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/glossary.md
View on GitHub# Glossary
| Term | Plain meaning | Further reading |
| --- | --- | --- |
| Completion request | The JSON payload sent to `/v1/completions` with language, editor segments, debug options, and optional generation knobs. | [Completion contract module](modules/completion-contract.md) |
| `CompletionRequest` | The Rust request struct that represents the completion JSON after Axum parses the body. | [Completion contract module](modules/completion-contract.md) |
| `CompletionResponse` | The Rust response struct serialized back to JSON after model generation finishes. | [Completion contract module](modules/completion-contract.md) |
| `CompletionService::generate` | The per-request service method that chooses the prompt source, builds generation options, calls the model, logs the event, and returns the completion response. | [Completion pipeline](modules/completion-pipeline.md) |
| `CompletionError::EmptyPrompt` | The service error used when a completion request has neither a raw prompt nor the required segment/edit-history input for its mode. | [One real run](walkthroughs/one-real-run.md) |
| `serve::main` | The server startup function that merges config, loads model services, creates routers, and starts the Axum app. | [One real run](walkthroughs/one-real-run.md) |
| Segment | The editor-state object holding text before the cursor, optional text after it, file/repository identity, and optional snippets. | [One real run](walkthroughs/one-real-run.md) |
| Raw prompt | A debug path where the caller supplies the full model prompt and bypasses segment-based prompt building. | [Completion pipeline](modules/completion-pipeline.md) |
| `debug_options.raw_prompt` | The request field that bypasses segment prompt building and sends caller-provided prompt text to inference. | [Completion contract module](modules/completion-contract.md) |
| Retrieval context | Extra code snippets added to the prompt before the current prefix so the model can see related code. | [Retrieval context](modules/retrieval-context.md) |
| `PromptBuilder::collect` | The snippet collection method that combines editor-provided snippets with optional indexed-code search. | [Retrieval context](modules/retrieval-context.md) |
| Allowed code repository | The route/server-side repository allowlist used before indexed code search can use a request `git_url`. | [Retrieval context](modules/retrieval-context.md) |
| `AllowedCodeRepository` | The source type that carries the allowed repository set into the completion route and prompt builder. | [Retrieval context](modules/retrieval-context.md) |
| Prompt template | The model-specific string that arranges prefix and suffix into the form expected by the completion backend. | [Completion pipeline](modules/completion-pipeline.md) |
| `CompletionConfig` | The shared configuration object that provides completion defaults such as max input length and max decoding tokens. | [Completion contract module](modules/completion-contract.md) |
| `ServeArgs` | The CLI argument shape used during server startup, including host, port, device, and model override fields. | [Completion contract module](modules/completion-contract.md) |
| `DebugData` | The optional response object that can include collected snippets or the final prompt when debug options request them. | [Completion contract module](modules/completion-contract.md) |
| `DebugOptions` | The request object that enables raw prompt override, returned snippets, returned prompt, or retrieval disablement. | [Completion contract module](modules/completion-contract.md) |
| `segments.git_url` | The request field that identifies the repository for indexed-code search when repository access is allowed. | [Completion contract module](modules/completion-contract.md) |
| Golden test | An end-to-end test that starts a Tabby server, posts real completion requests, and snapshots the JSON result. | [Source evidence](references/source-evidence.md) |
| `400 Bad Request` | The HTTP status the completion route returns when the service rejects a malformed or incomplete completion request. | [Completion contract module](modules/completion-contract.md) |
| `501 Not Implemented` | The HTTP status registered for `/v1/completions` when the server has no completion service because no completion model is configured. | [Completion contract module](modules/completion-contract.md) |
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 |