skills/lwy-requirement-workflow/SKILL.md
Use when the user wants to build, implement, or develop a feature. Orchestrates evidence-driven Spec-Driven Development. Default lifecycle is `lite` (INIT → IMPLEMENTING → TESTING → DONE); auto-promote to `standard` or `full` when scope, risk, or AC traceability demands it. Triggers: 'develop feature', 'implement this', 'build feature', 'add module', 'fix bug', '开发功能', '实现这个'.
npx skillsauth add learnwy/skills lwy-requirement-workflowInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
A minimal orchestrator for spec-driven development. The CLI keeps state, runs gates, and writes a curated brief for the next phase — read the brief instead of re-discovering the codebase.
| Concept | Where | Purpose |
|---|---|---|
| Lifecycle | lite / standard / full | Phase ladder — start small, escalate on evidence |
| Brief | briefs/<PHASE>.md | Curated context the next agent reads |
| Gate | TS validator per phase | Blocks advance until artifacts meet criteria |
| Traceability | traceability.md | Auto-rebuilt AC ↔ task ↔ files matrix |
lite INIT → IMPLEMENTING → TESTING → DONE
standard INIT → PLANNING → IMPLEMENTING → TESTING → DONE
full INIT → DEFINING → PLANNING → DESIGNING → IMPLEMENTING → TESTING → DELIVERING → DONE
Use lite by default. Promote with:
node scripts/cli.cjs escalate -r . --to standard --reason "scope grew past 5 files"
node scripts/cli.cjs escalate -r . --to full --reason "auth code touched"
Common escalation triggers:
node scripts/cli.cjs init -r . -n "<name>" [-l lite|standard|full]
node scripts/cli.cjs advance -r . # gate-checked transition
node scripts/cli.cjs status -r . # phase, brief, last gate, AC/task counts
Plus three useful auxiliaries:
node scripts/cli.cjs brief -r . --print # show current-phase brief
node scripts/cli.cjs brief -r . --regen # rebuild brief from current artifacts
node scripts/cli.cjs trace -r . # rebuild traceability.md
1. cli.cjs init -r . -n "..." ← scaffolds .agents/workflow/<id>/
2. cli.cjs advance -r . ← runs gate, writes next brief
3. AI reads briefs/<NEW PHASE>.md ← single context source
4. AI edits the artifact named in the brief (spec.md / tasks.md / design.md / code / checklist.md)
5. Repeat 2-4 until DONE
If the gate fails, advance exits 2 and prints which criterion failed. Fix the artifact and retry, or pass --force to bypass.
| Phase | When | Reference | |---|---|---| | INIT | Always | n/a | | DEFINING | full only | references/phases/DEFINING.md | | PLANNING | standard, full | references/phases/PLANNING.md | | DESIGNING | full only | references/phases/DESIGNING.md | | IMPLEMENTING | Always | references/phases/IMPLEMENTING.md | | TESTING | Always | references/phases/TESTING.md | | DELIVERING | full only | references/phases/DELIVERING.md |
Each phase has one default agent (run first) and a list of optional agents (opt-in when needed). See agents/AGENTS.md for the full registry.
| Phase | Default | Optional |
|---|---|---|
| DEFINING | problem-definer | iron-audit-pm, risk-auditor, spec-by-example |
| PLANNING | story-mapper | mvp-freeze-architect |
| DESIGNING | architecture-advisor | domain-modeler, responsibility-modeler |
| IMPLEMENTING | tdd-coach | refactoring-guide, legacy-surgeon |
| TESTING | test-strategist | test-strategy-advisor, code-reviewer, error-analyzer |
| DELIVERING | tech-design-reviewer | code-reviewer |
node scripts/cli.cjs hooks generate -r . # print hooks.json
node scripts/cli.cjs hooks install -r . # write hooks.json to .trae/ and .claude/ (IDE-owned config). Workflow state itself lives in `.agents/`.
Installs a SessionStart hook that surfaces the active workflow + brief path, and a Stop quality gate that blocks premature stopping in IMPLEMENTING/TESTING.
tools
Fallback skill when no project-specific one matches. Provides 10 battle-tested software-engineering methodology agents: problem-definer (Weinberg), story-mapper (Patton), spec-by-example (Adzic), domain-modeler (DDD/Evans), responsibility-modeler (CRC/Wirfs-Brock), architecture-advisor (Bass), tdd-coach (Beck), refactoring-guide (Fowler), legacy-surgeon (Feathers), test-strategist (Crispin). Use when user asks about DDD, TDD, refactoring, story mapping, test strategy, or software-architecture quality attributes.
documentation
当用户需要创建、更新或设计项目级技能(.agents/skills/*/SKILL.md)时使用此技能。Analyzes the user's problem and project context to design reusable skill solutions. 触发词:'创建技能'、'编写技能'、'构建技能'、'添加技能'、'更新技能'、'项目技能'、'新建技能'、'设计技能', or when the user describes a repetitive workflow that should be captured as a reusable AI skill.
tools
Use this skill when the user wants to install, add, or configure a skill in a project. Analyze the project's tech stack and workflow, then recommend and install the best-matching skill. Triggers: 'install skill', 'add skill', 'configure skill', 'set up skill', 'enable skill', 'use skill in project', 'project skill', or when the user asks how to bring an existing skill capability into the current workspace.
development
Use when the user wants to create or update project-level AI rules (written to .agents/rules/*.md) that constrain AI behaviour. The rule format is the common frontmatter+markdown convention used by Trae / Cursor / Windsurf — not Trae-specific. Good for: code-style enforcement, naming conventions, commit-message format, or making the AI consistently follow a project pattern. NOT for skills (use project-skill-writer) or agents (use project-agent-writer). Triggers: '创建规则', '添加规则', '设置代码风格', '强制约定', '配置 AI 行为', 'AI 规则', '始终做 X', or any 'always do X' / 'never do Y' AI-behaviour request that should persist across sessions.