用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/AvivK5498/The-Claude-Protocol --skill subagents-discipline命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Bootstrap lean multi-agent orchestration with beads task tracking. Use for projects needing agent delegation without heavy MCP overhead.
Bootstrap lean multi-agent orchestration with beads task tracking. Use for projects needing agent delegation without heavy MCP overhead.
Core engineering principles for implementation tasks
基于 SOC 职业分类
正在显示 SKILL.md
| name | subagents-discipline |
| description | Invoke at the start of any implementation task to enforce verification-first development |
Core principle: Test the FEATURE, not just the component you built.
Before writing code that touches external data (API, database, file, config):
This catches: field name mismatches, wrong data shapes, missing fields, format differences.
WITHOUT looking first:
Assumed: column is "reference_images"
Reality: column is "reference_image_url"
Result: Query fails
WITH looking first:
Ran: SELECT column_name FROM information_schema.columns WHERE table_name = 'assets';
Saw: reference_image_url
Coded against: reference_image_url
Result: Works
Component test catches: logic bugs, edge cases, type errors Feature test catches: integration bugs, auth issues, data flow problems
Both are required. Component test alone is NOT sufficient.
| You built | Component test | Feature test |
|---|---|---|
| API endpoint | curl returns 200 | UI calls API, displays result |
| Database change | Migration runs | App reads/writes correctly |
| Frontend component | Renders, no errors | User can see and interact |
| Full-stack feature | Each piece works alone | End-to-end flow works |
The pattern:
Before claiming you can't fully test:
"I couldn't test the feature" is only valid after exhausting available options.
Every completion must include evidence. Code reviewer will verify this.
DEMO:
COMPONENT:
Command: [what you ran to test the component]
Result: [what you observed]
FEATURE:
Steps: [how you tested the integrated feature]
Result: [what you observed - screenshot, output, etc.]
If you genuinely cannot test end-to-end (long-running job, external service, no browser tools):
DEMO:
COMPONENT:
Command: curl localhost:3008/api/endpoint
Result: 200, returns expected data
FEATURE: PARTIAL
Verified: [what you could test]
Needs human check: [what still needs verification]
Why: [specific reason - no browser MCP, takes 10+ minutes, requires external service]
Not acceptable reasons for PARTIAL:
Acceptable reasons:
If your BEAD_ID contains a dot (e.g., BD-001.2), you're implementing part of a larger feature:
bd show {EPIC_ID} --json | jq -r '.[0].design'Design docs ensure all pieces fit together. If you deviate, integration fails.
Before marking done:
When you catch yourself thinking:
When you're about to say:
Component test passing ≠ feature works
Curl returning 200 ≠ UI displays correctly
TypeScript compiles ≠ user can use it
Test the feature like a user would use it. Then show evidence. Then claim done.