Module Docs Explainer
- 1 installs
- Updated July 27, 2026
- cristopher2874/ocigeniworkshop
Generate module-level documentation for Python OCI AI learning paths and workshops.
About
Module Docs Explainer helps document OCI AI services, LangChain integration, and multimodal/agentic workflows in Python.
- Module-level documentation generation
- OCI AI learning path guidance
Module Docs Explainer by the numbers
- 1 all-time installs (skills.sh)
- Ranked #1,361 of 1,879 Documentation skills by installs in the Skillselion catalog
- Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/cristopher2874/ocigeniworkshop --skill module-docs-explainerAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1 |
|---|---|
| Last updated | July 27, 2026 |
| Repository | cristopher2874/ocigeniworkshop ↗ |
What it does
Generate module-level documentation for Python OCI AI learning paths and workshops.
Files
Module Docs Explainer
Use this skill to turn repo docs into a clear learning explanation. It is mid-level: load a small reference file when useful, then inspect the actual README or module files before answering.
Workflow
1. Read references/module-map.md when the user asks where a topic lives. 2. Read references/explanation-examples.md when the user asks for a learning path, comparison, or module explanation. 3. Inspect the relevant repo README before giving detailed guidance. 4. Explain the module in terms of purpose, best entry docs, runnable examples, prerequisites, and a small practice task. 5. Keep file recommendations focused; prefer 3-6 concrete paths over a directory dump.
Output Shape
Return these sections when they fit the request:
What this module teachesBest files to openHow to read itSafe commands to tryWatch outs
Do not invent cloud/API results. If a script needs OCI credentials, say what must be configured before running it.
interface:
display_name: "Module Docs Explainer"
short_description: "Explain modules using repo docs"
default_prompt: "Use $module-docs-explainer to explain the RAG module and point me to the best files."
Explanation Examples
Use these shapes as examples, not rigid templates.
Beginner Topic Request
User asks: "Where should I start if I want to learn agents?"
Answer shape:
1. Start with openai_sdk/agent_sdk/readme_agent_sdk.md for the SDK-first path. 2. Then compare with langChain/agents/readme_agents.md for framework orchestration. 3. Open one simple script before notebooks. 4. Mention the environment check if they plan to run code.
Module Deep Dive
User asks: "Explain langChain/rag."
Answer shape:
1. State what the module teaches. 2. Name the entry README. 3. Group files by concept: chunking, embeddings, retrieval, reranking, full RAG. 4. Suggest one read-only pass and one runnable command. 5. Call out credentials or local files needed for execution.
Path Comparison
User asks: "OpenAI SDK or LangChain first?"
Answer shape:
1. Recommend openai_sdk for most new users in this repo. 2. Recommend langChain when they want framework abstractions and orchestration patterns. 3. Mention oci_genai as useful for direct OCI-native patterns, not the default first stop. 4. Give one concrete file from each path so the comparison is actionable.
Module Map
Use this reference as a lightweight orientation aid. Confirm details in the current repo files before answering.
Primary Paths
| Path | Use it for | Good entry files |
|---|---|---|
README.md | Full repo orientation, setup, learning paths | README.md |
openai_sdk/ | Recommended OpenAI-compatible OCI patterns | readme_openai_sdk.md, genai_client/readme_genai.md, agent_sdk/readme_agent_sdk.md, skills/readme_skills.md |
langChain/ | Framework-based chains, tools, RAG, agents, multimodal examples | llm/readme_langchain_llm.md, agents/readme_agents.md, rag/readme_lang_rag.md |
oci_genai/ | OCI-native examples and legacy/direct SDK flows | module READMEs under llm/, function_calling/, rag/, speech/, vision/ |
database/ | Oracle Database AI examples | readme_database.md, selectai_demo.py, nl2sql_demo.py |
Topic Hints
- Start with
openai_sdk/for project-scoped Responses API examples, containers, memory, vector stores, skills, and Agents SDK. - Start with
langChain/for orchestration patterns and ecosystem integrations. - Start with
database/for Select AI, NL2SQL, semantic cache, and database-backed RAG. - Start with
oci_genai/only when the user specifically needs OCI-native lower-level examples. - Start with
openai_sdk/skills/when the user wants local, inline, curated, or hosted skill examples.
Environment Notes
- Prefer
uv run <path/to/script.py>from the repo root. - Use
uv run AISandboxEnvCheck.pyas the first environment check. - Many AI and database examples require
sandbox.yaml,.env, OCI credentials, and sometimes wallet files. - Notebooks are teaching assets; scripts are usually better for quick verification.
Related skills
Lark MarkdownInstantly turn any markdown file into clean, formatted Lark/Figma-compatible documents without manual reformatting.488k
Lark DocCreate, read, update, summarize, rewrite and manage Feishu/Lark cloud documents directly from agent workflows.401k16.1kLark WikiCreate, organize, query, and manage documents, spaces, and members inside Lark (Feishu) knowledge bases directly from AI agent workflows.397k16.1k
Domain ModelingBuild and sharpen a project's domain model: pin down domain terminology in a glossary and record architectural decisions as ADRs.318k202k
Opensource Guide CoachGet expert, attribution-safe guidance on launching and sustaining an open-source project.270k71Readme I18nMaintain consistent, updatable language selector blocks across every README variant in a multilingual repository.270k71