for termination detection
  • load the API reference for pipeline details
  • separate parsing, termination, and UI updates

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,144. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.