growth: measured 'built by AI, for AI agents' positioning to attract AI-assisted contributors (after #1275)
维护者通常 1 天内回复
还没有人认领这个 Issue。
评估
- 难度
- 5/5
- 预计耗时
- 一周以上
- 新手友好度
- 25/100
- Issue 类型
- 功能
- 描述清晰度
- 描述清楚
- 活跃度
- 活跃
- 技术栈
- c
调研方向
Start by reading #1275 and the repository's existing contributor documentation, then map the benchmark script, docs site page, CONTRIBUTING.md, docs/llms.txt, make precheck, and issue forms. Done means a reproducible protocol, runs on at least three models and a baseline, a dated public results page, updated contributor guidance, and five qualifying good-first-issue issues.
由索引模型根据 Issue 内容生成。
描述
Goal. Bring in more AI-assisted contributors by making the claim "EigenScript is built by AI, for AI agents to work on" measured and public, not asserted.
Why this compounds. An AI contributor's cost is what #1275's benchmark measures: tokens, precheck/CI rounds, and whether the first push is green. Lower cost means more contributions. Each contribution surfaces a gap, and the forcing-function rule routes it into docs, gates or llms.txt, which lowers the next contributor's cost. Evidence both ways: the heaviest outside contributor (AI-assisted, 63 PRs) stopped on 2026-08-20, as contributor-facing burden grew (#1275).
First data point (2026-09-24, #1275). A fresh claude-sonnet-5, given only the repo's docs, fixed #1236 with a regression test in 9.8 min for $2.21. Its first push was green on 33/33 checks (#1300).
Sequencing. Starts after #1275 closes. Publishing the benchmark mid-consolidation would advertise the burden being removed.
Done when:
- The benchmark protocol is a script in the repo. It covers the history-free snapshot, a stub
origin/main, the suite run in the foreground, and the metrics captured from the agent's result event, so any run is reproducible by command. - It has run on ≥ 3 models (e.g. Sonnet 5, Opus 5.5, GPT-6 Sol) and on a baseline: a comparable one-line stdlib bug plus a test in an established language's repo, the same protocol. Without the baseline, the claim is a data point, not a comparison.
- A public page (docs site) shows the table, the protocol and the date, with a re-run date stated.
- CONTRIBUTING.md has a short "Contributing with an AI agent" section that points the agent at
docs/llms.txt,make precheckand the issue forms' "Done when". It is kept lean, per the contributor-facing-docs rule. - ≥ 5 open issues carry
good first issuewith a "Done when" an agent can verify. - The wording says "for AI agents" / "AI-written software", not "AI language" (Mojo's meaning).
- 主要语言
- C
- 星标
- 3
- 派生
- 7
- 平均合并
- 3 小时 58 分钟
- 30 天内合并 PR
- 105
环境准备
在浏览器里用你自己的 GitHub 账号启动这个项目的开发容器。
- 提供 Dockerfile 或 Docker Compose 文件
- 有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue，再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库，在一个分支上完成修改。
- 提交 Pull Request，并在描述里引用这个 Issue 编号。
InauguralSystems/EigenScript 的其他 Issue
-
area:lint-tooling bug
难度 2/5 1-3 小时 新手友好度 88/100
InauguralSystems/EigenScript#1340 ·
维护者通常 1 天内回复
-
area:stdlib found-by:code-review kind:silent-wrong
难度 2/5 1-3 小时 新手友好度 88/100
InauguralSystems/EigenScript#1338 ·
维护者通常 1 天内回复
-
area:lint-tooling found-by:critic kind:docs-drift
难度 2/5 1-3 小时 新手友好度 76/100
InauguralSystems/EigenScript#1335 ·
维护者通常 1 天内回复
-
area:ci found-by:critic kind:gate-defect
难度 2/5 1-3 小时 新手友好度 86/100
InauguralSystems/EigenScript#1311 ·
维护者通常 1 天内回复
-
enrolment: decide test_gc_runner_controls.py (exempt vs enrol) and whether floors need a ratchet未关闭area:gates found-by:critic kind:decision
难度 2/5 1-3 小时 新手友好度 65/100
InauguralSystems/EigenScript#1280 · 1 条评论 ·
维护者通常 1 天内回复
查看 InauguralSystems/EigenScript 的全部 Issue
相似的 Issue
-
难度 2/5 1-3 小时 新手友好度 76/100
-
难度 1/5 1 小时以内 新手友好度 75/100
NabuCasa/silabs-firmware-builder#231 · 1 条评论 ·
-
难度 1/5 1-3 小时 新手友好度 88/100
ClickHouse/pg_clickhouse#383 · 1 条评论 ·
维护者通常 1 天内回复
-
bug
难度 2/5 1-3 小时 新手友好度 76/100
johnsonjh/emu2-cpm86#68 · 1 条评论 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 78/100
维护者通常 1 天内回复