Publish Sign in

Chinese Spec-Driven Development (SDD) Agent Skill

Guides structured, specification-driven development in Chinese with rigorous brownfield compatibility checks and automated Spec Kit…

Install this skill Read the source first Free Written by zuyu-ultra
Context cost
298.4k tokensestimated from the bundle; more than a 200k window holds
Bundle
180 of 599 fileshanded out here; the rest is at its source
Licence
not declarednone named by its author
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

唯一的中文规格驱动开发（SDD）Skill。用户输入 `$sdd`、`$SDD`，或要求执行 constitution、spec、plan、tasks、implement、converge、存量项目兼容、Bug 根因分析及 Spec Kit 工作流时使用。它内置完整能力，但对外只提供普通的 SDD 入口。

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

productivity
Filed under

Productivity & Workflow

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md29.0 kB · preview
--- name: sdd ---
6# SDD
7
8把固定版本的官方 specify-cli 当作执行内核，把本 Skill 当作中文控制面。不要重新实现官方 extension、preset、workflow、bundle、catalog、authentication 或 integration 生命周期。
9
10## 固定能力基线
11
12- 官方仓库：https://github.com/github/spec-kit
13- 提交：83883a2ebad7e7de667fd00381b100d597faf846
14- 版本：0.16.4.dev0
15- 叶子 CLI 命令：84
16- Integration：38
17- 核心 agentic commands：10
18
19官方仓库除 .git 对象数据库外的全部 539 个文件原样位于 vendor/spec-kit/，覆盖源码、运行资产、文档、测试、CI、开发容器、媒体与项目元数据；SHA-256 清单位于 vendor/MANIFEST.sha256。28 个跨平台离线 wheel 位于 vendor/wheelhouse/，其他受支持平台若没有匹配 wheel，可在用户授权联网后从 vendored 源码安装依赖。
20
21需要精确命令和参数时读取 references/capability-map.json，并以固定运行时的实时 --help 为最终依据。禁止调用 PATH 上版本不明的 specify。
22
23## 语言与兼容性
24
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md1,321 words
Files180
Licencenot declared
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈50
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
298,325
on trigger
The instruction body and 179 supporting files, read only when the skill fires.
1.5×
a 200k window
It does not fit in the window: loaded whole, it would need more room than the model has.
050k100k150k200k context window

298.4k tokens, estimated from the bundle at four bytes to the token — more than the whole window, so it cannot all be held at once: the model reads SKILL.md when the skill fires and the other files only as the instructions call for them. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

The download carries 180 of the 599 files in its source folder; the list here names 180 files, 4014.7 kB on disk. Mostly text — the instructions the model reads — with 77 scripts in it that your client would run only if the instructions tell it to. The other 419 are not in the download — the first 100 are listed after these, with why.

