Skill Creator
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
创建 / 修改 dna-builder 的远端下发技能(server/skills/<技能名/SKILL.md,由服务端实时打包下发给资料检索 Agent 与配装助手)。当需要新增一个给 Agent 用的领域技能(黑话表、机制读法、检索口径、判据清单…)、调整已有技能正文、或排查「技能不生效 / 描述没更新 / 下发被跳过」时使用。注意:server/skills/(下发库)与…
$ npx skills add pa001024/dna-builder --skill dob-skill-creator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pa001024/dna-builder dob-skill-creator --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/pa001024/dna-builder.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/dob-skill-creator .claude/skills/dob-skill-creator && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "dob-skill-creator" agent skill from https://github.com/pa001024/dna-builder/tree/master/.agents/skills/dob-skill-creator into .claude/skills/dob-skill-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dob-skill-creator", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/pa001024/dna-builder/tree/master/.agents/skills/dob-skill-creatorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add pa001024/dna-builder --skill dob-skill-creator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pa001024/dna-builder dob-skill-creator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pa001024/dna-builder.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/dob-skill-creator .agents/skills/dob-skill-creator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "dob-skill-creator" agent skill from https://github.com/pa001024/dna-builder/tree/master/.agents/skills/dob-skill-creator into .agents/skills/dob-skill-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dob-skill-creator", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add pa001024/dna-builder --skill dob-skill-creator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pa001024/dna-builder dob-skill-creator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pa001024/dna-builder.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/dob-skill-creator .cursor/skills/dob-skill-creator && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "dob-skill-creator" agent skill from https://github.com/pa001024/dna-builder/tree/master/.agents/skills/dob-skill-creator into .cursor/skills/dob-skill-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dob-skill-creator", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/pa001024/dna-builder.git --path .agents/skills/dob-skill-creator--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add pa001024/dna-builder --skill dob-skill-creator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pa001024/dna-builder dob-skill-creator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pa001024/dna-builder.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/dob-skill-creator .gemini/skills/dob-skill-creator && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "dob-skill-creator" agent skill from https://github.com/pa001024/dna-builder/tree/master/.agents/skills/dob-skill-creator into .gemini/skills/dob-skill-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dob-skill-creator", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install pa001024/dna-builder dob-skill-creatorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add pa001024/dna-builder --skill dob-skill-creator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/pa001024/dna-builder.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/dob-skill-creator .github/skills/dob-skill-creator && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "dob-skill-creator" agent skill from https://github.com/pa001024/dna-builder/tree/master/.agents/skills/dob-skill-creator into .github/skills/dob-skill-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dob-skill-creator", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add pa001024/dna-builder --skill dob-skill-creator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install pa001024/dna-builder dob-skill-creator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pa001024/dna-builder.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/dob-skill-creator .opencode/skills/dob-skill-creator && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "dob-skill-creator" agent skill from https://github.com/pa001024/dna-builder/tree/master/.agents/skills/dob-skill-creator into .opencode/skills/dob-skill-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dob-skill-creator", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
dob-skill-creator创建 / 修改 dna-builder 的远端下发技能(server/skills/<技能名/SKILL.md,由服务端实时打包下发给资料检索 Agent 与配装助手)。当需要新增一个给 Agent 用的领域技能(黑话表、机制读法、检索口径、判据清单…)、调整已有技能正文、或排查「技能不生效 / 描述没更新 / 下发被跳过」时使用。注意:server/skills/(下发库)与…
Dob Skill Creator is an agent skill from pa001024/dna-builder. 创建 / 修改 dna-builder 的远端下发技能(server/skills/<技能名/SKILL.md,由服务端实时打包下发给资料检索 Agent 与配装助手)。当需要新增一个给 Agent 用的领域技能(黑话表、机制读法、检索口径、判据清单…)、调整已有技能正文、或排查「技能不生效 / 描述没更新 / 下发被跳过」时使用。注意:server/skills/(下发库)与 .agents/skills/(本机 agent 技能)是两套东西,别混。
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Skill authoring. The repository describes itself as: 二重螺旋构筑模拟器 Duet Night Abyss Builder. The licence is MIT.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 0a808c9. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
bunjqFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Dob Skill Creator loads about 2.2k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 434 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from pa001024/dna-builder at commit 0a808c9, republished under its MIT licence (© pa001024). 434 words, ~2,160 tokens.
