Not in the top 1,000 by GitHub stars
SimpleEve/development-skills
Reusable agent skills for end-to-end software delivery, from requirements and implementation to review, testing, and release.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
implement/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
7cfd6ea6e8cc → 7cfd6ea6e8cc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 7cfd6ea6e8cc
No earlier version was observed for comparison.
plan/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
7cfd6ea6e8cc → 7cfd6ea6e8cc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 7cfd6ea6e8cc
No earlier version was observed for comparison.
review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
7cfd6ea6e8cc → 7cfd6ea6e8cc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 7cfd6ea6e8cc
No earlier version was observed for comparison.
spec/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
7cfd6ea6e8cc → 7cfd6ea6e8cc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 7cfd6ea6e8cc
No earlier version was observed for comparison.
test/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
7cfd6ea6e8cc → 7cfd6ea6e8cc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 7cfd6ea6e8cc
No earlier version was observed for comparison.
Verified commit 7cfd6ea6e8ccf8018319a2ab3488cc3d55a6e86a
git clone --filter=blob:none --no-checkout https://github.com/SimpleEve/development-skills.git .hotskills/simpleeve-development-skills && git -C .hotskills/simpleeve-development-skills checkout --detach 7cfd6ea6e8ccf8018319a2ab3488cc3d55a6e86a
# Copy each selected skill directory from .hotskills/simpleeve-development-skills into .claude/skills/<skill-name>/Heat
0.4- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
implement
When your agent uses it
代码实现技能。当用户要求根据 plan 编写代码、实现功能、修复 bug 时使用。触发词包括"实现"、"写代码"、"开发"、"implement"、"fix"、"/implement"。
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
1,065 tokensWhen the skill is activated
Reference documents
4,985 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 核心原则
- 前置条件
- 工作流程
- 编码规范
- 关键约束
Files
../.claude-plugin/marketplace.jsonasset993 bytes../.claude-plugin/plugin.jsonasset499 bytesSKILL.mdcore3,758 bytes../plan/SKILL.mddoc4,602 bytes../review/SKILL.mddoc4,339 bytes../spec/SKILL.mddoc3,705 bytes../test/SKILL.mddoc4,587 bytes
Read SKILL.md
# Implement - 代码实现技能
根据 plan 文档进行代码实现,或根据 test/review 的反馈进行修复。
## 核心原则
1. **严格遵循 Plan**:按照已确认的 `plan.md` 中的 TODO 逐项实现
2. **架构一致**:遵循项目整体既有的架构设计、模块边界与依赖方向
3. **模块化与可扩展**:代码必须模块化,遵循 SOLID 原则和适当的设计模式
4. **最小变更**:只实现 Plan 要求的内容,不做额外的"优化"或"改进"
## 前置条件
- 对应功能的 `plan.md` 必须已存在且状态为"已确认"View the complete source on GitHubplan
When your agent uses it
实施计划技能。当用户要求制定实施计划、拆解任务、做技术方案设计时使用。必须基于已有的 spec 文档。触发词包括"写 plan"、"实施计划"、"任务拆解"、"技术方案"、"/plan"。
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
1,348 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 核心原则
- 前置条件
- 工作流程
- 固定模板
- 关键约束
Files
SKILL.mdcore4,602 bytes
Read SKILL.md
# Plan - 实施计划技能
将已确认的 spec 文档转化为可执行落地的详细实施计划与任务清单。
## 核心原则
1. **不猜测**:代码侧的技术细节遇到不确定的,必须向用户澄清
2. **不模糊**:每个 TODO 子项必须描述清楚做什么、影响哪些文件、验收标准是什么
3. **不写代码**:不写详细实现代码,但可以描述接口签名、数据结构、模块职责
4. **固定产出**:输出到项目既有的需求目录;若无统一约定,建议使用 `spec/<spec-name>/plan.md`
## 前置条件
- 对应功能的 `spec.md` 必须已存在且状态为"已确认"View the complete source on GitHubreview
When your agent uses it
代码审查技能。当用户要求做代码审查、检查代码质量、检查 bug 和风险时使用。触发词包括"review"、"代码审查"、"代码检查"、"review 代码"、"/review"。
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
1,262 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 核心原则
- 前置条件
- 工作流程
- 固定模板
- 关键约束
Files
SKILL.mdcore4,339 bytes
Read SKILL.md
# Review - 代码审查技能
根据 spec 和 plan 文档对代码进行全面审查,产出结构化的审查报告。