  • SKILL.md29.0 kB
  • agents/openai.yaml0.3 kB
  • evals/evals.json23.0 kB
  • manifests/managed-predecessors.json14.3 kB
  • references/brownfield-compatibility.md12.3 kB
  • references/bundles.md2.5 kB
  • references/capability-map.json62.9 kB
  • references/cli-core.md5.2 kB
  • references/customization.md0.7 kB
  • references/extensions.md3.8 kB
  • references/integrations.md3.7 kB
  • references/presets.md2.7 kB
  • references/sdd-strategies.md7.2 kB
  • references/security-offline.md3.7 kB
  • references/upstream.md0.9 kB
  • references/upstream-development.md5.1 kB
  • references/workflows.md5.3 kB
  • scripts/build_vendored_manifest.py3.5 kB
  • scripts/generate_capability_manifest.py3.5 kB
  • scripts/install_project.py26.8 kB
  • scripts/run_evals.py13.6 kB
  • scripts/specify_runtime.py13.4 kB
  • scripts/verify_skill.py22.6 kB
  • tests/test_brownfield_guards.py8.2 kB
  • tests/test_eval_harness.py11.4 kB
  • tests/test_skill_bundle.py46.4 kB
  • vendor/upstream-lock.json1.2 kB
  • vendor/spec-kit/.markdownlint-cli2.jsonc0.5 kB
  • vendor/spec-kit/.pre-commit-config.yaml0.3 kB
  • vendor/spec-kit/.zenodo.json0.9 kB
  • vendor/spec-kit/AGENTS.md30.9 kB
  • vendor/spec-kit/CHANGELOG.md107.9 kB
  • vendor/spec-kit/CODE_OF_CONDUCT.md3.2 kB
  • vendor/spec-kit/CONTRIBUTING.md15.4 kB
  • vendor/spec-kit/DEVELOPMENT.md2.5 kB
  • vendor/spec-kit/LICENSE1.1 kB
  • vendor/spec-kit/pyproject.toml3.3 kB
  • vendor/spec-kit/README.md21.9 kB
  • vendor/spec-kit/README.zh-CN.md20.4 kB
  • vendor/spec-kit/SECURITY.md1.7 kB
  • vendor/spec-kit/spec-driven.md26.2 kB
  • vendor/spec-kit/SUPPORT.md1.0 kB
  • evals/fixtures/date-range-project/pyproject.toml0.2 kB
  • evals/fixtures/hidden-caller-project/pyproject.toml0.2 kB
  • evals/fixtures/phone-project/pyproject.toml0.2 kB
  • evals/fixtures/red-herring-project/pyproject.toml0.2 kB
  • evals/fixtures/renamed-duplicate-project/pyproject.toml0.2 kB
  • vendor/spec-kit/.devcontainer/devcontainer.json2.2 kB
  • vendor/spec-kit/.devcontainer/post-create.sh3.6 kB
  • vendor/spec-kit/.github/CODEOWNERS0.2 kB
  • vendor/spec-kit/.github/dependabot.yml0.4 kB
  • vendor/spec-kit/.github/PULL_REQUEST_TEMPLATE.md0.7 kB
  • vendor/spec-kit/.github/security-audit-requirements.txt18.1 kB
  • vendor/spec-kit/bundles/catalog.community.json1.1 kB
  • vendor/spec-kit/docs/docfx.json1.6 kB
  • vendor/spec-kit/docs/index.md5.9 kB
  • vendor/spec-kit/docs/installation.md6.8 kB
  • vendor/spec-kit/docs/local-development.md6.1 kB
  • vendor/spec-kit/docs/quickstart.md7.1 kB
  • vendor/spec-kit/docs/README.md0.9 kB
  • vendor/spec-kit/docs/toc.yml2.1 kB
  • vendor/spec-kit/docs/upgrade.md22.2 kB
  • vendor/spec-kit/extensions/catalog.community.json193.3 kB
  • vendor/spec-kit/extensions/catalog.json2.1 kB
  • vendor/spec-kit/extensions/EXTENSION-API-REFERENCE.md22.8 kB
  • vendor/spec-kit/extensions/EXTENSION-DEVELOPMENT-GUIDE.md22.1 kB
  • vendor/spec-kit/extensions/EXTENSION-PUBLISHING-GUIDE.md11.5 kB
  • vendor/spec-kit/extensions/EXTENSION-USER-GUIDE.md26.1 kB
  • vendor/spec-kit/extensions/README.md5.9 kB
  • vendor/spec-kit/extensions/RFC-EXTENSION-SYSTEM.md61.5 kB
  • vendor/spec-kit/integrations/catalog.community.json0.2 kB