.claude/skills/dob-skill-creator/SKILL.md (or your agent's skills folder).dna-builder 里有两套技能,职责完全不同 —— 动手前先确认你要改哪一套:
| 下发技能(本技能管这套) | 本机 agent 技能 | |
|---|---|---|
| 位置 | server/skills/<技能名>/SKILL.md | .agents/skills/<名>/SKILL.md |
| 给谁看 | 资料检索 Agent / 配装助手(线上模型) | 你(本机编码 agent) |
| 怎么分发 | 服务端实时打包 zip → 客户端落盘 → 模型用 skill 加载 | 本地直接读 |
| 内容形态 | 面向模型的领域知识与检索口径 | 面向编码 agent 的操作手册(可含脚本、命令) |
| 版本管理 | 主仓 git,改文件即改技能 | 同左 |
判断依据:内容主要是「跑脚本 / 执行命令 / 改仓库代码 / 访问文件系统」这类你(本机 agent)的操作步骤
→ 那是 .agents/skills/。内容主要是「一份对照表 / 一段口径 / 一套读法 / 一批判据」这类给模型的知识
→ 才是 server/skills/。
⚠️ 注意 server/skills/ 的技能会同时下发给两个能力面不同的 Agent(见铁律 1):
配装助手有 run_code 沙盒,资料检索 Agent 没有 —— 写正文前先想清楚这条内容服务谁。
机制细节见 .agents/docs/agent-skills.md;库自带说明见 server/skills/README.md。
下发技能同时服务两个 Agent,工具面不一样:| Agent | 独有 | 共同没有 |
|---|---|---|
| 资料检索 Agent | 检索工具(read_entry / query_module_entries / search_data / explain_damage / search_story / read_story / list_* / ask_user,+rag_search) | 真实文件系统、网络 |
| 配装助手 | 检索工具 + run_code(build 沙盒,可读当前构筑 / 查数据 / 跑计算)+ 配装页 UI 工具 | 真实文件系统、网络 |
⇒ 一个技能要在两种能力面下都不出错。 判断分两种:
run_code 跑一段代码比较方案」)→ 必须显式限定适用方
(在正文里写清「这条仅适用于配装助手,资料检索 Agent 请改用 X」),否则资料检索 Agent 拿到会照做、然后失败。⚠️ 反过来说也一样:不要替配装助手说「你没有算力」 —— 它有 run_code。
技能的正文会被两个 Agent 都读到,任何「你没有 X」式的断言,只要对其中一方不成立,就是错误信息,
会干扰它对自己能力的判断。能写的是「该用哪个工具 / 读哪个字段」,不是「你有没有某种能力」。
自检一句话:这条指令,两个 Agent 各自用手上的工具能完成吗? 只有一方能 → 标明适用方。
技能里的每个数值 / 术语 / id / 路径,都要有明确的取数来源——否则模型会把它当"已知事实"复述给用户, 而用户一去页面核对就对不上。
read_entry 的 技能字段(值本身必须与数据包一致)。技能术语解释 的原文。query_module_entries 返回的 path 一致(如 /db/char/1101)。outputs/ 里的脚本或旧稿 —— 脚本可能有错、口径可能已改,必须用下面这个工具复现一遍,
必要时再回数据包(src/data/d/*.data.ts)核对。权威取数工具:bun tools/agent-exec.ts(仓库自带,不接模型、不花 token、不联网)。
它跑的就是线上 Agent 的工具实现 —— 同一份 createDbRetrievalTools 装配、同一份检索层,
所以它打印出来的就是模型会看到的那份结果。核对事实、确认字段名与工具名、判断两个 Agent 的工具面,都以它为准:
bun tools/agent-exec.ts --list # 模型能看到哪些工具、参数叫什么
bun tools/agent-exec.ts read_entry '{"module":"mod","name":"充盈·巧力"}' # 核对倍率 / 术语 / 投影字段名(= 模型看到的 fields)
bun tools/agent-exec.ts read_entry '{"module":"weapon","name":"血染织羽"}' # 尾部 selectableFields = fields 没覆盖、但能用 select 查的字段
bun tools/agent-exec.ts query_module_entries '{"module":"mod","keyword":"技能威力","mode":"grep"}' # 按字段找条目
bun tools/agent-exec.ts explain_damage '{"keyword":"充盈"}' # 机制术语与结算步骤原文
bun tools/agent-exec.ts list_data_modules --profile db # 资料检索 Agent 的模块面(默认)
bun tools/agent-exec.ts list_data_modules --profile build # 配装助手的检索子集(6 个模块)read_entry 的 fields),--list 与 selectableFields 才是可写进技能的名字来源。src/data/d/*.data.ts 的原始结构:技能里指路要写投影里的字段名
(例:魔之楔写 词条属性(满级) / 效果(满级) / 效果(1级),而不是数据包内部结构名)。--profile build 里少掉的模块(剧情、读物、NPC…)就是配装助手查不到的,
涉及这些模块的指令必须限定适用方(见铁律 1)。--json 出原文便于管道(| jq);--lang en|jp|kr|fr|tc 核对多语言口径;--max <n> 只截默认输出;
