無料GitHub で公開

honey-gain

Honey benchmark scoreboard vs baseline and rival skills.

Green-PT/honey-for-devs

インストール方法を見る

含まれるファイル（1）

SKILL.md2.4 KB

SKILL.md（原文）

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Honey Gain

Report the committed benchmark results — never a guessed or per-session number, and never an embedded copy that can drift from the bench.

Do

Recompute from the committed records at use time — don't recite from memory, and prefer the raw records over any rendered table (renderings go stale, the records don't):
```
cd bench && node src/report.js --stamp full-opus48 --by-type
```
Offline, no API spend. Swap --stamp full-gpt55 for the cross-provider figure, drop --by-type for the whole suite. Hive handoff numbers → bench/hive/RESULTS.md.
Report the tier table terse: Δ LOC and Δ output, each with its p, judge as win/loss/tie, and the test pass-rate, per variant. The tier split is the finding — deepest on code and handoffs, output a statistical tie on user-facing (the polish carve-out). Lead with Δ LOC: it measures Lever 1 directly, while output tokens mix code with the prose around it, and the two come apart (Ponytail cuts lines but narrates at length).

Rules

Never quote a delta without its p-value, and call (ns) results ties, not wins. Every figure is a paired per-task median; a ratio of arm totals is not quotable.
Prose renderings (bench/README.md, results/combined.md) are secondary. If one disagrees with a fresh --stamp recompute, the recompute wins — say the rendering is out of sync.
Quality is a tie, not a gain — that's the honest claim. Don't upgrade it.
Cost/CO₂ savings are a modelled counterfactual, not measured; those belong to honey-eco, which labels them. Don't state a dollar saving here.
Asked for numbers on this repo? The bench measures the skill on a fixed task suite, not the user's codebase — offer cd bench && npm run bench, don't extrapolate.
One honest caveat, once: 23 author-written tasks, judge noise — the objective test-pass column is the trustworthy correctness signal.
Never resurrect the old unreproducible 92%/78%/73% / −57%/−65%/−70% numbers, or the superseded arm-total figures (−49% code, −15% aggregate) — see bench/METHODOLOGY.md.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

ログインしてレビューを書く

同じリポジトリのスキル

概要と使いどころ

honey

無料

Write less code and say less about it. Applies YAGNI and stdlib/native-first so the agent writes the minimum code that needs to exist, and responds tersely — stripping filler, hedging, and pleasantries while keeping code, identifiers, and technical terms exact. Use whenever writing, modifying, refactoring, reviewing, or explaining code, or any response where output volume drives token cost — even if the user never says "minimal" or "concise". Especially in agentic coding, where the volume of generated code and prose runs up the bill.

日本語の概要は準備中です。原文の説明を表示しています。