Bio Single Cell Hashing Demultiplexing
GPTomics/bioSkills
Assign cells to their sample of origin from cell or nucleus hashing (CITE-seq HTOs, MULTI-seq lipid/cholesterol tags, CellPlex CMOs) and call cross-sample doublets using Seurat…
A skill your agent uses when 在 Nucleus V2 目标仓库中基于需求设计与特性拆解输入开发一个或多个特性。
MITAuto-check passed
Install Feature Development
$ npx skills add protect-my-hair/nucleus-marketplace --skill feature-development -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install protect-my-hair/nucleus-marketplace feature-development --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/protect-my-hair/nucleus-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/nucleus/skills/feature-development .claude/skills/feature-development && 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 "feature-development" agent skill from https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/feature-development into .claude/skills/feature-development/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-development", 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/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/feature-developmentType 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 protect-my-hair/nucleus-marketplace --skill feature-development -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install protect-my-hair/nucleus-marketplace feature-development --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/nucleus/skills/feature-development .agents/skills/feature-development && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "feature-development" agent skill from https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/feature-development into .agents/skills/feature-development/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-development", 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 protect-my-hair/nucleus-marketplace --skill feature-development -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install protect-my-hair/nucleus-marketplace feature-development --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/nucleus/skills/feature-development .cursor/skills/feature-development && 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 "feature-development" agent skill from https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/feature-development into .cursor/skills/feature-development/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-development", 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/protect-my-hair/nucleus-marketplace.git --path plugins/nucleus/skills/feature-development--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 protect-my-hair/nucleus-marketplace --skill feature-development -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install protect-my-hair/nucleus-marketplace feature-development --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/nucleus/skills/feature-development .gemini/skills/feature-development && 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 "feature-development" agent skill from https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/feature-development into .gemini/skills/feature-development/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-development", 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 protect-my-hair/nucleus-marketplace feature-developmentInstalls 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 protect-my-hair/nucleus-marketplace --skill feature-development -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/nucleus/skills/feature-development .github/skills/feature-development && 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 "feature-development" agent skill from https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/feature-development into .github/skills/feature-development/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-development", 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 protect-my-hair/nucleus-marketplace --skill feature-development -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install protect-my-hair/nucleus-marketplace feature-development --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/nucleus/skills/feature-development .opencode/skills/feature-development && 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 "feature-development" agent skill from https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/feature-development into .opencode/skills/feature-development/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "feature-development", 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.
Facts
- Skill name
feature-development- GitHub stars
- 164
- Token cost
- ~1.3k tokens
- SKILL.md length
- 350 words
- Files
- 7 (incl. scripts, references, assets)
- Skills in repo
- 18
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when 在 Nucleus V2 目标仓库中基于需求设计与特性拆解输入开发一个或多个特性。
- Works in 11 steps: 读取需求设计产物：读取需求实现方案、拆解结果和… → 读取特性拆解输入：读取 requirement-decomposition… → 确认需求分支：调用或执行 requirement-branch；缺分支授权时… → …
- 在 Nucleus V2 目标仓库中基于需求设计与特性拆解输入开发一个或多个特性
- SKILL.md covers 核心原则, Checklist, 本 Skill 解决什么 and 必须先做, plus 4 more sections
- Runs Python scripts from its folder
What it does
Feature Development is an agent skill from protect-my-hair/nucleus-marketplace. Use when 在 Nucleus V2 目标仓库中基于需求设计与特性拆解输入开发一个或多个特性。
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/feature-development-task-list-template.md` and `assets/nucleus-feature-development-task-list.schema.json`).
The repository describes itself as: Nucleus — Claude Code / Codex 工作流插件，确保 AI 编码产出结构可信、边界可审计、过程可追溯. The licence is MIT.
When your agent uses it
- 在 Nucleus V2 目标仓库中基于需求设计与特性拆解输入开发一个或多个特性
Example prompts
- “/feature-development”
Requirements
- Python 3
Workflow steps
11 steps, taken from the first numbered list in SKILL.md.
- 读取需求设计产物：读取需求实现方案、拆解结果和 .nucleus/context/.json；不把上游评审是否文件化作为本阶段 input 阻塞。
- 读取特性拆解输入：读取 requirement-decomposition 输出的特性路径、优先级、依赖和 feature-doc-design 输入。
- 确认需求分支：调用或执行 requirement-branch；缺分支授权时 ALERT_AND_BLOCK。
- 读取现有特性树：读取目标仓库 docs/features/** 既有结构，避免跨特性误写。
- 创建宿主特性任务包：为每个特性创建独立 task 包；当前特性未完成前不得开始下一个特性。
- 执行当前特性设计：调用 feature-doc-design 直接写入 docs/features/** 待评审特性文档，先按 _shared/references/subagent-precheck-protocol.md 完成 subagentPreReview；通过后按…
- 生成并确认实施计划：设计评审通过后生成实施计划，先按 _shared/references/subagent-precheck-protocol.md 完成 subagentPreReview；通过后按…
- 按计划实现并验证：每个 task 写源码、测试或样式前，先重读 specAnchor.sourceEvidencePaths 指向的 specs、UI 设计证据和实施计划，再补测试或测试资产，再实现当前特性覆盖内容，并运行计划声明的验证命令。若计划…
- 完成多维评审：调用 multi-review 做 code-review、方案一致性评审和计划满足度评审。
- 整改并复核：整改评审意见或写明不采纳理由，再完成复核。
- 收口当前特性证据：确认当前特性证据完整且无越界改动后，才允许解锁下一个特性。
What it can do on your machine
Read from SKILL.md and the folder at commit 3c82085. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Feature Development loads about 1.3k tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 18 tokens; SKILL.md has 350 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.
Safety
Auto-check passed
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); the scripts in this folder are not scanned.
SKILL.md
The full file from protect-my-hair/nucleus-marketplace at commit 3c82085, republished under its MIT licence (© protect-my-hair). 350 words, ~1,325 tokens.
Download SKILL.mdSave it as
.claude/skills/feature-development/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.- name
- feature-development
- description
- Use when 在 Nucleus V2 目标仓库中基于需求设计与特性拆解输入开发一个或多个特性。
特性开发
前置：使用本 Skill 前，先按
using-nucleus完成 Nucleus 入口识别（Claude Code 会话由插件 SessionStart hook 自动注入该纪律）。
核心原则
特性开发是按特性分组的 task / todo 编排，不是脚本循环，也不是一个大开发任务。
<HARD-GATE>
未读取需求设计产物和特性拆解结果，未确认需求分支，或当前特性缺少设计评审、实施计划、独立评审、整改复核事实时，不得进入对应下游写入或解锁动作。当前特性涉及 UI，且 docs/ui-design/**、Pencil 文件、ui-prototype.md 或用户明确设计稿存在时，未把相关 UI 设计源纳入实施计划、实现任务和完成评审证据前，不得写 UI 源码或把当前特性标记完成；仅发现仓库候选设计源时，未完成人工相关性确认前不得写 UI 源码。
当前特性实施计划缺少 developmentSpecs，或目标仓库 docs/specs/** 规范缺失但没有 setup gap 处理结论时，不得写源码、测试或把当前特性标记完成。
当前特性实施计划缺少 specAnchor，或上下文压缩 / 会话恢复 / 阶段切换后没有从磁盘重读 .nucleus/runs/<workflowRunId>/spec-anchor.json 及其 sourceEvidencePaths 时，不得写源码、测试、样式或请求完成评审。
未创建宿主 todo/task 任务包，不得执行 feature-doc-design、feature-development-prepare、feature-implementation、multi-review 或进入下一个特性。
每个特性设计评审、实施计划确认和特性完成评审请求发给人之前，必须先按 _shared/references/subagent-precheck-protocol.md 调度独立 reviewer 完成 subagentPreReview；未取得“材料可提交人工审查”结论时，不得请求人工评审通过。
</HARD-GATE>
Checklist
启动本 Skill 后，必须先为以下每一项创建宿主 todo/task，并按顺序执行；Codex 使用计划 / 任务工具，Claude Code 使用 TodoWrite 或等价宿主 todo。每完成、阻塞或等待一项，都必须逐项更新状态。.nucleus/runs/<workflowRunId>/feature-development/tasks.json 和 tasks.md 只是这些宿主任务包的镜像证据，不能替代宿主任务、设计评审、计划确认、review、整改复核或 PMS 状态。
