YurunChen/repo-docs-skills / docs
repo-docs
FlaggedBuild and maintain a Markdown guide that helps humans understand a repository through real behavior, concepts, and evidence. Use when a user asks to understand a repo, generate or update repo-docs, answer repo-architecture/onboarding questions, seed docs for a new project, sync docs after code changes, or delete generated repo docs.
case-studies/generated/tabby/repo-docs/README.md
View on GitHub# Tabby Repo Guide
Tabby is a self-hosted AI coding assistant. This guide starts with the local server path that IDE extensions rely on: a client sends a code-completion request, the server builds a model prompt from editor state and optional code context, then returns a completion response.
The current guide is scoped to the open-source `crates/tabby` completion request path. It does not try to explain the whole monorepo. After the walkthrough, you should be able to follow how `tabby serve --model ...` exposes `/v1/completions`, where request fields become prompt material, which fallbacks keep completion working when context is unavailable, and which tests verify the core behavior.
## Reader Routes
| Reader goal | Start here | What this page gives you |
| --- | --- | --- |
| Understand one real run | [Follow a completion request through the server](walkthroughs/one-real-run.md) | The observable request, service handoffs, prompt construction, model call, response, and boundary cases. |
| Locate the implementation | [Use the completion code map](code-map.md) | Directory responsibilities, important files and symbols, tests, and scoped exclusions. |
| Understand the main concept | [Read the completion pipeline model](modules/completion-pipeline.md) | A plain model for where routing ends, where prompt work begins, and where inference is called. |
| Understand code-context enrichment | [Read how retrieval context enters the prompt](modules/retrieval-context.md) | The rules for editor-provided snippets, indexed-code snippets, repository allow checks, and graceful fallback. |
| Look up exact fields and knobs | [Use the completion contract module](modules/completion-contract.md) | Request fields, response shape, timeout/defaults, and verification commands. |
| Audit the claims | [Inspect the evidence ledger](references/source-evidence.md) | Source links, tests, command evidence, caveats, and the traversal passes used to build the guide. |
| Check guide quality and scope | [Read the quality review](references/quality-review.md) | What the guide proves, what remains out of scope, and what would falsify the model. |
## Scope Note
Confirmed: this first guide covers the Rust server completion endpoint under `crates/tabby`, the shared config fields it depends on, and tests that exercise prompt construction and line-ending behavior.
Out of scope for this first build: the enterprise webserver attachment, chat completions, UI packages, IDE-client internals, model downloader details, code-index construction, deployment guides, and generated web assets. Those areas are adjacent, but they are separate reader paths.
Evidence status: Confirmed unless noted.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |