Skills Plugins MCP Prompt Model 博客 我的中心

compiler-verify

Use when you need to run all compiler checks (tests, lint, format) before committing. Detects whether TS or Rust code changed and runs the appropriate checks.

DeepseekModel Curated skill Quality Excellent · 90 v1.0.0

Get

https://deepseekmodel.com/api/download.php?id=react-react-compiler-claude-skills-compiler-verify-skill-md&format=skill
Download .skill Standard format with system_prompt and model_config, ready for any agent framework
The actual content of the system_prompt field in the .skill file.
name compiler-verify description Use when you need to run all compiler checks (tests, lint, format) before committing. Detects whether TS or Rust code changed and runs the appropriate checks. Compiler Verify Run all verification steps for compiler changes. Arguments: $ARGUMENTS: Optional test pattern for yarn snap -p <pattern> Instructions Detect what changed by running git diff --name-only HEAD (or vs the base branch). Categorize changes: TS changes : files in compiler/packages/ Rust changes : files in compiler/crates/ Both : run all checks If TS changed , run these sequentially (stop on failure): yarn snap (or yarn snap -p <pattern> if a pattern was provided) — compiler tests yarn test — test full compiler yarn workspace babel-plugin-react-compiler lint — lint compiler source If Rust changed , run these sequentially (stop on failure): bash compiler/scripts/test-babel-ast.sh — Babel AST round-trip tests bash compiler/scripts/test-rust-port.sh — full Rust port test suite (compares Rust vs TS compiler output across all passes; must have 0 failures — do not regress) yarn snap --rust — end-to-end snap tests using the Rust compiler (compares compiled output and logger events against .expect.md fixtures; use yarn snap --rust -p <pattern> for focused checks) Always run (from the repo root): yarn prettier-all — format all changed files If implementing a plan doc , check: Plan doc has no unaddressed "Remaining Work" items Plan doc status is updated to reflect current state Report results: list each step as passed/failed. On failure, stop and show the error with suggested fixes. Common Mistakes Running yarn snap without -p is fine for full verification, but slow. Use -p for focused checks. Running prettier from compiler/ — must run from the repo root. Forgetting Rust tests — if you touched .rs files, always run the round-trip test and yarn snap --rust .
Keywords that activate this skill. Click one to copy it.

This skill does not provide trigger words.

The downloaded .skill package contains the following fields.
Field Description
formatFormat tag (skill/v1)
skill_idUnique skill ID
nameSkill name
versionVersion
descriptionDescription
categoryCategories (array)
trigger_wordsTrigger words
tagsTags
sourceSource
source_urlSource URL (this page)
exported_atExported at (set per download)
system_promptSystem prompt body
model_configModel config: provider / model / temperature / max_tokens / top_p
examplesExamples
install_guideImport guide for Coze / Dify / Claude / custom frameworks
The same skill can be exported in different platform formats.
.skill Standard format with system_prompt and model_config, ready for any agent framework Download
.skillpro Enhanced format with scripts, tools, dependencies and hooks Download
.json Plain JSON export with system_prompt and model parameters only Download
Coze Markdown with frontmatter, for Coze platform import Download
Dify Dify DSL, import directly after creating an app Download

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

验证码 --

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。