--script <file.json> 批量、无参数进交互模式。完整用法见 --help。src/utils/db-search.ts / src/api/agent/tools/* 之后更要跑它 —— 技能里写的取数路径一旦失效,
线上模型是静默查错的(把查不到当成没有),本地跑一遍才能发现。技能的价值 = 它补上了模型靠自己拿不到的部分。分两类,别写错方向:
read_entry 直接能读)→ ❌ 不要抄进技能。
例:机制名词的官方定义、溯源数组原文、灾厄熔炼的逐档文案、技能描述 —— 让模型自己用工具读。
抄进技能只会:① 占上下文;② 与数据包产生第二份事实,版本更新后两边打架。衰朽 每 1.0 秒 10%」两条散点原文,
换算成「掉血上限 14%/s + 10%/s = 24%/s」 —— 数据包里没有 24 这个数,只有散点。自检一句话:这条内容,模型用工具读得到吗?读得到就别抄;读不到的推导就留。
^[a-z0-9][a-z0-9-]*$,≤64 字符。
frontmatter 里的 name 只为阅读,清单与下发的 id 用目录名。server/skills/<技能名>/
├── SKILL.md # 必需,且在根级
└── references/ # 可选,按需加载的补充资料(正文里用路径引用)索引型技能(覆盖一大批同类条目时用,例:全角色攻略、每种武器的口径、每张地图的路线): 把
SKILL.md写成索引表(条目 → 关键字段 → 文件路径 + 「什么时候读它」), 细节拆进references/<条目名>.md,每个条目一个文件。 ⚠️ 文件数上限 50(含 SKILL.md)——条目再多也要按主题合并,或把 references 也做成一层索引。 ⚠️ 每条 references 正文里保留同一套小节标题,模型才能横向对比;条目名与query_module_entries的path/名称对齐,别用自己起的简称。
SKILL.md 的 frontmatter(服务端只认 --- 包裹的扁平静态键值,不解析嵌套 / 多行块):
---
name: <技能名,与目录名一致便于阅读>
description: <必填,≤1024 字。写清「干什么 + 什么时候用 + 触发关键词」。这一段是模型唯一的触发依据。>
whenToUse: <可选,补充触发场景>
version: <可选,信息性版本号>
enabled: <可选,false 时清单与下载都不出>
sortOrder: <可选,数字,小者靠前>
---
# 标题
正文……⚠️
description是触发开关:模型就是靠它决定要不要skill加载。写含糊了技能等于不存在。 建议句式:「<这是什么>。当<什么场景>、<什么提问>时使用。触发词:<词1>、<词2>。」 frontmatter 在注入模型前会被剥掉,所以元数据别在正文里重复描述。
推荐骨架(按需删减,别硬凑):
写作纪律:
战技 / 终结技 / 普攻 / 武器输出 / 技能输出),不要「E 技能 / 大招 / 平A」。用服务端同一份逻辑跑,确保目录合法、能打包、description 不超限。
写到项目根 .tmp/verify-skill.ts 再 bun 跑(临时文件放 .tmp):
import { readdir, readFile, stat } from "node:fs/promises"
import { join, relative } from "node:path"
import { deriveSkillMeta } from "../server/src/util/skill-source"
const ROOT = join(import.meta.dir, "..", "server", "skills")
for (const dir of await readdir(ROOT, { withFileTypes: true })) {
if (!dir.isDirectory()) continue
const base = join(ROOT, dir.name)
const entries: Array<{ path: string; size: number; content: Uint8Array }> = []
const walk = async (cur: string) => {
for (const e of await readdir(cur, { withFileTypes: true })) {
const abs = join(cur, e.name)
if (e.isDirectory()) { await walk(abs); continue }
entries.push({ path: relative(base, abs).replace(/\\/g, "/"), size: (await stat(abs)).size, content: await readFile(abs) })
}
}
await walk(base)
const r = deriveSkillMeta(dir.name, entries, Date.now())
console.log("error" in r ? `❌ ${dir.name}: ${r.error}` : `✅ ${dir.name} size=${r.meta.packageSize}B desc=${r.meta.description.length}字`)
}另外必须核对技能里的事实:每一个数值 / id / 术语 / 路径,先用 bun tools/agent-exec.ts 跑一遍
(见铁律 2 的权威取数工具),确认「模型用工具确实读得到、且与你写的一致」;投影没覆盖的底层结构
再回数据包(src/data/d/*.data.ts)对一遍。这是最容易省掉、也最不该省的一步(见铁律 2)。
server/skills/README.md 的「当前技能」表加一行(技能名 + 一句话说明)。
server/src/util/skill-source.ts 的 deriveSkillMeta)| 项 | 限制 |
|---|---|
| 技能名(目录名) | ^[a-z0-9][a-z0-9-]*$,≤64 字符 |
| 描述 | 必填,≤1024 字符 |
