hillclimb SKILL.md skillA
hillclimb from suge8/friedbun is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add suge8/friedbun/hillclimb@git:20261105.956d98aPins git:20261105.956d98a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- suge8/friedbun
- Path
skills/workflow/hillclimb/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261105.956d98a, committed Nov 5, 2026
- First version recorded
- Nov 4, 2026
- Size
- 4,729 bytes
- Repository stars
- 13
- License
- MIT
爬山优化：把一个可测指标（性能、命中率、通过率、评分、体积）反复改动、测量、推向目标时使用；一次性修复不用。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 爬山 一次改一处，测一次，保留或回退。agent 的典型失败是前几步进步很快，随后在一个好实现、但有天花板的方向里反复调参；这个流程的关键是认出停滞并换方向。 1. **定指标与停止条件**：一个指标、哪边算好、目标值，再加最少尝试次数，免得早期一次偶然的好结果就收工。用户给了数字就用用户的。完成标准：写下“指标 / 方向 / 目标 / 至少 N 次尝试”。 2. **建评测并冻结**：一条命令输出指标，多次采样取中位数并报噪声幅度，同时跑回归检查（必须保持通过的测试与检查）。 - 按生产配置跑（模型、思考档、工具），单次运行设超时上限。 - 用例分优化集和留出集。留出集只在收尾确认时跑，结果不拿来改方案；被拿去找过问题的留出题换新题。 - 评分表和模型裁判先拿几份已知好坏的输出试一遍，确认奖励的是想要的行为（出现过因“缺地址价格”扣分、等于鼓励编造的评分表）；人工核对一小批，确认裁判和人一致。整场比较只用这一个裁判。 - 被优化的一方碰不到评测脚本、用例与参考答案；正确性失败记 0 分。 - 评测不动生产账号余额、真实设备和共享额度：用独立的 key 或设备。按量付费的余额每批前查一次；会自动换号的订阅不设额度停止线，以调用真的失败为准（只看一个号的额度，会把还能用的调用拦下）。 - 评分表、阈值、用例或裁判一改，旧结果就不可比：换一个批次名重跑基线。 完成标准：基线、噪声幅度、回归检查结果和每批的预计花费都已记下。 3. **开决策记录**：在评测目录（不进仓库）放一张表，每次尝试一行：编号、假设、改动、前后指标、回归检查、保留或回退、备注。每次尝试前先读它；中断后据它接着做，已有结果不重跑。完成标准：表已建好，基线是第一行。 4. **循环**，每轮一个假设： - 假设写明机制（“X 在启动路径上阻塞首帧，挪到首帧之后”），不写“试试加缓存”。只针对基线多次运行里重复出现的失败；只出现一次的是噪声，专门改它就是过拟合。 - 只改这一处。超过噪声且回归检查通过才保留，否则整个回退；保留时在运行记录里指出改动起作用的那一刻，只有分数涨了不够。不叠加没测过的改动，不凭读代码宣布变好。 - 互不依赖的假设各派一个子代理、各用一个 worktree 并行试；你只出假设、看 diff、裁决。几个候选各自过关后合成一版再测一次，不默认叠加。 - 改动落到最便宜的有效部件：重复的机械活交给脚本，窄流程做成按需技能；写进提示词的规则，模型几次里有一次以上没照做，就不再改措辞，改由脚本或检查保证。 - 完成标准：这次尝试在决策记录里有一行；回退的改动已撤干净，保留的改动叠在一起时回归检查仍通过。 …
Read the whole file at its exact version.
How to install
mdr add suge8/friedbun/hillclimb@sha256:9cc2dc86af5d4562The line at the top of this page pins the label git:20261105.956d98a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_dy5wkj6xw4iiw5tl)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Nov 4, 2026 and Nov 5, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261105.956d98a latest | 2026-11-05 | 956d98a | 4,729 B | A | view · diff |
| git:20261104.03bba56 | 2026-11-04 | 03bba56 | 4,237 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4729 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
suge8/friedbun · 13 stars · license MIT · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_dy5wkj6xw4iiw5tl GET https://markdownregistry.com/api/v1/resolve?ref=suge8/friedbun/hillclimb GET https://markdownregistry.com/api/v1/blob/9cc2dc86af5d45624a420befbf985c96fcefb1bfd34cac9941aa8afd54e0d026
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.