zero-yx/static_flow / skills/tech-impl-deep-dive-writer
tech-impl-deep-dive-writer
VerifiedWrite mechanism-first technical implementation deep-dive articles for system/design/code explanations. Use when users ask for detailed implementation docs or engineering blog posts that must explain principles, data flow, trade-offs, and operations, and avoid source-location dumps or flashy/non-structured headings.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.3 KB |
| agents/openai.yaml | config | 362 B |
| references/outline-template.md | markdown | 1.5 KB |
| references/style-contract.md | markdown | 1.6 KB |
references/style-contract.md
View on GitHub# Style Contract for Implementation Deep-Dive Articles
## 1. Heading Rules
### Required
- Write headings as declarative noun phrases.
- Keep heading semantics specific and layered.
- Ensure chapter order follows total -> detail -> operation.
### Forbidden
- Question headings (for example: "Why X is not enough?").
- Emotional or exaggerated headings (for example: "ultimate", "crazy", "explosive").
- Ambiguous chapter labels (for example: "Other", "Misc", "Random Thoughts").
## 2. Narrative Rules
### Required
- Explain problem and constraints before solution details.
- Explain mechanism behavior before code references.
- Separate architecture, runtime path, and operations into explicit sections.
### Forbidden
- Using code location lists as the main narrative.
- Claiming performance gains without evidence or clear rationale.
- Repeating implementation details without stating trade-offs.
## 3. Evidence Rules
### Required
- Use diagrams for data flow or control flow.
- Use at least one comparison table for design alternatives.
- Include concrete troubleshooting scenarios.
### Forbidden
- Long unstructured source-file dumps.
- Excessive inline file:line references in explanatory paragraphs.
## 4. Tone Rules
### Required
- Keep language technical, precise, and neutral.
- Prefer concrete terms over slogans.
- Keep claims falsifiable and operational.
### Forbidden
- Marketing adjectives and hype language.
- Rhetorical flourish that weakens precision.
## 5. Definition Rules
- Define domain terms once in a dedicated section.
- Reuse the same term names consistently across sections.
- When two terms are similar, explicitly distinguish them.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |