rootnode-domain-software-engineering
Specialized software engineering prompt methodology for Claude. Use when building prompts for system design, code review, incident response, security analysis, API design, architecture decisions, RFCs, ADRs, runbooks, or technical leadership. Trigger on: "build a prompt for code review," "system design prompt," "SRE prompt," "security review prompt," "incident response prompt," "API design prompt," "architecture decision prompt," "RFC prompt," "runbook prompt." Provides 11 tested approaches across identity, reasoning, and output for engineering analysis. Do NOT use for general coding help, writing code, or debugging — this builds prompts that shape engineering analysis, not code itself. Do NOT use for evaluating existing prompts (use rootnode-prompt-validation if available).
rootnode · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add drayline/rootnode-skills --skill rootnode-domain-software-engineering技能说明
name: rootnode-domain-software-engineering description: >- Specialized software engineering prompt methodology for Claude. Use when building prompts for system design, code review, incident response, security analysis, API design, architecture decisions, RFCs, ADRs, runbooks, or technical leadership. Trigger on: "build a prompt for code review," "system design prompt," "SRE prompt," "security review prompt," "incident response prompt," "API design prompt," "architecture decision prompt," "RFC prompt," "runbook prompt." Provides 11 tested approaches across identity, reasoning, and output for engineering analysis. Do NOT use for general coding help, writing code, or debugging — this builds prompts that shape engineering analysis, not code itself. Do NOT use for evaluating existing prompts (use rootnode-prompt-validation if available). license: Apache-2.0 metadata: author: rootnode version: "4.0.0" original-source: "DOMAIN_PACK_SOFTWARE_ENGINEERING.md"
Software Engineering Prompt Methodology
Calibration: Tier 1 (Model-compatible) - runs cleanly on the current dual-primary tier (Opus 5, Sonnet 5) as well as Haiku 4.5 with extended thinking. Structured retrieval, rule evaluation, or template lookup - output shape does not depend on model class. Correct-shape output also on Opus 4.8 (fallback-graceful) and Sonnet 4.6 (legacy-graceful). See repository README for model compatibility.
Specialized approaches for building Claude prompts that handle software engineering tasks — reliability engineering, security analysis, code review, API design, performance analysis, threat modeling, and engineering document formats (RFCs, ADRs, runbooks, code review feedback).
When to use this Skill: You have a task that requires engineering-domain expertise in a Claude prompt — not general system architecture (use a Technical Architect identity for that), but deeper specialization: SRE thinking, adversarial security analysis, code-level technical leadership, or engineering-specific deliverable formats.
What this Skill provides:
- 3 identity approaches (SRE / Platform Engineer, Security Engineer, Staff+ Engineer / Tech Lead)
- 4 reasoning methodologies (Code & Design Review, API Design, Performance & Scalability Analysis, Threat Modeling) — see
references/reasoning-approaches.md - 4 output format specifications (RFC, ADR, Runbook, Code Review Feedback) — see
references/output-formats.md - Behavioral countermeasures for engineering-specific Claude failure modes
v4.0 update — Opus 5 cyber classifier posture
Opus 5's cybersecurity classifiers are proportionally less restrictive than Fable 5's — expected to intervene approximately 85% less often (per Anthropic's Opus 5 announcement). For defensive-security software-engineering workflows, Opus 5 is the friction-optimal target.
Permitted on Opus 5:
- Source-code vulnerability finding and review.
- Defensive analysis of application code, configurations, and infrastructure-as-code.
- Threat modeling against source-available systems.
Blocked on Opus 5 (routes to fallback):
- Binary-based vulnerability scanning (opaque binaries analyzed for exploits).
- Penetration testing (active exploitation against systems).
- Exploit generation and weaponization.
The 85%-less-often intervention estimate is Fable-5-relative, not absolute — Opus 5 classifiers still trigger on the blocked categories above.
Fallback destination. On Claude.ai, Claude Code, and Claude Cowork, Opus 5 refusals fall back to Opus 4.8 by default. Skills designed for defensive-security workflows should produce correct-shape output on Opus 4.8 (fallback-graceful) as well as on Opus 5 (primary).
Conservative-review-instruction fix. For code-review prompts, do NOT use only report high-severity issues or be conservative — Opus 5 follows literally and under-reports. Rewrite to report-everything-then-filter form: "Report every issue you find, categorized by severity. In a separate pass at the end, filter to [severity threshold] and list only those in the final report. Include the full list in an appendix." See root_OPTIMIZATION_REFERENCE.md "Prompt/environment-conditional defects" for details.
How to Use This Skill
Step 1: Identify the Engineering Sub-Domain
Determine which specialization the task requires:
| Task Focus | Identity Approach | Primary Reasoning | Typical Output |
|---|---|---|---|
| Production reliability, incidents, observability, capacity | SRE / Platform Engineer | Performance & Scalability Analysis | Runbook |
| Threat modeling, security review, vulnerability assessment | Security Engineer | Threat Modeling | RFC or ADR |
| Code review, design review, technical mentorship | Staff+ Engineer / Tech Lead | Code & Design Review | Code Review Feedback |
| API contracts, versioning, developer experience | (Technical Architect or Staff+) | API Design | RFC or ADR |
| Proposing a significant technical change | (match to domain) | (match to task) | RFC |
| Recording an architecture decision | (match to domain) | (match to task) | ADR |
Step 2: Select the Identity Approach
Choose one identity approach for the prompt. Each shapes Claude's perspective and priorities.
SRE / Platform Engineer — Use when the task involves production reliability, observability, incident management, capacity planning, infrastructure automation, or reducing operational toil. This identity thinks in terms of failure domains, blast radius, and recovery procedures — not just whether a system works, but how it fails and how quickly you recover.
<role>
You are a senior site reliability engineer with deep experience operating large-scale distributed systems in production. You think in terms of reliability budgets, failure domains, and degradation modes — not just whether a system works, but how it fails, how quickly you detect the failure, and how you recover.
You are skeptical of designs that optimize for the happy path.
阅读完整来源 ↗