Agent Skillsn8n-io/n8n › n8n:spec-driven-development

n8n:spec-driven-development

GitHub

规范驱动开发技能,确保实现与规格说明同步。用于在功能开发、验证或更新规格时,通过读取、实施和校验保持代码与文档一致,防止漂移。

.agents/skills/spec-driven-development/SKILL.md n8n-io/n8n

触发场景

用户启动具有规格文档的功能开发 用户输入/spec命令 用户要求根据规格验证实现 用户要求更新因变更而失效的规格

安装

npx skills add n8n-io/n8n --skill n8n:spec-driven-development -g -y
更多选项

非标准路径

npx skills add https://github.com/n8n-io/n8n/tree/master/.agents/skills/spec-driven-development -g -y

不安装直接使用

npx skills use n8n-io/n8n@n8n:spec-driven-development

指定 Agent (Claude Code)

npx skills add n8n-io/n8n --skill n8n:spec-driven-development -a claude-code -g -y

安装 repo 全部 skill

npx skills add n8n-io/n8n --all -g -y

预览 repo 内 skill

npx skills add n8n-io/n8n --list

SKILL.md

Frontmatter
{
    "name": "n8n:spec-driven-development",
    "description": "Keeps implementation and specs in sync. Use when working on a feature that has a spec in .agents\/specs\/, when the user says \/spec, or when starting implementation of a documented feature. Also use when the user asks to verify implementation against a spec or update a spec after changes."
}

Spec-Driven Development

Specs live in .agents/specs/. They are the source of truth for architectural decisions, API contracts, and implementation scope. Implementation and specs must stay in sync — neither leads exclusively.

Core Loop

Read spec → Implement → Verify alignment → Update spec or code → Repeat

Before Starting Work

  1. Find the spec. Search .agents/specs/ for files matching the feature:
ls .agents/specs/
  1. Read the full spec. Understand scope, decisions, API contracts, and open questions before writing code.

  2. If no spec exists and the task is non-trivial (new module, new API, architectural change), ask the user whether to create one first.

During Implementation

  • Reference spec decisions — don't re-decide what the spec already settled.
  • When you diverge from the spec (better approach found, user requested change, constraint discovered), update the spec immediately in the same session. Don't leave spec and code out of sync.
  • Tick off TODO checkboxes (- [ ]- [x]) as items are completed.
  • Strike through or annotate items that were deliberately skipped or replaced, with a brief reason:
    - [x] ~~OpenRouter proxy~~ → Direct execution: nodes call OpenRouter directly
    

After Completing Work

Run a spec verification pass:

  1. Re-read the spec alongside the implementation.
  2. Check each section:
    • Do API endpoints in spec match the controller?
    • Do config/env vars in spec match the config class?
    • Does the module structure in spec match the actual file tree?
    • Do type definitions in spec match @n8n/api-types?
    • Are all TODO items correctly checked/unchecked?
  3. Update the spec for any drift found. Common drift:
    • New files added that aren't listed in the structure section
    • API response shapes changed during implementation
    • Config defaults adjusted
    • Architectural decisions refined
  4. Flag unresolved gaps to the user — things the spec promises but implementation doesn't deliver yet (acceptable for MVP, but should be noted).

Spec File Conventions

  • One or more markdown files per feature in .agents/specs/.
  • Keep specs concise. Use tables for mappings, code blocks for shapes.
  • Use ## Implementation TODO with checkboxes to track progress.
  • Split into multiple files when it helps (e.g. separate backend/frontend), but don't enforce a rigid naming scheme.

When the User Asks to "Self-Review" or "Verify Against Spec"

  1. Read all relevant specs.
  2. Read all implementation files.
  3. Produce a structured comparison:
    • Aligned: items where spec and code match
    • Drift: items where they diverge (fix immediately)
    • Gaps: spec items not yet implemented (note as future work)
  4. Fix drift, update specs, report gaps to the user.

版本历史

  • c31d0e5 当前 2026-08-20 19:08

同 Skill 集合

.agents/skills/community-pr-readiness-check/SKILL.md
.agents/skills/content-design/SKILL.md
.agents/skills/conventions/SKILL.md
.agents/skills/create-agent-builder-eval/SKILL.md
.agents/skills/create-community-node-lint-rule/SKILL.md
.agents/skills/create-instance-ai-eval/SKILL.md
.agents/skills/create-issue/SKILL.md
.agents/skills/create-pr/SKILL.md
.agents/skills/create-skill/SKILL.md
.agents/skills/db-migrations/SKILL.md
.agents/skills/design-system/SKILL.md
.agents/skills/experiments/SKILL.md
.agents/skills/gh-stack/SKILL.md
.agents/skills/human-like-code-review/SKILL.md
.agents/skills/linear-issue/SKILL.md
.agents/skills/loom-transcript/SKILL.md
.agents/skills/nathan/SKILL.md
.agents/skills/node-add-oauth/SKILL.md
.agents/skills/protect-endpoints/SKILL.md
.agents/skills/public-api/SKILL.md
.agents/skills/reproduce-bug/SKILL.md
.agents/skills/telemetry/SKILL.md
.agents/skills/ui-design/SKILL.md
.claude/plugins/n8n/skills/setup-mcps/SKILL.md
.opencode/skills/setup-mcps/SKILL.md
packages/@n8n/cli/skills/n8n-cli/SKILL.md
packages/@n8n/instance-ai/skills/agent-builder/SKILL.md
packages/@n8n/instance-ai/skills/config-evals/SKILL.md
packages/@n8n/instance-ai/skills/credential-recipe-research/SKILL.md
packages/@n8n/instance-ai/skills/credential-setup-with-computer-use/SKILL.md
packages/@n8n/instance-ai/skills/debugging-executions/SKILL.md
packages/@n8n/instance-ai/skills/instance-awareness/SKILL.md
packages/@n8n/instance-ai/skills/n8n-docs-assistant/SKILL.md
packages/@n8n/instance-ai/skills/planned-task-runtime/SKILL.md
packages/@n8n/instance-ai/skills/planning/SKILL.md
packages/@n8n/instance-ai/skills/post-build-flow/SKILL.md
packages/@n8n/instance-ai/skills/data-table-manager/SKILL.md
packages/@n8n/instance-ai/skills/intent-recognition/SKILL.md
packages/@n8n/instance-ai/skills/model-selection/SKILL.md
packages/@n8n/instance-ai/skills/one-off-operations/SKILL.md
packages/@n8n/instance-ai/skills/progressive-building/SKILL.md
packages/@n8n/instance-ai/skills/workflow-builder/SKILL.md

元信息

文件数
0
版本
fe0fad5
Hash
3a30e96f
收录时间
2026-08-20 19:08

首页 - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-09-23 15:21
浙ICP备14020137号-1