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/aider/repo-docs/glossary.md
View on GitHub# Glossary
| Term | Plain meaning | Further reading |
| --- | --- | --- |
| `Coder` | The session object that owns chat context, model sending, edit parsing, file writes, reflection, lint/test hooks, and optional commits. | [One real run](walkthroughs/one-real-run.md) |
| `main()` | The CLI entrypoint that turns arguments, config, environment, git state, and mode flags into a configured Aider session. | [Session assembly](modules/session-assembly.md) |
| `Coder.create()` | The factory that chooses the concrete coder class for an edit format and carries session context when switching coders. | [Session assembly](modules/session-assembly.md) |
| `send_message()` | The method that formats the conversation, sends it to the model layer, captures the reply, and starts the post-reply edit checks. | [One real run](walkthroughs/one-real-run.md) |
| `apply_updates()` | The shared method that parses proposed edits, dry-runs them, checks file authority, writes accepted edits, and reflects malformed output. | [Edit lifecycle](modules/edit-lifecycle.md) |
| `prepare_to_edit()` | The step inside `apply_updates()` that checks target-file authority and creates dirty-work checkpoints before final writes. | [Edit lifecycle](modules/edit-lifecycle.md) |
| `check_for_dirty_commit()` | The check that marks an already-dirty target file for a pre-edit checkpoint commit. | [One real run](walkthroughs/one-real-run.md) |
| `allowed_to_edit()` | The file authority check that decides whether a proposed target is already allowed, gitignored, new, or outside the chat. | [Edit lifecycle](modules/edit-lifecycle.md) |
| `dirty_commit()` | The method that commits marked dirty target files before the model edit is written. | [Edit lifecycle](modules/edit-lifecycle.md) |
| `EditBlockCoder` | The concrete coder for diff-style SEARCH/REPLACE edits. | [One real run](walkthroughs/one-real-run.md) |
| `EditBlockCoder.get_edits()` | The parser entrypoint that turns assistant text into structured diff edit tuples. | [Edit lifecycle](modules/edit-lifecycle.md) |
| `EditBlockCoder.apply_edits()` | The concrete write path for SEARCH/REPLACE edits, including the no-match error message. | [Edit lifecycle](modules/edit-lifecycle.md) |
| `ValueError` | The exception family this path uses to signal malformed or non-applicable edit output for reflection. | [Edit lifecycle](modules/edit-lifecycle.md) |
| Edit format | The protocol a concrete coder expects the model to use when proposing changes, such as diff-style SEARCH/REPLACE blocks. | [Edit lifecycle](modules/edit-lifecycle.md) |
| In-chat file | A file that has been added to the current session’s editable context. Aider treats it differently from files merely present in the repo. | [Edit lifecycle](modules/edit-lifecycle.md) |
| Reflected message | Feedback stored for the next model turn when an edit, lint, or test check fails. | [Edit lifecycle](modules/edit-lifecycle.md) |
| Dirty commit | A checkpoint commit for user changes that existed before Aider applies a model edit to the same target file. | [One real run](walkthroughs/one-real-run.md) |
| Auto-commit | A commit Aider may create after applying its own edit when git and options allow it. | [Edit lifecycle](modules/edit-lifecycle.md) |
| Source evidence | The guide’s claim ledger linking explanations to inspected source, tests, commands, and caveats. | [Source evidence](references/source-evidence.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 |