Agent Skills › uw-syfi/vibesys › combine-candidates

combine-candidates

GitHub

将多个候选变更按序合并至指定基线,自动解决冲突并运行测试。若无法遵循指令则停止,最终提交结果并通过vibesys:measure进行性能与正确性评估,返回完整报告供负责人决策。

skills/search/combine-candidates/SKILL.md uw-syfi/vibesys

触发场景

需要合并多个候选变更到一个新提交 将获胜者合并到主分支

安装

npx skills add uw-syfi/vibesys --skill combine-candidates -g -y
更多选项

非标准路径

npx skills add https://github.com/uw-syfi/vibesys/tree/main/skills/search/combine-candidates -g -y

不安装直接使用

npx skills use uw-syfi/vibesys@combine-candidates

指定 Agent (Claude Code)

npx skills add uw-syfi/vibesys --skill combine-candidates -a claude-code -g -y

安装 repo 全部 skill

npx skills add uw-syfi/vibesys --all -g -y

预览 repo 内 skill

npx skills add uw-syfi/vibesys --list

SKILL.md

Frontmatter
{
    "name": "combine-candidates",
    "description": "Use when a vibesys optimize brief asks you to combine several candidates' changes into one new commit on a given base, or to merge judged winners into main. Applies each candidate's own change in the stated order, resolves conflicts as the brief says, runs the checks, measures the result with vibesys:measure, and hands back the commit and anything that could not be applied."
}

Combine candidates

You build one new commit from several candidates' changes, in your own worktree, on the exact base commit the brief names. The steps and the lead's side of a merge are in combining.md.

Start

Run the first command of your brief and confirm the worktree and branch. Read OBJECTIVE.md. Load vibesys:measure and the domain skills the brief names.

Work

  1. Apply each candidate's own change in the order given. Its own change is the diff from the commit it was built on to the candidate, not from main: git diff <built-on> <candidate> | git apply --3way
  2. A hunk that does not apply is left with conflict markers: resolve them as the brief says, so each candidate's change survives. Keep every part's behavior. Do not redesign a part.
  3. If an instruction cannot be followed without redesigning a candidate, stop and say which instruction and why. Main stays as it is.
  4. Run the project's fast tests and fix what the combination broke.
  5. Commit. Without a measurement slot, return the SHA as ready for measurement for the lead. Otherwise measure the commit with vibesys:measure: the check, then at least 5 samples. Compare it with main: compare --commit <sha> --base <main SHA>, and with each part.

Never

Edit anything under .vibesys/, the task's checker or its benchmark. Add a shortcut that raises a number without the work being done.

Hand back

The commit SHA; each part you applied and each part, or piece of one, you could not apply and why; the checks you ran with results; the compare output against main and against the best part. You do not decide whether the result becomes main: the lead does.

版本历史

  • 3a50e8b 当前 2026-11-02 13:57

同 Skill 集合

.agents/skills/add-agent-provider/SKILL.md
.agents/skills/add-bundled-skill/SKILL.md
.agents/skills/build-client-feature/SKILL.md
.agents/skills/change-container-images/SKILL.md
.agents/skills/create-issue/SKILL.md
.agents/skills/enforce-rules/SKILL.md
.agents/skills/open-pr/SKILL.md
.agents/skills/review-pr/SKILL.md
.agents/skills/software-design/SKILL.md
.agents/skills/testing/SKILL.md
.agents/skills/vs-init/SKILL.md
.agents/skills/write-agent-prompt/SKILL.md
.agents/skills/write-docs/SKILL.md
.agents/skills/write-skills/SKILL.md
.agents/skills/write-vibesys-tests/SKILL.md
resources/chat-skills/reading-ideas/SKILL.md
resources/chat-skills/results-against-base/SKILL.md
resources/chat-skills/run-roles/SKILL.md
resources/chat-skills/steering-a-run/SKILL.md
resources/skills/dial9-tokio/skills/dial9-diagnose-long-poll/SKILL.md
resources/skills/dial9-tokio/skills/dial9-red-flags/SKILL.md
resources/skills/dial9-tokio/skills/dial9-runtime/SKILL.md
resources/skills/dial9-tokio/skills/dial9-toolkit/SKILL.md
resources/skills/dial9-tokio/skills/dial9-trace-analysis/SKILL.md
resources/skills/dial9-tokio/skills/dial9-trace-loading/SKILL.md
resources/skills/dial9-tokio/skills/dial9-trace-recipes/SKILL.md
resources/skills/dial9-tokio/skills/dial9-zoom-window/SKILL.md
resources/skills/kernel-correctness/SKILL.md
resources/skills/kernel-ncu-analysis/SKILL.md
resources/skills/kernel-performance/SKILL.md
resources/skills/kernel-rocprof-analysis/SKILL.md
resources/skills/microservice-optimization/SKILL.md
resources/skills/neuron-agentic-development/skills/neuron-nki-debugging/SKILL.md
resources/skills/neuron-agentic-development/skills/neuron-nki-docs/SKILL.md
resources/skills/neuron-agentic-development/skills/neuron-nki-profiling/SKILL.md
resources/skills/serving-systems/SKILL.md
skills/domains/dial9-tokio/dial9-rank-bottlenecks/SKILL.md
skills/domains/dial9-tokio/skills/dial9-diagnose-long-poll/SKILL.md
skills/domains/dial9-tokio/skills/dial9-red-flags/SKILL.md
skills/domains/dial9-tokio/skills/dial9-runtime/SKILL.md
skills/domains/dial9-tokio/skills/dial9-toolkit/SKILL.md
skills/domains/dial9-tokio/skills/dial9-trace-analysis/SKILL.md
skills/domains/dial9-tokio/skills/dial9-trace-loading/SKILL.md
skills/domains/dial9-tokio/skills/dial9-trace-recipes/SKILL.md
skills/domains/dial9-tokio/skills/dial9-zoom-window/SKILL.md
skills/domains/kernel-correctness/SKILL.md
skills/domains/kernel-ncu-analysis/SKILL.md
skills/domains/kernel-performance/SKILL.md
skills/domains/kernel-rocprof-analysis/SKILL.md
skills/domains/kernel-timeline-analysis/SKILL.md

元信息

文件数
0
版本
3a50e8b
Hash
be249811
收录时间
2026-11-02 13:57

首页 - Wiki
Copyright © 2011-2026 iteam. Current version is 2.156.0. UTC+08:00, 2026-11-05 23:05
浙ICP备14020137号-1