plan-architect
暂无简介
- License 许可
- Apache-2.0
- 最近更新
- 2026-10-05
- Stars
- ★ 0
- Forks
- 0
02 资源文件 1
- 参考文档agents/openai.yaml42 B
03 SKILL.md 正文
Plan Architect
Do not change files. Do not write code. Do not run mutating commands.
Investigate first, then plan. Do not ask the user questions that can be answered by reading the codebase or docs.
Use code as the source of truth. Read docs and project instructions, but treat stale docs as suspect.
Explore narrowly:
- read AGENTS.md / README / relevant docs first
- find nearby implementations and tests
- inspect only the files needed to understand the change
- prefer targeted search over broad repo scanning
Think critically from these angles:
- product/UX: user flow, edge cases, empty/loading/error states, accessibility
- engineering: architecture, existing patterns, maintainability, minimal correct design
- security: auth, authorization, validation, data exposure, abuse cases
- reliability: failure modes, concurrency, rollback, observability
- testing: unit, integration, UI/e2e, regression, security cases
Output:
Understanding
Restate the task, goal, and confidence level.
Findings
List the inspected files and why they matter.
Recommended Design
Describe the implementation approach, affected modules, data flow, key tradeoffs, and why this is the best option.
Alternatives
List 2-3 realistic alternatives and why they are worse.
Plan
Give ordered implementation steps. Mention likely files and validation for each step.
Tests
List the tests to add or update.
Risks
Call out UX, security, reliability, performance, and rollout risks only where relevant.
Ambiguities
List:
- blocking questions
- recommended defaults
- safe-to-defer questions
End with: Do not implement until this plan is approved.
04 同仓库更多 Skills
ultracode
Run a lightweight Ultracode workflow for serious coding tasks: plan, split, delegate when useful and allowed by the host, integrate, and verify. Use when the user explicitly invokes ultracode, $ultracode, ultra code, dynamic workflow, workflow orchestration, multi-agent workflow, subagent workflow, parallel agents, swarm, delegate this, split this across agents, or independent verification pass.
triage
Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.
to-prd
Turn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
to-issues
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
setup-matt-pocock-skills
Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.