best-skills is a collection of reusable skills for coding agents, including tools for writing papers, creating diagrams and presentations, generating code documentation, and other tasks. Users install its skills into agents such as Cursor, Claude Code, Codex, or OpenClaw so those agents can recognize relevant requests and run the corresponding workflows. The catalogue entries are examples of the skills included in the collection.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add xstongxue/best-skills --skill dev-workflowgit clone --depth 1 https://github.com/xstongxue/best-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xstongxue/best-skills/dev-workflow)<a href="https://agentmods.dev/skills/xstongxue/best-skills/dev-workflow"><img src="https://agentmods.dev/badge/skills/xstongxue/best-skills/dev-workflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xstongxue/best-skills/dev-workflow"><img src="https://agentmods.dev/badge/skills/xstongxue/best-skills/dev-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00079 | $0.01058 |
| Opus 5 | $0.00039 | $0.00529 |
| Sonnet 5 | $0.00016 | $0.00212 |
| Haiku 4.5 | $0.00008 | $0.00106 |
Grade A, and why
dev-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
开发流程五步法
需求理解 → 方案设计 → 代码实现 → 代码审查 → Bug 修复
使用时机
- 用户描述新功能/项目想法，需要需求分析
- 用户提到「方案设计」「架构设计」「怎么实现」
- 用户提到「代码实现」「开始写代码」「帮我实现」
- 用户提到「代码审查」「Review」「检查代码」「看看有没有问题」
- 用户提到「bug」「报错」「崩溃」「异常」「不工作」「出错了」「测试失败」
Step 1：识别当前步骤
根据用户需求选择对应 reference 文件执行：
| 步骤 | 文件 | 触发关键词 |
|---|---|---|
| 需求理解 | requirement.md | 需求分析、理解需求、整理需求、帮我梳理 |
| 方案设计 | design.md | 方案设计、技术设计、架构设计、怎么实现 |
| 代码实现 | implementation.md | 代码实现、开始写代码、帮我实现、写一下 |
| 代码审查 | review.md | 代码审查、Review、检查代码、看看有没有问题 |
| Bug 修复 | bug-fix.md | bug、报错、崩溃、异常、不工作、出错了、测试失败 |
Step 2：收集输入
- 需求理解：从用户描述或对话中提取功能想法、约束条件
- 方案设计：确认已有需求文档，或简要收集关键信息
- 代码实现：确认已有技术方案，或根据需求快速拟定实现思路
- 代码审查：明确审查范围（哪些文件/模块）
- Bug 修复：确认错误信息、复现步骤、环境信息
Step 3：执行、输出与自动落盘
读取对应 reference 中的完整流程，按步骤执行，输出符合该阶段要求的交付物。
其中以下步骤必须自动写入文档：
- 需求理解：
- 单模块/未指定模块：将最终需求文档追加写入当前工作目录的
docs/需求理解.md - 多模块且已识别模块名：将最终需求文档追加写入
docs/<module>/需求理解.md
- 单模块/未指定模块：将最终需求文档追加写入当前工作目录的
- 方案设计：
- 单模块/未指定模块：将最终方案文档追加写入当前工作目录的
docs/方案设计.md - 多模块且已识别模块名：将最终方案文档追加写入
docs/<module>/方案设计.md
- 单模块/未指定模块：将最终方案文档追加写入当前工作目录的
- 代码审查：
- 单模块/未指定模块：将最终审查报告追加写入当前工作目录的
docs/代码审查.md - 多模块且已识别模块名：将最终审查报告追加写入
docs/<module>/代码审查.md
- 单模块/未指定模块：将最终审查报告追加写入当前工作目录的
落盘规则：
- 默认目录为当前工作目录
docs/，若不存在则创建后再写入 - 多模块项目优先使用
docs/<module>/分目录；若无法确定模块则回退到docs/根目录 <module>使用稳定标识（建议用目录名/包名，避免同义词）- 文件不存在则创建，存在则追加，不覆盖历史内容
- 每次新增内容前写入时间标题：
## YYYY-MM-DD HH:mm - 标题后粘贴本次完整输出正文，末尾加分隔线
--- - 若用户明确指定了其他文件路径，优先按用户指定路径写入
- 可选维护
docs/模块索引.md记录模块名与文档路径映射，便于检索与归档
注意事项
-
流程串联：需求理解 → 方案设计 → 代码实现 → 代码审查 → Bug 修复；每步完成后提示用户进入下一阶段
-
上游缺失时：提示用户先完成前置步骤，或简要收集关键信息后继续
-
需求理解、方案设计与代码审查阶段默认必须自动落盘（追加写入），不要覆盖历史记录
What ships with it
22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- reference/bug-fix.md 2.9 KB
- reference/design.md 4.2 KB
- reference/implementation.md 3.6 KB
- reference/requirement.md 3.2 KB
- reference/review-kit/guides/architecture-review-guide.md 15 KB
- reference/review-kit/guides/c.md 5.4 KB
- reference/review-kit/guides/common-bugs-checklist.md 31 KB
- reference/review-kit/guides/cpp.md 7.5 KB
- reference/review-kit/guides/css-less-sass.md 13 KB
- reference/review-kit/guides/go.md 20 KB
- reference/review-kit/guides/java.md 10.0 KB
- reference/review-kit/guides/performance-review-guide.md 17 KB
- reference/review-kit/guides/python.md 24 KB
- reference/review-kit/guides/qt.md 6.0 KB
- reference/review-kit/guides/react.md 22 KB
- reference/review-kit/guides/rust.md 21 KB
- reference/review-kit/guides/security-review-guide.md 6.3 KB
- reference/review-kit/guides/typescript.md 13 KB
- reference/review-kit/guides/vue.md 20 KB
- reference/review-kit/templates/pr-review-template.md 1.8 KB
- reference/review-kit/templates/review-checklist.md 3.0 KB
- reference/review.md 7.5 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 73 lines · 79 tokens per session scan A 49c3fab85eb4
dev-workflow is a skill published in the GitHub repository xstongxue/best-skills (2,797 stars, last pushed 15d ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,058 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
gh-pr-review
Automated Cherry Studio review for local branches, PRs, commits, files, architecture docs, and repository skills. Use for code or documentation reviews that need project-specific naming, main/renderer/shared placement and dependency rules, IpcApi and DataApi boundaries, lifecycle/service ownership, renderer hooks…
prepare-release
Prepare a new release by collecting commits, generating bilingual release notes, updating version files, and creating a release branch. Use when asked to prepare/create a release, bump version, or run /prepare-release.
claude-automation-recommender
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what…
gh-create-pr
Create or update GitHub pull requests using the repository-required workflow and template compliance. Use when asked to create/open/update a PR so the assistant reads .github/pullrequesttemplate.md, fills every template section, preserves markdown structure exactly, and marks missing data as N/A or None instead of…
cherry-tool-guide
Cherry Studio first-party tool and bundled-shell routing for general agents. For straightforward local work in shell-capable sessions, run JS/TS with bun and one-off JS tools with bun x; run Python with uv run [--with ] python and one-off Python CLIs with uvx; search with rg. Load this guide before changing project…