Not in the top 1,000 by GitHub stars
SmartSunruiyang/Agent-development-specification
一个通用、不绑定技术栈的 Claude Code 技能：在写第一行代码之前，先为项目铺好 Agent 规则、文档与架构，并在项目演进中持续把它们当作"源真相"。
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
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
44eec9b88f91 → 44eec9b88f91
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 44eec9b88f91
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit 44eec9b88f919fd6684c6429b8a24e4686e31202
git clone --filter=blob:none --no-checkout https://github.com/SmartSunruiyang/Agent-development-specification.git .hotskills/smartsunruiyang-agent-development-specification && git -C .hotskills/smartsunruiyang-agent-development-specification checkout --detach 44eec9b88f919fd6684c6429b8a24e4686e31202
# Copy each selected skill directory from .hotskills/smartsunruiyang-agent-development-specification into .agents/skills/<skill-name>/149GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days
Heat
0.3- 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
agent-development-specification
When your agent uses it
Bootstraps the Day-0 agent-governance + documentation scaffold for ANY project on ANY stack. Generates the agent rule system (CLAUDE.md, AGENTS.md, SELF_CONSTRAINTS.md, VIBECODING_GUIDE.md) plus upstream docs (PRD, ARCHITECTURE with module cards + dependency DAG, ROADMAP, CONVENTIONS), initializes version control with a zero-point commit, and runs a guided requirements→architecture interview to fill them with real content. Works for greenfield AND retrofitting an existing codebase (reverse-engineers a draft architecture from the code). Use whenever the user runs /ads:init or /agent-development-specification, starts a NEW project, or asks to set up agent rules / governance / project spec / self-constraints, scaffold CLAUDE.md / AGENTS.md / architecture docs, establish module boundaries before coding, or mentions 项目起步 / 起步指南 / Agent规范 / 自我约束 / 架构文档. Trigger even when the user doesn't say "skill" or "ads": laying down a project's rules, docs, and architecture before writing code is this skill's job.
What it loads into context
Frontmatter
265 tokensAlways available to the agent
SKILL.md
2,501 tokensWhen the skill is activated
Reference documents
24,841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prime directive: obey the rules you install
- The init workflow
- Language of generated docs
- Resources
- Token conventions inside the templates
Scripts executed separately
scripts/scaffold.py
Files
LICENSEasset1,062 bytesREADME.mddoc10,916 bytesSKILL.mdcore10,159 bytesSKILL.mdcore10,159 bytesSKILL.mdcore10,159 bytesSKILL.mdcore10,159 bytesSKILL.mdcore10,159 bytesassets/templates/AGENTS.mddoc3,907 bytesassets/templates/CLAUDE.mddoc3,686 bytesassets/templates/SELF_CONSTRAINTS.mddoc7,208 bytesassets/templates/VIBECODING_GUIDE.mddoc12,449 bytesassets/templates/docs/ARCHITECTURE.mddoc3,632 bytesassets/templates/docs/CONVENTIONS.mddoc2,619 bytesassets/templates/docs/PRD.mddoc2,416 bytesassets/templates/docs/ROADMAP.mddoc1,842 bytesassets/templates/docs/UIUX.mddoc1,371 bytesassets/templates/gitignore-baseasset523 bytesassets/templates/log-README.mddoc1,455 bytesassets/templates/settings.jsonasset74 bytesdist/agent-development-specification.skillasset49,805 bytesevals/evals.jsonasset4,471 bytesreferences/interview-flow.mddoc4,813 bytesreferences/retrofit.mddoc3,434 bytesreferences/spec.mddoc29,231 bytesscripts/scaffold.pyruns8,622 bytes
Read SKILL.md
# Agent Development Specification (ADS)
This skill installs a **project-startup governance system**: the agent rules, the upstream
documents, and the architecture that must exist *before* code, so that every later session —
yours or another agent's — works against a stable source of truth instead of free-styling on a
codebase nobody can fully see.
The full rationale lives in `references/spec.md` (the canonical, technology-agnostic spec).
Read it when you need depth on *why* a rule exists; this file tells you *what to do*.
## Prime directive: obey the rules you install
This skill's output is a set of hard constraints (`SELF_CONSTRAINTS.md`) and a practice guide.
