Home / ccdawn / codex-skills · skills/competition/briefbound-huawei-nslb-score-loop/SKILL.md · GitHub

briefbound-huawei-nslb-score-loop skillA

briefbound-huawei-nslb-score-loop is agent-read markdown (skill) from ccdawn/codex-skills: Use when a Huawei Algorithm Challenge 37 NSLB workspace needs live status, adaptive solver search, comparable evaluation, packaging, or online-score feedback; it is a thin project adapter over briefbound-score-loop..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Huawei NSLB Score Loop

## 目标

这是 `briefbound-score-loop` 的 Huawei NSLB 适配层,补充项目识别、工具命令、solver 约束和线上反馈;候选搜索、淘汰和替换仍用通用 score loop。

不得把 skill 内的旧分数、hash 或聊天记忆当成当前事实;最好方案、源码 hash、活跃运行和提交映射从项目现场读取。

## Briefbound task contract

- Context Boundary: 项目根目录、当前 baseline/hash、评价协议、solver 写入面、工具状态和线上反馈。
- Output Contract: 当前状态、下一候选、可比证据、替换决定、提交包或恢复结果。
- Allowed Action: 只在项目授权范围内运行命令和修改隔离 workspace;不静默改主 baseline、ledger、提交映射或线上最佳记录。
- Success Evidence: 当前命令输出、source hash、candidate diff/config、可复现指标、`child_result.json`、gate 或短名提交包。
- Stop Condition: source drift 未解释、协议不可比、共享事实源写冲突、child result 无效、提交包无效、线上反馈归属不清或用户暂停。
- Route Out: `briefbound-score-loop`、项目工具、`briefbound-bug-review`、online feedback wait、项目 memory 或 BLOCKED。

## 统一调用契约

- 只处理 Briefbound task contract;Route Out 仅以 Briefbound task contract 为准。
- 用户可见内容默认中文,先说状态、原因和下一步,不先列 ledger、epoch 或内部枚举。
- 首次出现代理测试时解释:它是用于快速淘汰候选的小测试,不能代替正式分数。
- 只有复杂问题需要时才展开 hash、worker、校准或搜索图;有自然闸门时末行 `下一步建议: <一个具体动作>`,否则继续已授权工作。

## Live-State Gate

从 `--project`、`BRIEFBOUND_HUAWEI_NSLB_ROOT` 或当前仓库解析根目录,确认 `src/Solution.cpp`,再定位工具。检查 `status`、`doctor`、`drift`,读取已有 baseline、ledger、online feedback 和 package map;缺失就说明,不新造事实源。协议或 baseline 漂移时先恢复可比性。
…

Read the whole file at its exact version.

How to install

Latest version
mdr add ccdawn/codex-skills/briefbound-huawei-nslb-score-loop@git:20260916.292b0ac
Exact content
mdr add ccdawn/codex-skills/briefbound-huawei-nslb-score-loop@sha256:43485cd4d9b6c19d

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_mnfzdo6eghezvsai.svg)](https://markdownregistry.com/a/art_mnfzdo6eghezvsai)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260916.292b0ac latest2026-09-16 292b0ac 4,600 BA view · diff
git:20260813.dec1d142026-08-13 dec1d14 4,583 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4600 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

GitHub

ccdawn/codex-skills · 6 stars · license MIT · pushed 2026-09-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_mnfzdo6eghezvsai
GET https://markdownregistry.com/api/v1/resolve?ref=ccdawn/codex-skills/briefbound-huawei-nslb-score-loop
GET https://markdownregistry.com/api/v1/blob/43485cd4d9b6c19d5c6772d98c15531bf19340630277df3fcfea616471acd959

Your agent 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.

More from ccdawn/codex-skills

AGENTS.md agents
ccdawn/codex-skills · AGENTS.md
git:20260813.dec1d14 · audit A · 6 stars
CLAUDE.md claude
ccdawn/codex-skills · CLAUDE.md
git:20260813.dec1d14 · audit A · 6 stars
briefbound-score-loop skill
ccdawn/codex-skills · skills/competition/briefbound-score-loop/SKILL.md · Use when repeated work is governed by an explicit metric, active baseline, candidate search, promotion rule…
git:20260916.292b0ac · audit A · 6 stars
briefbound-creative-toolbox skill
ccdawn/codex-skills · skills/creative/briefbound-creative-toolbox/SKILL.md · Use when the user wants non-obvious but useful ideas, concept invention, naming, reframing, variation, selection…
git:20260916.292b0ac · audit A · 6 stars
briefbound-diagram-design skill
ccdawn/codex-skills · skills/creative/briefbound-diagram-design/SKILL.md · Use when creating or redrawing structured diagrams such as architecture, flowcharts, sequences, ER/UML, timelines or…
git:20260916.ed1d50d · audit A · 6 stars
briefbound-api-contract skill
ccdawn/codex-skills · skills/engineering/briefbound-api-contract/SKILL.md · Use when a change touches an external contract surface - REST/GraphQL endpoints, request/response schemas, DB schema…
git:20260920.280b6d2 · audit A · 6 stars
briefbound-autonomous-collaboration-loop skill
ccdawn/codex-skills · skills/engineering/briefbound-autonomous-collaboration-loop/SKILL.md · Use when the user explicitly enables an automated same-project multi-thread development loop that keeps peer Codex…
git:20260919.ae05288 · audit A · 6 stars
briefbound-bdd-tdd-development skill
ccdawn/codex-skills · skills/engineering/briefbound-bdd-tdd-development/SKILL.md · Use when an already-defined new behavior or high-risk implementation contract needs a failing test before…
git:20260916.292b0ac · audit A · 6 stars
briefbound-bug-review skill
ccdawn/codex-skills · skills/engineering/briefbound-bug-review/SKILL.md · Use when an observed bug, correctness regression, failing test, build failure, abnormal behavior, or unresolved root…
git:20260916.292b0ac · audit A · 6 stars
briefbound-code-structure-guard skill
ccdawn/codex-skills · skills/engineering/briefbound-code-structure-guard/SKILL.md · Use when active development or explicit refactoring has concrete code-structure risk: a source file is accumulating…
git:20260916.292b0ac · audit A · 6 stars
briefbound-design-system skill
ccdawn/codex-skills · skills/engineering/briefbound-design-system/SKILL.md · Use when a frontend task primarily concerns cross-component design tokens, semantic theming, component APIs, variants…
git:20260916.292b0ac · audit A · 6 stars
briefbound-development-cleanup skill
ccdawn/codex-skills · skills/engineering/briefbound-development-cleanup/SKILL.md · Use when a verified or integrated software change has concrete temporary artifacts, generated noise, task-owned…
git:20260919.ae05288 · audit A · 6 stars

Every file in ccdawn/codex-skills

Browse by kind, by grade A, or by owner.