orch-add-feature
Orchestrate building a brand-new feature end to end — research, plan, TDD implementation, review, and gated commit — by delegating each phase to the matching ECC agent. Use when adding a capability that does not exist yet.
- License 许可
- MIT
- 最近更新
- 2026-11-05
- Stars
- ★ 2
- Forks
- 1
01 前言 Front Matter
- name
- orch-add-feature
- metadata
- { "origin": "ECC" }
- description
- Orchestrate building a brand-new feature end to end — research, plan, TDD implementation, review, and gated commit — by delegating each phase to the matching ECC agent. Use when adding a capability that does not exist yet.
03 SKILL.md 正文
orch-add-feature
Actor · action · target: orch · add · feature. Thin wrapper over the shared
engine in orch-pipeline.
When to Use
- The user wants a capability that does not exist yet ("add", "build", "implement", "support …").
- It is net-new behavior — not a correction (
orch-fix-defect) and not an alteration of existing behavior (orch-change-feature).
Operation settings
- Default size floor: standard — run Research + Plan unless clearly small.
- Phase mask: 0 → 1 → 2 → 4 → 5 → 6 (skip 3 Scaffold; that is MVP-only).
- First move (phase 4): write new failing tests for the new behavior, then implement to green.
How It Works
- Run the
orch-pipelineengine with the settings above. - Classify size first; small / trivial features collapse toward 4 → 5 → 6.
- Stop at Gate 1 (plan approval) and Gate 2 (pre-commit).
- Add
security-reviewerif the feature touches a security trigger.
Related:
/feature-devis a standalone version of this flow.orch-add-featurediffers by sharing theorch-pipelineengine — the size classifier and the two gates — with the rest of the family, so it right-sizes trivial features to 4 → 5 → 6.
Example
orch-add-feature: add OAuth2 login to nws-poller
→ research existing auth libs → plan task_list [GATE 1: approve]
→ TDD each task → code-review (+ security-reviewer: auth path)
→ commit [GATE 2: confirm]
04 同仓库更多 Skills
x-api
X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
workspace-surface-audit
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.
wizard
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
windows-desktop-e2e
E2E testing for Windows native desktop apps (WPF, WinForms, Win32/MFC, Qt) using pywinauto and Windows UI Automation. Use when writing E2E tests for a Windows native desktop app with pywinauto or UI Automation.
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.