## 核心原则
1. **对照文档审查**:严格依据 spec 和 plan 检查功能完整性与正确性
2. **最佳实践审查**:检查代码质量、命名规范、架构合理性
3. **结构化产出**:按 P0/P1/P2 分级,明确区分问题类型
4. **固定产出**:输出到项目既有的需求目录;若无统一约定,建议使用 `spec/<spec-name>/review.md`
## 前置条件
- 对应功能的 `spec.md` 和 `plan.md` 必须已存在View the complete source on GitHubspec
When your agent uses it
需求规格说明技能。当用户要求编写需求、撰写 spec、做需求分析、澄清功能边界时使用。触发词包括"写 spec"、"需求分析"、"需求规格"、"spec 文档"、"/spec"。
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
1,093 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 核心原则
- 工作流程
- 固定模板
- 关键约束
Files
SKILL.mdcore3,705 bytes
Read SKILL.md
# Spec - 需求规格说明技能
将模糊的需求意图转化为清晰、无歧义的需求规格文档。
## 核心原则
1. **不猜测**:遇到任何模糊点,必须向用户提问澄清,绝不自行假设
2. **不模糊**:每个需求边界必须是确定的,In Scope / Out of Scope 必须明确列出
3. **不写代码**:绝不写任何代码,包括伪代码。只用自然语言描述需求行为
4. **固定产出**:输出到项目既有的需求目录;若无统一约定,建议使用 `spec/<spec-name>/spec.md`
## 工作流程
### 第一步:理解与澄清View the complete source on GitHubtest
When your agent uses it
专注测试职能。用于编写/优化测试用例、执行单元测试与集成测试、产出测试报告。严禁修改任何业务代码,仅限操作测试代码。触发词包括"写测试"、"跑测试"、"单元测试"、"集成测试"、"test"、"/test"。
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,282 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 职能边界
- 核心原则
- 工作流程
- 固定模板
- 关键约束
Files
SKILL.mdcore4,587 bytes
Read SKILL.md
# Test - 测试技能
根据 plan 文档编写并执行单元测试与集成测试,产出结构化测试报告。该技能的核心目标是**验证**而非**修复**。
## 职能边界
1. **绝对禁令**:**禁止修改任何非测试相关的业务源码**。即便发现 bug,也只能在测试报告中记录并建议修复,不得自行调用 `/implement` 或手动修改源码。
2. **操作范围**:仅允许修改、新增测试文件、测试目录内容,或项目明确归类为测试资产的文件。
3. **输出目标**:高质量的测试代码覆盖及详尽的 `test.md` 测试报告。
## 核心原则
1. **以 Plan 为准**:测试用例严格基于 `plan.md` 中的验收标准与测试规范。
2. **验证驱动**:所有职能围绕“证明代码是否符合预期”展开。View the complete source on GitHubSkills included
- implement
- plan
- review
- spec
- test
Repository facts
- License
- MIT
- Created
- Mar 9, 2026
- Last pushed
- Mar 9, 2026
- Forks
- 12
- Open issues
- 0
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 4, 2026
- No broad tool permissions
- No dangerous shell commands
- 8 network referencesin 2 files: .claude-plugin/marketplace.json:1 .claude-plugin/plugin.json:7
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 8 signals by file
.claude-plugin/marketplace.json
- Network accessline 1
{ "$schema": "https://raw.githubusercontent.com/anthropics/claude-code/refs/heads/main/marketplace/marketplace.schema.json", - Network accessline 2
"$schema": "https://raw.githubusercontent.com/anthropics/claude-code/refs/heads/main/marketplace/marketplace.schema.json", - Network accessline 14
"name": "development-skills", "description": "Development workflow skills covering spec, plan, implement, review, and test.", "repository": "https://github.com/SimpleEve/development-skills", - Network accessline 15
"description": "Development workflow skills covering spec, plan, implement, review, and test.", "repository": "https://github.com/SimpleEve/development-skills", "version": "0.1.0", - Network accessline 16
"repository": "https://github.com/SimpleEve/development-skills",
.claude-plugin/plugin.json
- Network accessline 7
"email": "noreply@github.com" }, "repository": "https://github.com/SimpleEve/development-skills", - Network accessline 8
}, "repository": "https://github.com/SimpleEve/development-skills", "license": "MIT", - Network accessline 9
"repository": "https://github.com/SimpleEve/development-skills",
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md implement/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md implement/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md implement/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md implement/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md implement/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.