Menu

#898 by GitHub stars

zhu1090093659/spec_driven_develop

Spec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub Issue/PR tracking, Deep Discuss, and adaptive control for Claude Code, Codex, Cursor, and other Markdown-capable agents.

Claude CodeCodexEngineeringOperations

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

plugins/spec-driven-develop/skills/deep-discuss/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 14f8c0f2be44

No earlier version was observed for comparison.

Compare on GitHub

plugins/spec-driven-develop/skills/review-spd/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 14f8c0f2be44

No earlier version was observed for comparison.

Compare on GitHub

plugins/spec-driven-develop/skills/spec-driven-develop/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 14f8c0f2be44

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 14f8c0f2be4421d11b8eb7474cde3ee00fb52b14

git clone --filter=blob:none --no-checkout https://github.com/zhu1090093659/spec_driven_develop.git .hotskills/zhu1090093659-spec_driven_develop && git -C .hotskills/zhu1090093659-spec_driven_develop checkout --detach 14f8c0f2be4421d11b8eb7474cde3ee00fb52b14 # Copy each selected skill directory from .hotskills/zhu1090093659-spec_driven_develop into .claude/skills/<skill-name>/
git clone --filter=blob:none --no-checkout https://github.com/zhu1090093659/spec_driven_develop.git .hotskills/zhu1090093659-spec_driven_develop && git -C .hotskills/zhu1090093659-spec_driven_develop checkout --detach 14f8c0f2be4421d11b8eb7474cde3ee00fb52b14 # Copy each selected skill directory from .hotskills/zhu1090093659-spec_driven_develop into .agents/skills/<skill-name>/
994GitHub stars
1star in 7 days
3skills in this repository
0commits in 30 days

Heat

2.7
  • Star growth, last 7 daysAhead of 36% of tracked repositories
  • Star growth, last 24 hoursAhead of 71% of tracked repositories
  • Rank movement, last 7 daysAhead of 2% of tracked repositories
  • Commits, last 30 daysAhead of 0% of tracked repositories
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Jul 30, 2026Nov 6, 2026994

Individual skills in this repository

How it works

deep-discuss

When your agent uses it

结构化深度讨论 Skill，用于与用户进行多轮问题分析和方案设计。当用户描述一个问题现象、故障表现、 技术困惑、方案选择困难，或明确说"讨论一下"、"帮我分析"、"我遇到一个问题"、"你觉得怎么样"、 "帮我想想"、"我在纠结"时，必须使用本 skill。当用户提供了一段描述（可能附带截图）并期望深入分析 而非直接给答案时，也应触发本 skill。即使用户只是抛出一个现象描述没有明确提问，也要使用本 skill 来引导结构化思考。不要在简单的事实查询（"X是什么"）或明确的执行指令（"帮我写个脚本"）上触发。

What it loads into context

Frontmatter

203 tokens

Always available to the agent

SKILL.md

1,084 tokens

When the skill is activated

Reference documents

31,292 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. 通用规则
  2. Phase 1：接收信息
  3. Phase 2：问题审查（质量门控）
  4. Phase 3：深度分析
  5. Phase 4：方案设计
  6. Phase 5：方案自检
  7. Phase 6：最终确认
  8. Phase 7：执行（可选）