  • vendor/spec-kit/integrations/catalog.json10.9 kB
  • vendor/spec-kit/integrations/CONTRIBUTING.md4.7 kB
  • vendor/spec-kit/integrations/README.md3.6 kB
  • vendor/spec-kit/newsletters/2026-April.md24.0 kB
  • vendor/spec-kit/newsletters/2026-February.md11.6 kB
  • vendor/spec-kit/newsletters/2026-July.md31.8 kB
  • vendor/spec-kit/newsletters/2026-June.md28.8 kB
  • vendor/spec-kit/newsletters/2026-March.md13.2 kB
  • vendor/spec-kit/newsletters/2026-May.md21.1 kB
  • vendor/spec-kit/presets/ARCHITECTURE.md9.2 kB
  • vendor/spec-kit/presets/catalog.community.json34.7 kB
  • vendor/spec-kit/presets/catalog.json1.4 kB
  • vendor/spec-kit/presets/PUBLISHING.md12.7 kB
  • vendor/spec-kit/presets/README.md8.0 kB
  • vendor/spec-kit/templates/checklist-template.md2.1 kB
  • vendor/spec-kit/templates/constitution-template.md2.3 kB
  • vendor/spec-kit/templates/plan-template.md3.8 kB
  • vendor/spec-kit/templates/spec-template.md4.6 kB
  • vendor/spec-kit/templates/tasks-template.md9.2 kB
  • vendor/spec-kit/templates/vscode-settings.json0.4 kB
  • vendor/spec-kit/tests/__init__.py0.1 kB
  • vendor/spec-kit/tests/auth_helpers.py0.8 kB
  • vendor/spec-kit/tests/bundler_helpers.py4.2 kB
  • vendor/spec-kit/tests/conftest.py6.1 kB
  • vendor/spec-kit/tests/http_helpers.py1.5 kB
  • vendor/spec-kit/tests/parity_helpers.py6.4 kB
  • vendor/spec-kit/tests/self_upgrade_helpers.py2.0 kB
  • vendor/spec-kit/tests/test_agent_config_consistency.py17.0 kB
  • vendor/spec-kit/tests/test_authentication.py61.9 kB
  • vendor/spec-kit/tests/test_branch_numbering.py0.9 kB
  • vendor/spec-kit/tests/test_check_prerequisites_paths_only.py18.9 kB
  • vendor/spec-kit/tests/test_check_prerequisites_python_parity.py22.1 kB
  • vendor/spec-kit/tests/test_check_tool.py6.2 kB
  • vendor/spec-kit/tests/test_cli_version.py3.0 kB
  • vendor/spec-kit/tests/test_command_template_py_scripts.py8.2 kB
  • vendor/spec-kit/tests/test_commands_package.py3.4 kB
  • vendor/spec-kit/tests/test_console_imports.py1.7 kB
  • vendor/spec-kit/tests/test_create_new_feature_python_parity.py33.4 kB
  • vendor/spec-kit/tests/test_download_security.py49.3 kB
  • vendor/spec-kit/tests/test_extension_add_path_traversal.py12.4 kB
  • vendor/spec-kit/tests/test_extension_registration.py19.4 kB
  • vendor/spec-kit/tests/test_extension_skills.py152.0 kB
  • vendor/spec-kit/tests/test_extension_update_hardening.py72.5 kB
  • vendor/spec-kit/tests/test_extensions.py453.9 kB
  • vendor/spec-kit/tests/test_github_http.py17.7 kB
  • vendor/spec-kit/tests/test_github_workflows.py3.5 kB
  • vendor/spec-kit/tests/test_init_dir.py24.2 kB
  • vendor/spec-kit/tests/test_init_dir_cli.py11.9 kB
  • vendor/spec-kit/tests/test_init_output_markup.py6.3 kB
  • vendor/spec-kit/tests/test_live_transient_windows.py3.5 kB
  • vendor/spec-kit/tests/test_merge.py7.5 kB
  • vendor/spec-kit/tests/test_post_process.py10.0 kB
  • vendor/spec-kit/tests/test_presets.py608.0 kB
  • vendor/spec-kit/tests/test_ps1_encoding.py1.7 kB
  • vendor/spec-kit/tests/test_registrar_path_traversal.py14.7 kB
  • vendor/spec-kit/tests/test_resolve_template_python_parity.py24.2 kB
  • vendor/spec-kit/tests/test_security_workflow.py15.4 kB
  • vendor/spec-kit/tests/test_self_upgrade_detection.py37.7 kB
  • vendor/spec-kit/tests/test_self_upgrade_execution.py25.5 kB
  • vendor/spec-kit/tests/test_self_upgrade_guidance.py7.4 kB
  • vendor/spec-kit/tests/test_self_upgrade_verification.py28.3 kB
  • vendor/spec-kit/tests/test_setup_plan_feature_json.py9.2 kB
  • vendor/spec-kit/tests/test_setup_plan_no_overwrite.py10.2 kB
  • vendor/spec-kit/tests/test_setup_plan_python_parity.py12.6 kB
  • vendor/spec-kit/tests/test_setup_tasks.py36.1 kB
  • vendor/spec-kit/tests/test_setup_tasks_python_parity.py9.7 kB
  • vendor/spec-kit/tests/test_shared_infra_gitignore.py3.5 kB
  • vendor/spec-kit/tests/test_shared_infra_integrity.py3.8 kB
  • vendor/spec-kit/tests/test_skill_placeholder_py.py5.0 kB
  • vendor/spec-kit/tests/test_specify_template_numbering.py1.5 kB
  • vendor/spec-kit/tests/test_timestamp_branches.py63.2 kB
  • vendor/spec-kit/tests/test_upgrade.py19.4 kB
  • vendor/spec-kit/tests/test_utils.py0.7 kB
  • vendor/spec-kit/tests/test_utils_assets_imports.py0.6 kB
  • vendor/spec-kit/tests/test_version_imports.py1.1 kB
  • vendor/spec-kit/tests/test_workflow_run_without_project.py14.6 kB
  • vendor/spec-kit/tests/test_workflows.py664.8 kB
  • vendor/spec-kit/workflows/ARCHITECTURE.md10.3 kB
  • vendor/spec-kit/workflows/catalog.community.json1.9 kB
  • vendor/spec-kit/workflows/catalog.json0.6 kB
  • vendor/spec-kit/workflows/PUBLISHING.md11.2 kB
  • vendor/spec-kit/workflows/README.md15.5 kB
  • vendor/spec-kit/workflows/step-catalog.community.json0.2 kB
  • vendor/spec-kit/workflows/step-catalog.json0.2 kB
  • assets/project/.specify/memory/.constitution-template.json0.1 kB
  • assets/project/.specify/memory/constitution.md0.6 kB
  • assets/project/.specify/templates/checklist-template.md2.8 kB
  • assets/project/.specify/templates/constitution-template.md2.4 kB
  • assets/project/.specify/templates/plan-template.md6.7 kB
  • assets/project/.specify/templates/spec-template.md8.8 kB
  • assets/project/.specify/templates/tasks-template.md11.2 kB
  • evals/fixtures/date-range-project/src/date_range.py0.3 kB
  • evals/fixtures/date-range-project/tests/test_date_range.py0.5 kB
  • evals/fixtures/hidden-caller-project/tests/test_csv_export.py0.2 kB
  • evals/fixtures/hidden-caller-project/tests/test_formatter.py0.2 kB
  • evals/fixtures/phone-project/src/user_phone.py0.4 kB
  • evals/fixtures/phone-project/tests/test_user_phone.py0.5 kB
  • evals/fixtures/red-herring-project/tests/test_pricing.py0.9 kB
  • evals/fixtures/renamed-duplicate-project/tests/test_page.py0.1 kB
  • evals/fixtures/renamed-duplicate-project/tests/test_post.py0.5 kB
  • vendor/spec-kit/.github/aw/actions-lock.json1.4 kB
  • vendor/spec-kit/.github/ISSUE_TEMPLATE/agent_request.yml4.6 kB
  • vendor/spec-kit/.github/ISSUE_TEMPLATE/bug_report.yml3.3 kB
  • vendor/spec-kit/.github/ISSUE_TEMPLATE/bundle_submission.yml11.0 kB
  • vendor/spec-kit/.github/ISSUE_TEMPLATE/config.yml0.9 kB
  • vendor/spec-kit/.github/ISSUE_TEMPLATE/extension_submission.yml8.7 kB
  • vendor/spec-kit/.github/ISSUE_TEMPLATE/feature_request.yml3.3 kB
  • vendor/spec-kit/.github/ISSUE_TEMPLATE/preset_submission.yml6.8 kB
  • vendor/spec-kit/.github/scripts/check_security_requirements.py3.8 kB

