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/references/quality-review.md
View on GitHub# Quality Review
This is an audit note. It checks whether the guide transfers a usable reader model and where risk remains.
## Reader Simulation
| Reader question | Answer from the guide |
| --- | --- |
| What real path is followed? | A `tabby serve` server handles a POST to `/v1/completions` and returns completion JSON. |
| What is hard or non-trivial? | The server must turn editor state into a model prompt while optional retrieval context, line-ending style, route availability, and debug switches can change the path. |
| What changes at each phase? | CLI/config creates the service, the router adds request context, the service chooses raw prompt or segments, optional snippets enter the prefix, the prompt is templated, the model output is logged and returned. |
| Where would I change this behavior? | [`code-map.md`](../code-map.md) routes startup to `crates/tabby/src/`, HTTP adaptation to `routes/`, completion logic to `services/`, prompt enrichment to `services/completion/`, and verification to `crates/tabby/tests/`. |
| Where do assumptions stop? | Missing prompt material returns `400`; no completion model returns `501`; retrieval errors return no snippets and allow completion to continue. |
| What would prove this explanation wrong? | Changes in `CompletionService::generate`, `PromptBuilder::collect`, route status mapping, or completion config defaults that contradict the documented flow. |
| What would a careful newcomer ask next? | How repositories are indexed before retrieval can work. The guide defers that path and labels it out of scope. |
| How can I verify it? | Run the listed unit tests for prompt construction, CRLF, and retrieval fallback; use `run_golden_tests_cpu` for a heavier end-to-end server check. |
## Review Table
| Review question | Result | Evidence | Follow-up |
| --- | --- | --- | --- |
| Can a reader state the hard part in one sentence? | Pass | Walkthrough opening names prompt construction, optional context, line endings, and route/model availability. | Keep this pressure visible if the guide later expands to chat or indexing. |
| Can the walkthrough explain the flow without source links? | Pass | Each step starts with behavior before source locators. | Re-check after future syncs. |
| Is there a real boundary path? | Pass | Empty input maps to `400`; missing completion model maps to `501`; retrieval failure falls back to no snippets. | Add runtime output examples if a future sync runs the full server check. |
| Are claims backed by source, tests, config, data, or command evidence? | Pass | `references/source-evidence.md` records Pass 1, Pass 2, claim rows, source links, and commands. | Keep claim rows merged and concise as scope grows. |
| Does the evidence map name adjacent paths checked but not traced? | Pass | Coverage notes exclude chat, EE webserver, indexing internals, clients, deployment, and UI. | Build separate walkthroughs for those paths when requested. |
| What residual risk remains? | Medium | Unit-test verification is cheap; full golden test may require model startup/download and was not assumed as already run in the guide. | Run the exact tests before relying on the guide for release-critical behavior. |
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 |