| 文件数 | ≤50 |
| 单文件 | ≤1MB |
| 全部文件合计 | ≤8MB |
| 根级入口 | 必须有 SKILL.md |
| 忽略 | 隐藏文件(. 开头)、__MACOSX |
不合法的目录只告警并跳过,不影响其它技能 —— 所以「技能没出现」时,
先按上表查目录名 / description / 入口文件。
| 现象 | 原因 |
|---|---|
| 技能不在清单里 | 目录名非法 / 缺根级 SKILL.md / description 缺失或超 1024 字 / enabled: false |
| 改了描述但清单没变 | 库层缓存键是「路径+大小+mtime」指纹,正常改文件会失效;若没生效先确认保存了文件 |
| 模型不加载技能 | description 没写触发场景与关键词,模型判断不出该用它 |
| 模型照做却报错 | 技能里写的指令只有另一方能做到、又没标明适用方(见铁律 1) |
| 用户核对不上数值 | 技能里的事实没回数据包核对,或抄了过期的旧稿(见铁律 2) |
| 技能里的字段名 / 工具名模型用不了 | 照着数据包原始结构或旧稿写的,没先用 bun tools/agent-exec.ts 校对投影里的真实名字(见铁律 2) |
| 目录内容变了但拿到的还是旧包 | 客户端按清单 sha 内容寻址缓存;确认服务端已重扫(改文件即时生效),必要时让客户端重新拉清单 |
❌ 先跑 .tmp/recalc.ts 复现线上构筑,逐项消融后交付可导入 BD JSON。
→ 这条只有配装助手(有 run_code)做得到;没标明适用方,资料检索 Agent 会照做然后失败。
❌ 你没有代码执行能力,不要算数值。
→ 对配装助手不成立(它有 run_code)。技能正文两个 Agent 都读,别写这种「你没有 X」的断言。
❌ [执行者]状态中,[潜入夜色]替换为[暗影奔袭],每隔 3 秒转化攻击力……
→ 原文复述:read_entry 的「技能术语解释」直接能读到,抄进技能只是多一份会过期的事实。
❌ 角色强度 T0,属克下 66 亿,建议抽取。
→ 裸结论:数值会随版本失效,且没有取数来源可核对。
❌ 详细步骤见 charbuild-dps-ablation 技能。
→ 那是本机 agent 技能,不在下发给模型的库里面,模型根本读不到。
❌ 「魔之楔的 `词条属性` 里能查到充盈威力 +300%」
→ 字段名凭印象写的。先用 bun tools/agent-exec.ts read_entry '{"module":"mod","name":"充盈·巧力"}' 核对:
投影里的名字是 `词条属性(满级)`(带等级后缀),另外 `selectableFields` 里才出现 `充盈威力`。
© pa001024, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .agents/skills/dob-skill-creator of pa001024/dna-builder.
Open the folder on GitHubat commit 0a808c9
Dob Skill Creator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Dob Skill Creator this skillpa001024/dna-builder | 136 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Skill CreatorAzure/azqr | 795 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 | |
| Claude Code Skill Developer Guidediet103/claude-code-infrastructure-showcase | 10k | 11 repos | ~3.5k | Automated safety check: Pass | MIT | |
| Darwin Skill Optimizeralchaincyf/darwin-skill | 6.2k | 1 repos | ~4.7k | Automated safety check: Pass | MIT | |
| Claude Code Command Developmentanthropics/claude-plugins-official | 38k | 10 repos | ~4.8k | Automated safety check: Pass | Apache-2.0 | |
| Claude Code Plugin Structureanthropics/claude-plugins-official | 38k | 10 repos | ~3.4k | Automated safety check: Pass | Apache-2.0 |
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
diet103/claude-code-infrastructure-showcase
A guide to creating and managing Claude Code skills with auto-activation: skill-rules.json triggers, hooks, enforcement levels, YAML frontmatter and progressive disclosure.
alchaincyf/darwin-skill
Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.
anthropics/claude-plugins-official
Explains how to write Claude Code slash commands: Markdown files with YAML frontmatter, arguments, file references, bash context and interactive prompts.