Not in the download

The first 100 are named here, those the skill reads first. Too deep is past six folders, not carried is a type a skill download does not hold and over the limit is past 200 files or 4 MB a skill. Marked read: its SKILL.md or scripts name the file, so without it the skill works only in part. Take them from its source.

  • vendor/MANIFEST.sha256read · not carried
  • vendor/spec-kit/extensions/git/scripts/bash/create-new-feature-branch.shread · too deep
  • vendor/spec-kit/extensions/git/scripts/bash/git-common.shread · too deep
  • vendor/spec-kit/scripts/powershell/check-prerequisites.ps1read · not carried
  • vendor/spec-kit/scripts/powershell/common.ps1read · not carried
  • vendor/spec-kit/scripts/powershell/create-new-feature.ps1read · not carried
  • vendor/spec-kit/scripts/powershell/resolve-template.ps1read · not carried
  • vendor/spec-kit/scripts/powershell/setup-plan.ps1read · not carried
  • vendor/spec-kit/scripts/powershell/setup-tasks.ps1read · not carried
  • vendor/spec-kit/src/specify_cli/bundler/commands_impl/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/bundler/lib/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/bundler/models/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/bundler/models/catalog.pyread · too deep
  • vendor/spec-kit/src/specify_cli/bundler/services/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/commands/bundle/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/agy/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/alquimia/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/amp/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/auggie/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/bob/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/claude/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/cline/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/codebuddy/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/codex/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/command_code/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/copilot/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/cursor_agent/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/devin/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/droid/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/firebender/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/forge/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/gemini/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/generic/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/goose/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/grok/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/hermes/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/junie/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/kilocode/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/kimi/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/kiro_cli/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/lingma/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/omp/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/opencode/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/pi/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/qodercli/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/qwen/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/rovodev/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/shai/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/tabnine/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/trae/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/vibe/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/zcode/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/integrations/zed/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/workflows/overlays/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/workflows/steps/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/workflows/steps/command/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/workflows/steps/do_while/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/workflows/steps/fan_in/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/workflows/steps/fan_out/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/workflows/steps/gate/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/workflows/steps/if_then/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/workflows/steps/init/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/workflows/steps/prompt/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/workflows/steps/shell/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/workflows/steps/switch/__init__.pyread · too deep
  • vendor/spec-kit/src/specify_cli/workflows/steps/while_loop/__init__.pyread · too deep
  • vendor/WHEELHOUSE.sha256read · not carried
  • vendor/spec-kit/.github/workflows/security.ymlread · over the limit
  • vendor/spec-kit/.github/workflows/test.ymlread · over the limit
  • vendor/spec-kit/docs/community/bundles.mdread · over the limit
  • vendor/spec-kit/docs/community/extensions.mdread · over the limit
  • vendor/spec-kit/docs/community/presets.mdread · over the limit
  • vendor/spec-kit/docs/reference/bundles.mdread · over the limit
  • vendor/spec-kit/docs/reference/extensions.mdread · over the limit
  • vendor/spec-kit/docs/reference/integrations.mdread · over the limit
  • vendor/spec-kit/docs/reference/presets.mdread · over the limit
  • vendor/spec-kit/docs/reference/workflows.mdread · over the limit
  • vendor/spec-kit/extensions/agent-context/extension.ymlread · over the limit
  • vendor/spec-kit/extensions/agent-context/README.mdread · over the limit
  • vendor/spec-kit/extensions/assess/extension.ymlread · over the limit
  • vendor/spec-kit/extensions/assess/README.mdread · over the limit
  • vendor/spec-kit/extensions/bug/extension.ymlread · over the limit
  • vendor/spec-kit/extensions/bug/README.mdread · over the limit
  • vendor/spec-kit/extensions/git/config-template.ymlread · over the limit
  • vendor/spec-kit/extensions/git/extension.ymlread · over the limit
  • vendor/spec-kit/extensions/git/README.mdread · over the limit
  • vendor/spec-kit/extensions/selftest/extension.ymlread · over the limit
  • vendor/spec-kit/extensions/template/config-template.ymlread · over the limit
  • vendor/spec-kit/extensions/template/extension.ymlread · over the limit
  • vendor/spec-kit/extensions/template/README.mdread · over the limit
  • vendor/spec-kit/presets/constitution-sync/preset.ymlread · over the limit
  • vendor/spec-kit/presets/constitution-sync/README.mdread · over the limit
  • vendor/spec-kit/presets/lean/preset.ymlread · over the limit
  • vendor/spec-kit/presets/lean/README.mdread · over the limit
  • vendor/spec-kit/presets/scaffold/preset.ymlread · over the limit
  • vendor/spec-kit/presets/scaffold/README.mdread · over the limit
  • vendor/spec-kit/presets/self-test/preset.ymlread · over the limit
  • vendor/spec-kit/scripts/bash/check-prerequisites.shread · over the limit
  • vendor/spec-kit/scripts/bash/common.shread · over the limit
  • vendor/spec-kit/scripts/bash/create-new-feature.shread · over the limit
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 77 scripts beside the text, so the download is 180 files — not the whole of its source: at least 419 files are left out, and the skill reads 100 of them. The first 100 are listed under the files, with why.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Chinese Spec-Driven Development (SDD) · 298.4k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/chinese-spec-driven-development-sdd/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/chinese-spec-driven-development-sdd" ] && { [ ! -e .claude/skills/chinese-spec-driven-development-sdd ] || { mv .claude/skills/chinese-spec-driven-development-sdd "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/chinese-spec-driven-development-sdd" .claude/skills/ && echo "Installed .claude/skills/chinese-spec-driven-development-sdd"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add zuyu-ultra/chinese-spec-driven-development-sdd

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/chinese-spec-driven-development-sdd/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/chinese-spec-driven-development-sdd/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/chinese-spec-driven-development-sdd" ] && { [ ! -e ~/.claude/skills/chinese-spec-driven-development-sdd ] || { mv ~/.claude/skills/chinese-spec-driven-development-sdd "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/chinese-spec-driven-development-sdd" ~/.claude/skills/ && echo "Installed ~/.claude/skills/chinese-spec-driven-development-sdd" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/chinese-spec-driven-development-sdd/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as sdd in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, chinese-spec-driven-development-sdd. Not in this download: at least 419 files of its source, 100 of them read by its SKILL.md or scripts (the list, and why). Take them from its source.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencezuyu-ultra/chinese-spec-driven-development-sdd

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

ZU
zuyu-ultra

Publishes on mcprush.

0 servers listed2 skills listednot claimed
Profile
Publisher
Servers0
Claim this skill