Skip to content

V8-Serverless/Telegram-Bot-Production- / .flue/.agents/skills/style-guide-review

style-guide-review

Verified

Review changed MDX/docs files in a pull request against the Cloudflare docs style guide and return structured findings.

reference/rule-authoring.md

View on GitHub
# How to Write Style-Guide Review Rules

This file is guidance for maintainers and agents who add new rules to the style-guide review skill. It is not a runtime review file and is not listed in `manifest.json`.

## Rule categories

| Category     | Directory                  | Load condition                                           |
| ------------ | -------------------------- | -------------------------------------------------------- |
| `always`     | `reference/always/`        | Loaded for every reviewed MDX file with added content.   |
| `conditional`| `reference/conditional/`   | Loaded when the patch matches a trigger described in the manifest `when` field and the SKILL.md reference selection. |
| `component`  | `reference/components/`    | Loaded when the patch contains a specific component tag or imports a component name. The manifest `componentNames` field lists which names trigger the load. |

## Rule format

Each rule is an explicit if/then check with a severity:

```
- If <condition on added lines> → **<severity>**: <what to do>.
```

Severities:
- `warning` — clear rule violation, correctness issue, or convention breach.
- `suggestion` — improvement covered by a rule but not strictly required.

## Writing a good rule

1. **Be specific.** The condition must be checkable by mechanical pattern matching on added lines. Avoid vague guidance like "consider improving clarity."
2. **Include false-positive exceptions.** If a rule could fire inside code blocks, JSX component props, or application code examples, add an explicit exception.
3. **Do not duplicate CI.** Before adding a rule, verify the repository does not already catch the issue in CI (build, typecheck, lint, link validation, schema validation).
4. **Remember the agent sees added lines by default.** Rules match on the content of added/changed lines with their new-file line numbers. The agent can optionally use `read_repo_file` to read the full current file for surrounding context (e.g. to check whether an added line is inside a fenced code block), but rules should be written to match on the added lines themselves whenever possible.
5. **Consider providing examples.** Correct and incorrect examples help the model pattern-match accurately, but keep them minimal — rule files share context window space, so conciseness matters.

## Wiring a new rule

1. Create or edit the reference `.md` file in the appropriate `reference/` subdirectory.
2. Add an entry to `reference/manifest.json` with `id`, `file`, `load`, and `when` (plus `componentNames` for component rules).
3. Update the SKILL.md reference selection section with a new load condition line for conditional rules.
4. Add at least two eval cases: one that triggers the rule and one clean counterexample that does not.
5. Update `.agents/references/style-guide.md` if the rule represents a public docs convention that contributors should follow.

## Evaluating rules

Run the style-guide evals against a live Flue dev server:

```bash
pnpm run flue:dev          # terminal 1
pnpm --dir .flue run evals # terminal 2
```

Each new rule should have:
- A **violation eval** — added lines that should trigger the rule. Assert the finding exists with the expected severity, path, and line.
- A **clean counterexample eval** — added lines that are similar but correct. Assert no warnings are produced.
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: 471kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexUnverifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall