martin1847/evolab / skills/agent-backend-standard
agent-backend-standard
Verified后端架构与工程规范。适用于构建或评审 agent/LLM 后端、任何涉及数据库(DB)的后端,以及建立或评审后端仓库工程门禁。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.5 KB |
| references/agent-foundations.md | markdown | 2.3 KB |
| references/caching-discipline.md | markdown | 3.9 KB |
| references/code-dependency-lifecycle.md | markdown | 9.5 KB |
| references/data-write-discipline.md | markdown | 9.9 KB |
| references/engineering-interface.md | markdown | 10.9 KB |
| references/evals.md | markdown | 2.6 KB |
| references/governance.md | markdown | 2.7 KB |
| references/hitl-resume-safety.md | markdown | 2.7 KB |
| references/observability-cost.md | markdown | 1.2 KB |
| references/prompt-context.md | markdown | 1.6 KB |
| references/resilience.md | markdown | 3.9 KB |
| references/safety-bounded-execution.md | markdown | 4.5 KB |
| references/secrets-discipline.md | markdown | 2.5 KB |
| references/selfcheck-gates.md | markdown | 4.4 KB |
| references/state-durability.md | markdown | 2.6 KB |
| references/tool-design.md | markdown | 2.8 KB |
references/prompt-context.md
View on GitHub# II-3 — 上下文与 prompt 工程
> hub `agent-backend-standard` 的一章。当前只写实 **prompt 内容生命周期**(有真实素材);上下文工程四处方(just-in-time/compaction/note-taking/sub-agent)已写实于 I-2 合章(经 SKILL.md 目录进入);本章待扩的 prompt 层(右高度 system prompt、context 作有限资源)*TBD*。
## 1. prompt 内容生命周期(MUST)
prompt 比代码更易腐烂——常住字符串 / 模板 / config,逃过 code review 严格度,也逃过所有工具(它执行、它"对")。
- **判别同附录 A §2.1**:稳定指令不管;**情境绑定**的写死内容(为弱模型写死的格式 hack、客户特例、模型版本耦合)有生命周期。
- **退役标记**(canonical 定义在附录 A `code-dependency-lifecycle.md` §2.2):情境绑定的 prompt 写死项 MUST 带 `EXPIRES:` / `REVISIT-WHEN:` + reason + owner。模型版本耦合打 `REVISIT-WHEN: 换模型`——切模型时 `grep` 扫出。
- **prompt 额外:绑 eval**。prompt 里每个写死的具体值 / few-shot 例子 MUST 能追溯到一个 eval case(IM 侧 AAM `agent-eval-suite`)。**指不出哪个 eval 需要它 → 可疑、可删**;eval 不再需要时,它就该删。
## 2. 通用 context engineering(TBD)
右高度 system prompt、context 作有限资源、compaction / 结构化 note-taking、own-your-context——有真实落地素材再写实(Anthropic context engineering / 12-Factor F2·F3)。
## 一句话
> 情境绑定的 prompt 写死内容打 `EXPIRES`/`REVISIT-WHEN`(标记规则见附录 A)+ **绑一个 eval case**;指不出 eval 即可删。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |