AGENT SKILL

r1v4-api-testing

Draft, inspect, parse, and summarize Skywork R1V4 API batch tests without leaking API keys.

License 许可
MIT
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
r1v4-api-testing
license
MIT
metadata
{ "disco-role": "operating" }
description
Draft, inspect, parse, and summarize Skywork R1V4 API batch tests without leaking API keys.
disable-model-invocation
true

02 资源文件 8

03 SKILL.md 正文

R1V4 API Testing

Use this sub-skill when you need to prepare Skywork R1V4 API batch tests, dry-run request payloads, parse tagged tool-use responses, summarize result JSONL, or troubleshoot the batch viewer safely.

Start here

  1. Read references/api-batch-workflows.md for the four batch modes and Chinese terminology.
  2. Check references/data-formats.md for test_cases.jsonl, request payload, and result JSONL schemas.
  3. Validate input cases with scripts/validate_cases.py before any API run.
  4. Build a no-network payload preview with scripts/build_api_payload.py.
  5. Parse a tagged response or a result file with scripts/parse_r1v4_response.py.
  6. Summarize a result JSONL with scripts/summarize_results.py.

Bundled files

  • references/api-batch-workflows.md — workflow map for batch_nonstream.py, batch_stream.py, batch_planner_nonstream.py, and batch_planner_stream.py.
  • references/data-formats.md — input/output schemas and tagged response grammar.
  • references/result-analysis.md — safe headless analysis path and visualizer guidance.
  • references/troubleshooting.md — API, image, stream, parse, and viewer failure modes.
  • scripts/validate_cases.py — schema and optional image-path validation.
  • scripts/build_api_payload.py — OpenAI-compatible payload builder with data URL support.
  • scripts/parse_r1v4_response.py — tagged response parser and JSONL parser CLI.
  • scripts/summarize_results.py — batch result counters and response-length summary.

Routing notes

  • Use skywork/r1v4-lite for the regular batch modes and skywork/r1v4-vl-planner-lite for planner batch modes.
  • Keep the message order as image first, then text.
  • Bundled helpers do not make live API calls by default.
  • Leave API keys to env or caller config; do not hard-code them in payloads or scripts.
  • Use the bundled summary helper instead of copying the full Flask viewer into a workflow.
  • Route local Transformers/vLLM inference, CUDA setup, and model-weight issues to the sibling local-inference sub-skill.
  • Route VLMEvalKit, EMMA, MMK12, and benchmark reproduction tasks to the sibling evaluation-reproduction sub-skill.

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-solve

END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-pattern-fusion

Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).

★ 351