- 读取需求设计产物：读取需求实现方案、拆解结果和
.nucleus/context/<workflowRunId>.json；不把上游评审是否文件化作为本阶段 input 阻塞。 - 读取特性拆解输入：读取
requirement-decomposition输出的特性路径、优先级、依赖和feature-doc-design输入。 - 确认需求分支：调用或执行
requirement-branch；缺分支授权时ALERT_AND_BLOCK。 - 读取现有特性树：读取目标仓库
docs/features/**既有结构，避免跨特性误写。 - 创建宿主特性任务包：为每个特性创建独立 task 包；当前特性未完成前不得开始下一个特性。
- 执行当前特性设计：调用
feature-doc-design直接写入docs/features/**待评审特性文档，先按_shared/references/subagent-precheck-protocol.md完成subagentPreReview；通过后按_shared/references/interaction-format.md的确认型格式呈现给人评审，未通过时修订设计。 - 生成并确认实施计划：设计评审通过后生成实施计划，先按
_shared/references/subagent-precheck-protocol.md完成subagentPreReview；通过后按_shared/references/interaction-format.md的确认型格式请求确认，未确认时不得写源码或测试。计划必须包含specAnchor和developmentSpecs，列出docs/specs/**规范证据、适用 rules、缺失状态、facts manifest hash、reload policy 和 setup gap 处理要求。当前特性存在相关 UI 设计源时，计划必须包含 UI 设计源发现证据、Pencil frame / UI 状态映射、公共组件 / 公共样式契约和视觉证据路径；仅发现候选设计源时，计划必须要求人工确认相关性。 - 按计划实现并验证：每个 task 写源码、测试或样式前，先重读
specAnchor.sourceEvidencePaths指向的 specs、UI 设计证据和实施计划，再补测试或测试资产，再实现当前特性覆盖内容，并运行计划声明的验证命令。若计划uiDesign.applicability=required，必须先导出或读取设计 frame，按 frame / 状态映射实现，并采集浏览器截图、人工视觉证据或等价 UI 对照证据。 - 完成多维评审：调用
multi-review做 code-review、方案一致性评审和计划满足度评审。 - 整改并复核：整改评审意见或写明不采纳理由，再完成复核。
- 收口当前特性证据：确认当前特性证据完整且无越界改动后，才允许解锁下一个特性。
本 Skill 解决什么
本 Skill 只负责编排特性开发任务：
- 读取需求设计和特性拆解输入。
- 确认需求分支。
- 为每个特性创建 task / todo 任务包。
- 规定任务顺序、停点和证据。
- 调用对象型 Skill 完成具体设计、计划、实现、评审和收口。
它不替代 feature-doc-design、不替代实施计划、不开启脚本自动开发、不替人评审 PR、不批准合入或发布。
必须先做
- 读取
.nucleus/context/<workflowRunId>.json。 - 读取需求实现方案和
requirement-decomposition的特性拆解结果。 - 记录本阶段后续写入动作需要引用的人工事实字段，但不把上游评审文件化状态作为 input。
- 调用或执行
requirement-branch的分支检查纪律。 - 读取目标仓库
docs/features/**既有结构。 - 创建宿主 todo/task 列表，并逐项更新状态。
Show full SKILL.md (148 more words)Show less
单个特性任务包
每个特性必须按以下任务顺序执行：
- 读取当前特性输入和关联需求设计产物。
- 确认当前仍在需求分支，且工作区没有污染当前特性的无关改动。
- 执行
feature-doc-design，生成或更新当前特性的docs/features/**待评审文档。 - 设计材料先按
_shared/references/subagent-precheck-protocol.md完成subagentPreReview，确认材料可提交人工审查后再呈现并等待人工评审通过。 - 基于当前特性文档和输入生成实施计划；实施计划输出后再进入本阶段计划确认门禁。
- 实施计划先按
_shared/references/subagent-precheck-protocol.md完成subagentPreReview，确认材料可提交人工审查后再呈现并等待确认。 - 读取实施计划
specAnchor、.nucleus/runs/<workflowRunId>/spec-anchor.json、developmentSpecs和.nucleus/runs/<workflowRunId>/development-specs-evidence.json；存在docs/specs/rules/**时先读适用规则，缺失时确认 setup gap 已补齐或已有人工计划豁免。 - 上下文压缩、恢复、切换 task、写源码前、写 UI 前和进入评审前，都必须重读 spec anchor 的
sourceEvidencePaths，确认factsManifestHash未 stale；stale 时回到实施计划评审或重新生成 anchor。 - 如果实施计划声明
uiDesign.applicability=required，先完成 UI 设计源到 route / modal / tab / state 的映射，并确认公共组件 / 公共样式读取对象；缺映射或证据路径时回到计划评审。如果声明candidate-found，先取得候选设计源是否相关的人工确认；相关则回到计划补齐 required 映射，无关则记录理由后按公共组件 / 既有样式实现。 - 按计划先补测试或测试资产，再实现当前特性覆盖内容。
