القائمة
Write documentation in the Beyond voice. Use when writing API docs, guides, tutorials, or reference material.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | write-docs |
| description | Write documentation in the Beyond voice. Use when writing API docs, guides, tutorials, or reference material. |
| allowed-tools | Read, Glob, Grep, Edit, Write |
| model | claude-sonnet-4-6 |
Load the verbal identity:
Read: .claude/skills/brand/verbal-identity.md
Documentation is where precision matters most. Clear, direct, technical. Assume competence. Code over prose. No preamble, no context-setting.
POST /boxes/{id}/promote deploys a checkpoint to production.
Not:
In order to deploy your changes to production, you'll need to use our promote endpoint, which takes your checkpoint and makes it live...
These need to be explained once when introduced, then used freely:
| Aspect | Docs Approach |
|---|---|
| Tone | Neutral, precise |
| Assumptions | Reader is competent |
| Length | Minimal |
| Code:Prose | More code, less prose |
| Warmth | None needed |
Audit Rust codebase for production safety issues. Checks unsafe blocks, panic surfaces, resource leaks, concurrency footguns, lint suppression, error swallowing, and dependency risks. Use when reviewing code for production readiness, auditing unsafe usage, or evaluating a crate's safety posture.
Write or improve ARCHITECTURE.md files for packages and systems. Use when creating documentation for a new package, reviewing existing architecture docs, or when asked to document how a system works.
Deep technical audit of a codebase area. Auto-detects language persona (rustacean/gopher/product engineer), evaluates architecture, operations, performance, security, and idioms. Findings scored with ICE model. Use when asked to audit, review quality of, or evaluate a package or directory.
Self-audit after implementing a plan. Verifies completeness, correctness, and that everything is wired up. Rates confidence 1-10 and keeps working until confidence reaches 9+. Use after completing a plan, feature, or significant change.
Audit production readiness of a codebase area. Evaluates tracing, metrics, structured logging, tests, benchmarks, error handling, health checks, graceful shutdown, and configuration. Findings scored with ICE model. Use when asked about production readiness or operational maturity.
Audit test coverage, quality, and gaps for a codebase area. Identifies missing critical tests, evaluates test patterns, and scores gaps with ICE model. Use when asked about test coverage, missing tests, or testing quality.