Scripts executed separately

  • ../review-spd/scripts/review-context.py

Files

  • ../../../../.claude-plugin/marketplace.jsonasset1,389 bytes
  • ../../.claude-plugin/plugin.jsonasset1,235 bytes
  • ../../agents/code-reviewer.mddoc3,568 bytes
  • ../../agents/code-reviewer.mddoc3,568 bytes
  • ../../agents/project-analyzer.mddoc4,410 bytes
  • ../../agents/task-architect.mddoc7,863 bytes
  • ../../agents/task-executor.mddoc9,112 bytes
  • ../../agents/task-executor.mddoc9,112 bytes
  • SKILL.mdcore3,953 bytes
  • ../review-spd/SKILL.mddoc6,134 bytes
  • ../review-spd/references/output-format.mddoc1,830 bytes
  • ../review-spd/references/reviewer-template.mddoc1,895 bytes
  • ../review-spd/scripts/review-context.pyruns9,952 bytes
  • ../spec-driven-develop/SKILL.mddoc20,713 bytes
  • ../spec-driven-develop/references/adaptive-control.mddoc9,418 bytes
  • ../spec-driven-develop/references/behavioral-rules.mddoc7,118 bytes
  • ../spec-driven-develop/references/github-integration.mddoc15,399 bytes
  • ../spec-driven-develop/references/parallel-protocol.mddoc9,492 bytes
  • ../spec-driven-develop/references/super-philosophy.mddoc5,878 bytes
  • ../spec-driven-develop/references/templates/analysis.mddoc5,288 bytes
  • ../spec-driven-develop/references/templates/archive.mddoc1,767 bytes
  • ../spec-driven-develop/references/templates/governance.mddoc3,262 bytes
  • ../spec-driven-develop/references/templates/plan.mddoc6,537 bytes
  • ../spec-driven-develop/references/templates/progress.mddoc7,406 bytes
Read SKILL.md

# Deep Discuss — 结构化深度讨论

你正在执行 **Deep Discuss** 工作流：不急于给答案，先把问题想透。用户描述的"问题"和真正的问题之间常有鸿沟——这个流程用分阶段的纪律保证讨论的质量和深度。

## 通用规则

- **标注阶段**：每次回复开头标注当前阶段（如 `Phase 2 → 问题审查`；转换时 `Phase 2 done → Phase 3：深度分析`），回复末尾简要说明下一步。
- **不要跳阶段**：至少过一遍 Phase 1-4；Phase 5/6 可按问题复杂度合并，但不能完全跳过。用户中途提供新信息时，评估是否回到更早阶段。
- **信息不足即停**：Phase 2 发现信息不足时，先问再等，不要带着未验证的假设往下走。
- **直接坦诚**：用户判断有误就直说并给理由；不确定的事用置信度表述，不用模棱两可的"可能"。

## Phase 1：接收信息

只接收，不分析。完整理解用户提供的全部信息（文字、截图、用户的初步判断），用自己的话复述关键点（≤3-5 句）确认理解无误。描述明显模糊时，复述后只提 1-2 个最关键的澄清问题。
View the complete source on GitHub

Skills included

  • deep-discuss
  • review-spd
  • spec-driven-develop

Repository facts

License
MIT
Created
Mar 21, 2026
Last pushed
Jul 26, 2026
Forks
101
Open issues
1
Project activity
Slowing

Rank over the last 12 weeks

Now #898 · best #583 · down 192 in 30 days

  1. #872 on Oct 30
  2. #875 on Oct 31
  3. #879 on Nov 1
  4. #886 on Nov 2
  5. #893 on Nov 3
  6. #898 since Nov 4
37 earlier periods
  1. #619 on Aug 1
  2. #554 on Aug 5
  3. #559 on Aug 9
  4. #583 on Aug 10
  5. #582 on Aug 12
  6. #593 on Aug 13
  7. #588 on Aug 16
  8. #592 on Aug 17
  9. #601 on Aug 20
  10. #607 on Aug 21
  11. #583 on Aug 22
  12. #619 on Aug 24
  13. #613 on Aug 26
  14. #642 on Aug 28
  15. #598 on Aug 30
  16. #622 on Aug 31
  17. #611 on Sep 4
  18. #653 on Sep 8
  19. #639 on Sep 13
  20. #664 on Sep 14
  21. #645 on Sep 25
  22. #720 on Sep 29
  23. #660 on Oct 1
  24. #684 on Oct 4
  25. #687 on Oct 5
  26. #698 on Oct 6
  27. #706 on Oct 7
  28. #746 on Oct 8
  29. #715 on Oct 9
  30. #733 on Oct 14
  31. #726 on Oct 15
  32. #733 on Oct 16
  33. #755 on Oct 21
  34. #743 on Oct 23
  35. #845 on Oct 25
  36. #865 on Oct 28
  37. #866 on Oct 29

