knowledge-priming
starsforks
How to install knowledge-priming?
techygarg/lattice/knowledge-priming
$npx -y skills add techygarg/lattice --skill knowledge-primingLoad project-specific context -- tech stack, architecture overview, directory layout, trusted sources, and conventions -- so that all skills operate with awareness of what this project actually is. Use when a knowledge base document exists, or when the user asks about the project
SKILL.md
| 1 | # Knowledge Priming |
| 2 | |
| 3 | ## Config Resolution |
| 4 | |
| 5 | 1. Look for `.lattice/config.yaml` in repo root. |
| 6 | 2. If found, check `paths.knowledge_base` for custom doc path. |
| 7 | 3. If doc exists at that path, read the full document. |
| 8 | 4. **STOP: Apply the loaded document as ambient context before any design, implement, or review work begins.** |
| 9 | 5. If no config, path, or doc found → see "When No Document Exists". |
| 10 | |
| 11 | ## When No Document Exists |
| 12 | |
| 13 | Inform the user: |
| 14 | |
| 15 | > No project knowledge base found. AI skills will operate from generic assumptions about tech stack, architecture, and conventions. |
| 16 | > |
| 17 | > To create one, trigger **knowledge-priming-refiner** — guided interview (~10 questions) producing a concise document (~50 lines). |
| 18 | > |
| 19 | > Can also create `.lattice/standards/knowledge-base.md` manually and reference in `.lattice/config.yaml` under `paths.knowledge_base`. |
| 20 | |
| 21 | Do not block. Continue without knowledge base. |
| 22 | |
| 23 | ## What the Document Contains |
| 24 | |
| 25 | | # | Section | What It Captures | |
| 26 | |---|---------|-----------------| |
| 27 | | 1 | **Architecture Overview** | App type, major components, how they interact | |
| 28 | | 2 | **Tech Stack and Versions** | Specific technologies with version numbers, including "not X" clarifications | |
| 29 | | 3 | **Curated Knowledge Sources** | Official docs, trusted blogs, internal references (5–10 max) | |
| 30 | | 4 | **Project Structure** | Directory layout showing where things live | |
| 31 | | 5 | **Project Conventions** | Project-specific conventions other skills cannot infer from code | |
| 32 | |
| 33 | ## Scope Boundary |
| 34 | |
| 35 | | Concern | Owned By | |
| 36 | |---------|----------| |
| 37 | | Coding style, naming principles, function design | clean-code atom | |
| 38 | | Architectural layers, dependency direction | architecture atom | |
| 39 | | Domain modeling, aggregate design | domain-driven-design atom | |
| 40 | | Input validation, injection prevention | secure-coding atom | |
| 41 | | Test structure, assertion quality | test-quality atom | |
| 42 | |
| 43 | Knowledge priming answers *"what are we working with?"* — not *"how should we write?"* |
People who liked this also viewed
6 picksType
- requesting-code-reviewUse when completing tasks, implementing major features, or before merging to verify work meets requirementsSkillsJul 2026
- code-reviewSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- receiving-code-reviewUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performativeSkillsJul 2026
- baoyu-format-markdownFormats plain text or markdown files with frontmatter, titles, summaries, headings, bold, lists, and code blocks. Use when user asks to "format markdown", "beautify article", "add formatting", or imprSkillsJul 2026
- code-review-excellenceMaster effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing reSkillsJul 2026
- code-review-and-qualityConducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensiSkillsJul 2026