- 运行计划声明的验证命令；UI 设计源存在时，同时采集计划声明的截图、Pencil frame 导出或人工视觉对照证据。
- 调用
multi-review做 code-review、方案一致性评审、计划满足度评审和 spec compliance 复核。 - 整改评审意见，或写明不采纳的技术理由和证据。
- 复核整改结果。
- 收口当前特性证据。
当前特性未完成全部任务，不得开始下一个特性。
STOP 点
- 未读取需求设计产物和特性拆解结果：
ALERT_AND_BLOCK。 - 当前不在需求分支，且没有明确创建或切换授权：
ALERT_AND_BLOCK。 - 当前特性未完成
feature-doc-design：不得写实施计划、源码或测试。 - 特性设计未人工评审通过：不得写实施计划、源码或测试。
- 实施计划未生成或未确认：不得开发。
- 实施计划缺少
specAnchor，或实现前没有重读 spec anchor 及其 source evidence：不得开发。 - 实施计划缺少
developmentSpecs，或缺docs/specs/**处理结论：不得开发。 - UI 设计源存在但实施计划没有 UI 映射、公共组件 / 公共样式契约或视觉证据路径：不得写 UI 源码。
- 仅发现候选 UI 设计源但缺人工计划相关性确认：不得写 UI 源码。
- UI 实现缺少计划声明的截图、Pencil frame 对照或公共组件 / 样式契约复核：不得进入特性完成评审。
- 发现计划不成立或 scope 变化：停住，回到计划或特性设计评审节点。
- code-review、方案一致性评审、计划满足度评审缺任一项：不得进入下一个特性。
- 完成评审前没有按 changed files 重新计算 applicable rules -> evidence coverage：不得进入下一个特性。
- 评审意见未整改并复核：不得进入下一个特性。
- 所有特性未全部完成：不得准备 MR/PR。
Runtime 边界
scripts/feature_development.py 只能生成或校验 task list 证据。它不得执行开发、写源码、写测试、写正式特性文档、创建提交、创建 MR/PR、批准评审或发布。
证据
任务清单可写入 .nucleus/runs/<workflowRunId>/feature-development/tasks.json 和 tasks.md，仅作宿主任务包的镜像证据，只证明任务被编排或校验，不证明宿主任务已逐项执行。
© protect-my-hair, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 6 other files (scripts, references, assets) in plugins/nucleus/skills/feature-development of protect-my-hair/nucleus-marketplace.
- SKILL.md
- agents/openai.yaml
- assets/feature-development-task-list-template.md
- assets/nucleus-feature-development-task-list.schema.json
- references/blocker-matrix.md
- references/task-orchestration.md
- scripts/feature_development.py
Open the folder on GitHubat commit 3c82085
Compare with similar skills
Feature Development 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 |
|---|---|---|---|---|---|---|
| Feature Development this skillprotect-my-hair/nucleus-marketplace | 164 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Bio Single Cell Hashing DemultiplexingGPTomics/bioSkills | 1.2k | 1 repos | ~4.2k | Automated safety check: Pass | MIT | |
| Bio Single Cell Cnv InferenceGPTomics/bioSkills | 1.2k | 1 repos | ~4.7k | Automated safety check: Pass | MIT | |
| Scenario Maya Fxscenario-labs/skills | 946 | — | ~5.3k | Automated safety check: Pass | MIT | |
| Cellpose Cell Segmentationjaechang-hits/SciAgent-Skills | 374 | 1 repos | ~3.5k | Automated safety check: Pass | BSD-3-Clause | |
| Game Concept ArchitectDY-2026/GameDesignOS | 415 | — | ~2.1k | Automated safety check: Pass | MIT |
Similar skills
Bio Single Cell Cnv Inference
GPTomics/bioSkills
Infer large-scale copy-number alterations from tumor single-cell or single-nucleus RNA-seq to separate malignant from normal cells and call subclones, using inferCNV, copyKAT, Numbat, and SCEVAN.
Scenario Maya Fx
scenario-labs/skills
A skill your agent uses when a Maya task involves simulation or procedural effects: nCloth or Nucleus (a cape, skirt, flag or garment on an animated character, cloth through the body, jittery or…
Cellpose Cell Segmentation
jaechang-hits/SciAgent-Skills
DL cell/nucleus segmentation for fluorescence and brightfield microscopy.
Game Concept Architect
DY-2026/GameDesignOS
将一句话游戏创意扩展为可验证的游戏设计蓝图：从 concept seed、玩家动词、design nucleus options、动作-目标对齐、assumption ledger、玩家承诺、核心循环、scope gate 到 validation plan。适用于真实项目、私有项目、客户项目、公开案例或 synthetic cases；仓库示例发布规则由 CONTRIBUTING.md 管理。
Lattice
yogthos/Matryoshka
Analyze large files (500 lines) using handle-based Nucleus queries for 97% token savings.
More from protect-my-hair/nucleus-marketplace
All 18 skills in this repoNucleus Delivery Evidence Closure
protect-my-hair/nucleus-marketplace
Collects prior Nucleus task evidence into a candidate-only delivery closure package and PR/MR draft text, blocking if any feature's design, review or verification evidence is missing.
Nucleus Context Validator
protect-my-hair/nucleus-marketplace
Validates the context file for a Nucleus V2 workflow run, discovers standalone context from explicit input, and writes a blocked result when required context is missing.
Nucleus Session Binding Report
protect-my-hair/nucleus-marketplace
Collects, freezes and validates a Nucleus V2 session binding report that records the native Claude Code or Codex session ID, transcript path and hash.
Nucleus Result Package Builder
protect-my-hair/nucleus-marketplace
Builds the result.json file for a Nucleus V2 workflow run from its context, gates, blockers and step status, and exits non-zero when the run is blocked.
Defect Intake and RCA Candidates
protect-my-hair/nucleus-marketplace
Checks whether a defect report has enough context to be accepted, then drafts candidate-only root-cause evidence for human review without confirming causes or changing code.
Nucleus Delivery Evidence Finalizer
protect-my-hair/nucleus-marketplace
Combines the evidence from completed Nucleus workflow steps into a final evidence report and result package, without scheduling steps, updating trackers or opening pull requests.
Questions about Feature Development
What does Feature Development do?
A skill your agent uses when 在 Nucleus V2 目标仓库中基于需求设计与特性拆解输入开发一个或多个特性。. Feature Development is an agent skill from protect-my-hair/nucleus-marketplace.
When should I use Feature Development?
Feature Development fits situations like: 在 Nucleus V2 目标仓库中基于需求设计与特性拆解输入开发一个或多个特性.
How do I install Feature Development in Claude Code?
Run `npx skills add protect-my-hair/nucleus-marketplace --skill feature-development -a claude-code`. Or copy the skill folder (plugins/nucleus/skills/feature-development in protect-my-hair/nucleus-marketplace) into .claude/skills/feature-development in your project. Claude Code loads it when a task matches its description.
How do I install Feature Development in Codex?
Run `npx skills add protect-my-hair/nucleus-marketplace --skill feature-development -a codex`. Or copy the skill folder (plugins/nucleus/skills/feature-development in protect-my-hair/nucleus-marketplace) into .agents/skills/feature-development in your project. Codex loads it when a task matches its description.
Can I use Feature Development in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add protect-my-hair/nucleus-marketplace --skill feature-development -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/feature-development, .gemini/skills/feature-development, .github/skills/feature-development and .opencode/skills/feature-development in your project.
What does Feature Development need to run?
Going by SKILL.md and its folder, Feature Development needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Feature Development access the network?
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.
Is Feature Development safe to install?
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Feature Development use?
Feature Development is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Feature Development use?
About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 729 tokens, read only when the agent opens those files.
What are the alternatives to Feature Development?
Skills that share tags, products or a category with Feature Development: Bio Single Cell Hashing Demultiplexing (GPTomics/bioSkills, 1.2k stars), Bio Single Cell Cnv Inference (GPTomics/bioSkills, 1.2k stars), Scenario Maya Fx (scenario-labs/skills, 946 stars) and Cellpose Cell Segmentation (jaechang-hits/SciAgent-Skills, 374 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Feature Development?
protect-my-hair (a GitHub user) maintains it in protect-my-hair/nucleus-marketplace, which has 164 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on July 23, 2026.
Source: protect-my-hair/nucleus-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.