anthropics/claude-plugins-official
Explains the directory layout, plugin.json manifest and component organization of a Claude Code plugin, including auto-discovery and portable paths.
rohitg00/ai-engineering-from-scratch
Evaluates an Agent Skill bundle before release for structure, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity and host portability.
pa001024/dna-builder
This skill documents how to use the fmodel-mcp toolkit (a CUE4Parse-based .NET CLI plus a thin Python MCP server) to inspect and export Unreal Engine game assets — pak files, textures, meshes…
pa001024/dna-builder
使用 Bun 1.4 内置的 Bun.WebView 无头浏览器对前端页面(Vue/Vite 等)做端到端冒烟与交互测试。当需要加载页面、真实点击、读取 DOM/应用状态、做断言、截图归档,或对本地开发服务器/静态站点做零依赖的浏览器级验证、可视化巡检、交互回归测试时,应使用本技能。
pa001024/dna-builder
制作与调试 Unreal Engine 4.27 游戏的 pak 模组(模型/网格/资产换皮,如《二重螺旋》Duet Night Abyss)。两条路线:编辑器烘焙(Blender 自由改模型 → UE4.27 cook → pak)与二进制替换(改写已烘焙 .uasset 的导出名/载荷)。当需要「把 A 的模型换成 B 的模型」「让模型能自由导入 Blender…
pa001024/dna-builder
给 dna-builder 里任意角色从零推一套「最优构筑」(BD)的通用方法论:读角色机制 → 辅助候选排列组合 → buff 组(含光环型海妖 / 角色专属如大冲击)→ 定计算方向 → 魔灵与潜质 → 必带 MOD → 用 autoBuild 跑一遍并剔除不合理件 → 消融实验。当需要「给某个角色配一套最优 BD」「这个角色带什么辅助/队友最强」「跑一下 XX…
pa001024/dna-builder
用 V8 CPU profile 定位 JS/TS 热点函数,并用「同进程交替 A/B + best(min) 统计量 + checksum 锚点」的微基准方法安全地做性能优化。当需要优化计算热点、怀疑某函数耗时占比高、想评估某个优化(含 Wasm/SIMD 等加速路径)是否真有收益、或要建立可回归的性能基准时使用。
pa001024/dna-builder
《二重螺旋》新手开荒指南(校对至 1.6 版本)。含分阶段开荒流程(历练 35 前 / 35~45 / 45~60 / 60 后)、前期角色与武器获取清单、角色获取循环(深渊→周本→密函商店)、魔之楔六大系列与金 Mod 升级口径、减负活动、灾厄武器四把(棘刺绝响 / 无止无休 / 权火将熄 / 血染织羽)的两条刷取路线与 1.6 配队(暗队 /…
Categories
创建 / 修改 dna-builder 的远端下发技能(server/skills/<技能名/SKILL.md,由服务端实时打包下发给资料检索 Agent 与配装助手)。当需要新增一个给 Agent 用的领域技能(黑话表、机制读法、检索口径、判据清单…)、调整已有技能正文、或排查「技能不生效 / 描述没更新 / 下发被跳过」时使用。注意:server/skills/(下发库)与…. Dob Skill Creator is an agent skill from pa001024/dna-builder.
Dob Skill Creator fits situations like: tasks that involve Skill authoring.
Run `npx skills add pa001024/dna-builder --skill dob-skill-creator -a claude-code`. Or copy the skill folder (.agents/skills/dob-skill-creator in pa001024/dna-builder) into .claude/skills/dob-skill-creator in your project. Claude Code loads it when a task matches its description.
Run `npx skills add pa001024/dna-builder --skill dob-skill-creator -a codex`. Or copy the skill folder (.agents/skills/dob-skill-creator in pa001024/dna-builder) into .agents/skills/dob-skill-creator in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pa001024/dna-builder --skill dob-skill-creator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dob-skill-creator, .gemini/skills/dob-skill-creator, .github/skills/dob-skill-creator and .opencode/skills/dob-skill-creator in your project.
Going by SKILL.md and its folder, Dob Skill Creator needs the command-line tools its instructions call (bun and jq).
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Dob Skill Creator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.2k tokens (SKILL.md is roughly 8.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Dob Skill Creator: Skill Creator (Azure/azqr, 795 stars), Claude Code Skill Developer Guide (diet103/claude-code-infrastructure-showcase, 10k stars), Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars) and Claude Code Command Development (anthropics/claude-plugins-official, 38k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
pa001024 (a GitHub user) maintains it in pa001024/dna-builder, which has 136 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 8, 2026.
Source: pa001024/dna-builder on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.