// Synchronize DEV_SPEC.md and split it into chapter-specific files under specs/ directory. Run sync_spec.py to update, then read SPEC_INDEX.md for navigation. Foundation for all spec-based operations. Use when user says "同步规范", "sync spec", or before any spec-dependent task.
Summarize completed work, update progress tracking in DEV_SPEC.md, and prepare for next iteration. Final stage of dev-workflow pipeline. Use when task implementation and testing is completed, or when user says "完成检查点", "checkpoint", "保存进度", "save progress", "任务完成".
Master orchestrator for development workflow. Use when user says "下一阶段", "继续开发", "next task", "proceed", or asks to continue development. Coordinates spec-sync, progress-tracker, implement, testing-stage, and checkpoint skills in a pipeline to complete one sub-task per iteration.
Implement features following spec-driven workflow. Read specs first, extract design principles, plan file strategy, then write production-ready code with type hints and docstrings. Use when user asks to implement a feature, write code, or build a module. Depends on spec-sync for specification access.
Identify next development task from project schedule and validate claimed progress against actual codebase state. Serves as GPS for development - tells you where you are and where to go next. Stage 2 of dev-workflow pipeline. Use when user says "检查进度", "status", "下一个任务", "what's next", "定位任务".
Validate implementation through systematic testing after implement stage completes. Determines test type (unit/integration/e2e) based on task nature, runs pytest, and reports results. Stage 4 of dev-workflow pipeline. Use when user says "运行测试", "run tests", "test", or after implementation.
| name | spec-sync |
| description | Synchronize DEV_SPEC.md and split it into chapter-specific files under specs/ directory. Run sync_spec.py to update, then read SPEC_INDEX.md for navigation. Foundation for all spec-based operations. Use when user says "同步规范", "sync spec", or before any spec-dependent task. |
| metadata | {"category":"documentation","triggers":"sync spec, update spec, 同步规范"} |
| allowed-tools | Bash(python:*) Read |
This skill synchronizes the master specification document (DEV_SPEC.md) and splits it into smaller, chapter-specific files stored in the specs/ directory.
This is a prerequisite for all spec-based operations. Other skills depend on the split spec files to perform their tasks.
When you trigger dev-workflow (e.g., "下一阶段" or "继续开发"), spec-sync runs automatically as Stage 1. No manual action needed.
Only manually run if:
DEV_SPEC.md outside of workflow# Normal sync
python .github/skills/spec-sync/sync_spec.py
# Force regenerate (even if no changes detected)
python .github/skills/spec-sync/sync_spec.py --force
The script performs these operations:
DEV_SPEC.md from project rootspecs/SPEC_INDEX.md as the navigation indexUse SPEC_INDEX.md as your entry point to understand what each spec file contains:
Read: .github/skills/spec-sync/SPEC_INDEX.md
This index file provides:
Then read the specific spec file you need from specs/ directory:
Read: .github/skills/spec-sync/specs/05-architecture.md
.github/skills/spec-sync/
├── SKILL.md ← This file
├── SPEC_INDEX.md ← Auto-generated index (navigation index)
├── sync_spec.py ← Sync script
├── .spec_hash ← Hash file for change detection
└── specs/ ← Split spec files (chapter files)
├── 01-overview.md
├── 02-features.md
├── 03-tech-stack.md
├── 04-testing.md
├── 05-architecture.md
├── 06-schedule.md
└── 07-future.md
specs/ directly — they are auto-generatedDEV_SPEC.md and re-run the sync script--force flag to regenerate even if no changes detected:
python .github/skills/spec-sync/sync_spec.py --force