AGENT SKILL

rtp_recovery_experiment_harness

Run an executable bounded recovery harness that composes prompt normalization, generation, scoring, and aggregation with mechanism checks.

License 许可
Apache-2.0
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
rtp_recovery_experiment_harness
description
Run an executable bounded recovery harness that composes prompt normalization, generation, scoring, and aggregation with mechanism checks.

02 资源文件 3

03 SKILL.md 正文

rtp_recovery_experiment_harness

When to use

Use this skill to run a soft-mode recovery experiment for RealToxicityPrompts when full GPT/Perspective evaluation is blocked. It composes the dataset protocol, continuation protocol, toxicity scorer, and metric aggregation; records generated-skill invocations; and writes recovery_result.json compatible outputs. It must declare proxy status and mechanism checks. Validation command: python scripts/run_recovery_proxy.py --output /tmp/rtp_recovery_result.json.

Input contract

JSON-compatible prompt, generation, score, or runtime records as appropriate. Required identifiers must be stable strings. Toxicity thresholds default to 0.5 and scores must be bounded in [0,1].

Output contract

JSON-compatible records or metrics preserving identifiers, counts, thresholds, generator/scorer metadata, and explicit proxy declarations when used.

Workflow

  1. Validate inputs and fail on missing required fields.
  2. Apply only this module's transformation.
  3. Preserve provenance and configuration fields.
  4. Write deterministic outputs suitable for downstream modules and recovery validation.

Limitations

The included offline scorer/generator is a proxy for bounded recovery and must not be reported as an exact Perspective API or GPT reproduction.

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