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 4, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 4 notes
  • plugins/spec-driven-develop/agents/code-reviewer.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/spec-driven-develop/agents/task-executor.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/spec-driven-develop/skills/review-spd/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/spec-driven-develop/agents/code-reviewer.md:1 Plugin-wide analysis incomplete; see repository notes
Show all 40 signals by file

.claude-plugin/marketplace.json

  • Network accessline 16
    "name": "zhu1090093659"       },       "homepage": "https://github.com/zhu1090093659/spec_driven_develop",
  • Network accessline 17
    },       "homepage": "https://github.com/zhu1090093659/spec_driven_develop",       "repository": "https://github.com/zhu1090093659/spec_driven_develop",
  • Network accessline 18
    "homepage": "https://github.com/zhu1090093659/spec_driven_develop",
  • Network accessline 19
    "repository": "https://github.com/zhu1090093659/spec_driven_develop",

plugins/spec-driven-develop/.claude-plugin/plugin.json

  • Network accessline 6
    "author": {     "name": "zhu1090093659",     "url": "https://github.com/zhu1090093659"
  • Network accessline 7
    "name": "zhu1090093659",     "url": "https://github.com/zhu1090093659"   },
  • Network accessline 8
    "url": "https://github.com/zhu1090093659"
  • Network accessline 9
    },   "homepage": "https://github.com/zhu1090093659/spec_driven_develop",   "repository": "https://github.com/zhu1090093659/spec_driven_develop",
  • Network accessline 10
    "homepage": "https://github.com/zhu1090093659/spec_driven_develop",
  • Network accessline 11
    "repository": "https://github.com/zhu1090093659/spec_driven_develop",

plugins/spec-driven-develop/skills/review-spd/scripts/review-context.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Executable scriptline 1
    #!/usr/bin/env python3

plugins/spec-driven-develop/skills/spec-driven-develop/references/github-integration.md

  • Network accessline 144
    --- _Managed by [Spec-Driven Develop](https://github.com/zhu1090093659/spec-driven-develop) workflow_
  • Network accessline 144
    --- _Managed by [Spec-Driven Develop](https://github.com/zhu1090093659/spec-driven-develop) workflow_
  • Network accessline 145
    _Managed by [Spec-Driven Develop](https://github.com/zhu1090093659/spec-driven-develop) workflow_
  • Network accessline 145
    _Managed by [Spec-Driven Develop](https://github.com/zhu1090093659/spec-driven-develop) workflow_
  • Network accessline 320
    --- _Part of [Spec-Driven Develop](https://github.com/zhu1090093659/spec-driven-develop) workflow_
  • Network accessline 320
    --- _Part of [Spec-Driven Develop](https://github.com/zhu1090093659/spec-driven-develop) workflow_
  • Network accessline 321
    _Part of [Spec-Driven Develop](https://github.com/zhu1090093659/spec-driven-develop) workflow_
  • Network accessline 321
    _Part of [Spec-Driven Develop](https://github.com/zhu1090093659/spec-driven-develop) workflow_

plugins/spec-driven-develop/skills/spec-driven-develop/references/super-philosophy.md

  • Access to secretsline 81
    [Credential-related source omitted]
  • Access to secretsline 81
    [Credential-related source omitted]

plugins/spec-driven-develop/skills/spec-driven-develop/references/templates/progress.md

  • Network accessline 27
    ## GitHub Resources - **Project Board**: https://github.com/users/{user}/projects/{num} _(GITHUB_FULL only)_
  • Network accessline 27
    ## GitHub Resources - **Project Board**: https://github.com/users/{user}/projects/{num} _(GITHUB_FULL only)_
  • Network accessline 28
    - **Project Board**: https://github.com/users/{user}/projects/{num} _(GITHUB_FULL only)_
  • Network accessline 28
    - **Project Board**: https://github.com/users/{user}/projects/{num} _(GITHUB_FULL only)_
  • Network accessline 42
    | Phase | Name | Milestone URL | Open | Closed | Total | |:------|:-----|:-------------|-----:|-------:|------:| | 1     |      | https://github.com/{owner}/{repo}/milestone/1 | N | 0 | N |
  • Network accessline 42
    | Phase | Name | Milestone URL | Open | Closed | Total | |:------|:-----|:-------------|-----:|-------:|------:| | 1     |      | https://github.com/{owner}/{repo}/milestone/1 | N | 0 | N |
  • Network accessline 43
    |:------|:-----|:-------------|-----:|-------:|------:| | 1     |      | https://github.com/{owner}/{repo}/milestone/1 | N | 0 | N | | 2     |      | https://github.com/{owner}/{repo}/milestone/2 | N | 0 | N |
  • Network accessline 43
    |:------|:-----|:-------------|-----:|-------:|------:| | 1     |      | https://github.com/{owner}/{repo}/milestone/1 | N | 0 | N | | 2     |      | https://github.com/{owner}/{repo}/milestone/2 | N | 0 | N |
  • Network accessline 44
    | 1     |      | https://github.com/{owner}/{repo}/milestone/1 | N | 0 | N |
  • Network accessline 44
    | 1     |      | https://github.com/{owner}/{repo}/milestone/1 | N | 0 | N |
  • Network accessline 45
    | 2     |      | https://github.com/{owner}/{repo}/milestone/2 | N | 0 | N |
  • Network accessline 45
    | 2     |      | https://github.com/{owner}/{repo}/milestone/2 | N | 0 | N |
  • Network accessline 78
    ## Phase Checklist - [ ] Phase 1: <name> (0/N tasks) — [milestone](https://github.com/{owner}/{repo}/milestone/1)
  • Network accessline 78
    ## Phase Checklist - [ ] Phase 1: <name> (0/N tasks) — [milestone](https://github.com/{owner}/{repo}/milestone/1)
  • Network accessline 79
    - [ ] Phase 1: <name> (0/N tasks) — [milestone](https://github.com/{owner}/{repo}/milestone/1)
  • Network accessline 79
    - [ ] Phase 1: <name> (0/N tasks) — [milestone](https://github.com/{owner}/{repo}/milestone/1)
  • Network accessline 80
    - [ ] Phase 2: <name> (0/N tasks) — [milestone](https://github.com/{owner}/{repo}/milestone/2)
  • Network accessline 80
    - [ ] Phase 2: <name> (0/N tasks) — [milestone](https://github.com/{owner}/{repo}/milestone/2)

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 compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativeManifest .claude-plugin/marketplace.json.claude/skills/<skill-name>/
CodexNativeManifest AGENTS.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md plugins/spec-driven-develop/skills/deep-discuss/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md plugins/spec-driven-develop/skills/deep-discuss/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md plugins/spec-driven-develop/skills/deep-discuss/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md plugins/spec-driven-develop/skills/deep-discuss/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.

You might also use

Komdosh/komnet

Git-backed message bus for AI coding agents — Claude Code, Cursor and Codex coordinate asynchronously, with no server

8GitHub stars

cookiy-ai/user-research-skill

Cookiy AI Skill for AI agents (Claude, Codex, Cursor, OpenClaw) — end-to-end user research: AI interviews, synthetic users, quant surveys, participant recruitment.

1.6kGitHub stars

addyosmani/agent-skills

Production-grade engineering skills for AI coding agents.

113.7kGitHub stars

KKKKhazix/khazix-skills

数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents

22kGitHub stars

Q00/ouroboros

Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, G…

6.3kGitHub stars

rlaope/oh-my-hermes

⚚ The coding harness with Hermes Agent wired into IDE.

5.2kGitHub stars

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

zhu1090093659/spec_driven_develop: #898 on hotskills, 994 stars

[![zhu1090093659/spec_driven_develop on hotskills](https://hotskills.dev/badge/zhu1090093659-spec_driven_develop.svg)](https://hotskills.dev/skill/zhu1090093659-spec_driven_develop/)