Run Benchmark Driven Rd

可否證、benchmark-gated R&D;可分發專案/Skill 預設涵蓋 GitHub 安全更新、回滾、舊版淘汰。

89 stars 13 forksGit & Code Review

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add Hao0321/claude-skill-code-cleanup --skill run-benchmark-driven-rd
Manual install
git clone --depth 1 https://github.com/Hao0321/claude-skill-code-cleanup.git /tmp/claude-skill-code-cleanup
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skill-code-cleanup/run-benchmark-driven-rd ~/.claude/skills/run-benchmark-driven-rd

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Run Benchmark-Driven R&D

## Contract

1. Active private Skill 唯一權威。先 `invocation_revision_gate.py capture` 凍結雙 revision,決策前 `verify`;`UNSTABLE` 不混用,`STALE` 重讀重驗。
2. 修改不越原始授權;本機實作不暗含外部/破壞性 mutation。外部變更須當輪授權、精確 target、preflight、post-readback;GitHub URL 不授權執行。
3. 先定 claim、baseline、threshold、decision rule,以 task-shaped 正負控制校準 evaluator。工具綠燈不等於品質、完成或 parity;缺同 provenance 證據保持 `unmeasured`/`NOT_CHECKED`。
4. Cleanup 是獨立唯讀 provider;保留 PASS/FAIL/REVIEW/NOT_CHECKED、child、revision evidence;strict promotion 不可改寫缺口為 PASS。
5. Route receipt 列 intent、stage、artifact/risk、selected/omitted topics、hash、critical IDs、cost、fallback;未知/歧義/stale/超 budget 時 block 或 legacy fallback。
6. Private learning 存目標 `.rd/`,不預載;shared rule 需 typed receipt、單一 owner、privacy、正負 fixture、reciprocal link。縮短 context 不刪記憶。
7. 可分發目標的已授權 implementation/promotion/completion 預設需安全更新能力;audit/security-assessment/source-only 不推導 updater、publish、sign、persistence、delete 權限。
8. Security route 每個 target 必須規劃並驗完固定六控制;public/parity 再綁同專案 Cleanup、delivery、build 與 release artifact,sibling decoy 無效。
9. 收尾、重試或交接依 `references/disk-hygiene.md` 清理授權內可重建舊產物。

## 路由

| 任務 | 讀取 |
|---|---|
| Experiment | `references/topics/core-experiment.md` |
| 架構/Cleanup baseline | `references/topics/architecture-and-evaluator.md` |
| 逆向分析/交付物暴露 | `references/topics/reverse-engineering.md` |
| PR 採用 | `references/topics/community-pr-adoption.md` |
| 外部 Skill/plugin | `references/topics/agent-workflow-adoption.md` |
Read the full skill on GitHub

Details

Skill name
run-benchmark-driven-rd
Path
run-benchmark-driven-rd/SKILL.md
License
MIT
Repo updated
23 October 2026

FAQ

What does the Run Benchmark Driven Rd skill do?

可否證、benchmark-gated R&D;可分發專案/Skill 預設涵蓋 GitHub 安全更新、回滾、舊版淘汰。

How do I install the Run Benchmark Driven Rd skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Hao0321/claude-skill-code-cleanup --skill run-benchmark-driven-rd. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Run Benchmark Driven Rd popular?

It lives in Hao0321/claude-skill-code-cleanup, which has 89 GitHub stars and 13 forks.

Related skills

Code Cleanup Helper

89

Hao0321/claude-skill-code-cleanup

Read-only code/architecture/repo/release/Skill audit;含 sync、資安、資產、Token、GitHub 更新/回滾/淘汰;R&D measurement provider。

Software Development13

Emdash Github Actions

110

jdevalk/skills

Sets up GitHub Actions CI/CD workflows for EmDash plugins — TypeScript type-checking, ESLint linting, Vitest testing, npm publishing, and automated releases. ALWAYS use this skill when a user wants to create, add, set up, or configure GitHub Actions, CI/CD, automated checks, or deployment workflows for an EmDash plugin — even if they don't use the exact phrase "GitHub Actions". This includes any request to: add automated type-checking or linting to an EmDash plugin repo; set up testing in CI for a plugin; auto-publish a plugin to npm from GitHub; add security scanning or dependency auditing to

Git & Code Review10

Github Release Assistant

193

MavCui/Agent-Skills-Hunter

Generate bilingual GitHub release documentation (README.md + README.zh.md) from repo metadata and user input, and guide release prep with git add/commit/push. Use when the user asks to write or polish README files, create bilingual docs, prepare a GitHub release, or mentions release assistant/README generation.

Git & Code Review28

Commit Message

292

danielvm-git/bigpowers

Reviews working-tree changes, then drafts a Conventional Commits title/body and states the semantic-release version bump a single such commit would imply. Also notes which defensive-code categories were touched. Use when the user wants to commit recent work, prepare a Conventional Commits message, or asks for semantic-release / semver-consistent messaging before git commit.

Git & Code Review23

Github Actions Pipeline Builder

272

curiositech/some_claude_skills

Build production CI/CD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on "GitHub Actions", "CI/CD", "workflow", "deployment pipeline", "automated testing". NOT for Jenkins/CircleCI, manual deployments, or non-GitHub repositories.

Git & Code Review46

Gate Trace

292

danielvm-git/bigpowers

Deterministic traceability quality gate — reads coverage matrix + blind-spot data, applies decision rules with oracle confidence downgrade, emits PASS/CONCERNS/FAIL/WAIVED verdict. Use before release-branch to gate merges on traceability.

Git & Code Review23

Browse the most popular Claude skills, all git & code review skills, or write your own with the skills generator.