You must follow them while running init — installing a rulebook you then violate is worse thanSkills included
- agent-development-specification
Repository facts
- License
- MIT
- Created
- Jun 1, 2026
- Last pushed
- Jun 1, 2026
- Forks
- 0
- Open issues
- 0
- Project activity
- Slowing
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 4 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 19 network referencesin 1 file: README.md:3
- No hidden or obfuscated text
- No instruction overrides
- 1 executable scriptin 1 file: scripts/scaffold.py:1
- 1 reference to secretsin 1 file: assets/templates/gitignore-base:20
- No requests to vote in Hot
Show all 21 signals by file
README.md
- Network accessline 3
[](LICENSE) - Network accessline 4
[](https://claude.com/claude-code) - Network accessline 5
[](https://docs.claude.com/en/docs/claude-code) - Network accessline 6
[](https://www.python.org/) - Network accessline 7
[](https://github.com/SmartSunruiyang/agent-development-specification/pulls) - Network accessline 13
> A universal, tech-stack-agnostic [**Claude Code**](https://claude.com/claude-code) skill that lays down a project's - Network accessline 81
git clone https://github.com/SmartSunruiyang/agent-development-specification \ - Network accessline 141
- 📦 **This repo** — <https://github.com/SmartSunruiyang/agent-development-specification> - Network accessline 143
- 📖 **The canonical spec** — [`references/spec.md`](references/spec.md) (the tech-agnostic "why") - 🧠 **Skill entry point** — [`SKILL.md`](SKILL.md) - 🐛 **Issues / feedback** — <https://github.com/SmartSunruiyang/agent-development-specifica - Network accessline 144
- 🧠 **Skill entry point** — [`SKILL.md`](SKILL.md) - 🐛 **Issues / feedback** — <https://github.com/SmartSunruiyang/agent-development-specification/issues> - 🤖 **Claude Code** — [product](https://claude.com/claude-code) · [docs](https://docs - Network accessline 145
- 🐛 **Issues / feedback** — <https://github.com/SmartSunruiyang/agent-development-specification/issues> - Network accessline 146
- 🤖 **Claude Code** — [product](https://claude.com/claude-code) · [docs](https://docs.claude.com/en/docs/claude-code) - Network accessline 150
[MIT](LICENSE) © 2026 [SmartSunruiyang](https://github.com/SmartSunruiyang) - Network accessline 177
unzip dist/agent-development-specification.skill -d ~/.claude/skills/ # 或克隆本仓库到 skills 目录： git clone https://github.com/SmartSunruiyang/agent-development-specification ~/.claude/skills/agent-development-specification - Network accessline 179
git clone https://github.com/SmartSunruiyang/agent-development-specification ~/.claude/skills/agent-development-specification - Network accessline 189
## 相关链接 / 许可 - 仓库：<https://github.com/SmartSunruiyang/agent-development-specification> - Network accessline 190
- 仓库：<https://github.com/SmartSunruiyang/agent-development-specification> - Network accessline 191
- 预打包文件：[`dist/agent-development-specification.skill`](dist/agent-development-specification.skill) - 通用规范原文：[`references/spec.md`](references/spec.md) - 许可：[MIT](LICENSE) © 2026 [SmartSunruiyang](https://github.com/SmartSunruiyang) - Network accessline 193
- 许可：[MIT](LICENSE) © 2026 [SmartSunruiyang](https://github.com/SmartSunruiyang)
assets/templates/gitignore-base
- Access to secretsline 20
[Credential-related source omitted]
scripts/scaffold.py
- Executable scriptline 1
#!/usr/bin/env python3
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.
Signal confidence: 20 facts
- Network access in prose of documentationREADME.md:3Low confidence
- Network access in prose of documentationREADME.md:4Low confidence
- Network access in prose of documentationREADME.md:5Low confidence
- Network access in prose of documentationREADME.md:6Low confidence
- Network access in prose of documentationREADME.md:7Low confidence
- Network access in prose of documentationREADME.md:13Low confidence
- Network access in code of documentationREADME.md:81Low confidence
- Network access in prose of documentationREADME.md:141Low confidence
- Network access in prose of documentationREADME.md:143Low confidence
- Network access in prose of documentationREADME.md:144Low confidence
- Network access in prose of documentationREADME.md:145Low confidence
- Network access in prose of documentationREADME.md:146Low confidence
- Network access in prose of documentationREADME.md:150Low confidence
- Network access in code of documentationREADME.md:177Low confidence
- Network access in code of documentationREADME.md:179Low confidence
- Network access in prose of documentationREADME.md:189Low confidence
- Network access in prose of documentationREADME.md:190Low confidence
- Network access in prose of documentationREADME.md:191Low confidence
- Network access in prose of documentationREADME.md:193Low confidence
- Executable script in code of a file that runsscripts/scaffold.py:1High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest assets/templates/AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md 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.
