一键导入
just
Reference for `just`, the command runner. Use when working in a project with a `justfile` or when the user mentions `just` or `justfile`.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Reference for `just`, the command runner. Use when working in a project with a `justfile` or when the user mentions `just` or `justfile`.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Expert knowledge for the darkmatter Rust library - Markdown parsing, composition, frontmatter, terminal/HTML/Markdown rendering, style frontmatter, syntax highlighting, document comparison, and disclosure blocks. Use when parsing or composing Markdown, rendering Markdown to terminal/HTML/Markdown, working with DarkmatterPage, `style:` frontmatter, frontmatter hashing, disclosure blocks (`::disclosure` / `::details` / `::end-disclosure`), or comparing documents.
Use when working in the claudine/ package area or with the Claudine library/CLI — normalizing agentic-CLI lifecycle events and hooks, wrapping providers (Claude Code, Codex, Gemini, Goose, Kimi, OpenCode, Qwen, Kilo, Pi, Antigravity), composing Markdown prompts (compose/inline-compose/sequence), managing the MCP catalog, linking skills/commands/agents across providers, or researching agentic CLI platform behavior.
Expert knowledge for the unchained-ai LLM pipeline library including pipeline primitives, provider registry, model catalogs, rig-core integration, code generation, and agent status monitoring. Use when working in unchained-ai/, building LLM pipelines, adding providers/models, implementing pipeline steps, running the model generator, or querying agentic platform limits.
Expert knowledge for the Agent Client Protocol (ACP) and its underlying JSON-RPC standard, with Rust and TypeScript libraries. Use when implementing or integrating ACP, building an ACP client or agent, or devising strategies for interacting with agentic CLI providers (Claude Code, Codex, Kimi Code, OpenCode, Gemini CLI) over ACP.
Configuring models in agentic CLIs — adding local or cloud models to Claude Code, Codex, Gemini CLI, Goose, Kimi Code, OpenCode, Qwen Code, Pi, or Kilo Code. Use when wiring a local runner (Ollama, LM Studio, oMLX, llama.cpp, vLLM) into an agentic CLI, redirecting a provider's base URL (ANTHROPIC_BASE_URL, OPENAI_BASE_URL, model_providers, provider.<id>.options.baseURL), choosing between OpenAI-compatible and Anthropic-compatible endpoints, bridging a CLI to a different cloud vendor's models, or working with per-provider model config file shapes and merge semantics.
Detecting, configuring, and wiring local model runners into agentic CLIs. Use when working with Ollama, LM Studio, oMLX, llama.cpp (llama-server), or vLLM; probing which local runners are installed or running; hitting OpenAI-compatible local endpoints (/v1) or Anthropic-compatible /v1/messages; serving local models; or connecting a local model to OpenCode or Claude Code via base URL, ANTHROPIC_BASE_URL/ANTHROPIC_AUTH_TOKEN, or runner-native launch hooks.
| name | just |
| description | Reference for `just`, the command runner. Use when working in a project with a `justfile` or when the user mentions `just` or `justfile`. |
just --dump Print justfilejust --evaluate Print variable valuesjust --help Print detailed command-line syntax helpjust --list Print recipes with descriptionsjust --show <RECIPE> Print recipe sourcejust --summary Print recipes without descriptionsjust Run default recipejust <RECIPE> Run specific recipejust <RECIPE> <ARG1> <ARG2 Run recipe with argumentsexecutable := 'main'
# compile main.c
compile:
cc main.c -o {{ executable }}
# run main
run: compile
./{{ executable }}
# run test
test name: compile
./bin/test {{ name }}
# start webserver
serve port='8080':
python -m http.server {{port}}
# publish current tag
publish:
#!/usr/bin/env bash
set -euxo pipefail
tag=`git describe --tags --exact-match`
./bin/check-tag $tag
git push origin $tag
The comment proceeding a recipe is used as its doc-comment, and included in
just --list.
By default, each line of a recipe runs in a fresh shell. Recipes whose bodies
start with #! are written to a file and executed as a script.
Commonly used commands and scripts should be turned into just recipes.
In the rusty-monorepo (where you are currently working), you will find:
justfile at the root of the monorepojustfile in each "package area" in the mono repo (run sniff repo package-areas) for a list of package areasjust/* directory:
ai.just provides some useful recipes for interacting with AIdevops.just provides useful devops commands like commit, _build, _lint, _install, and many morelifecycle.just provides some opinionated lifecycle commands like:
schedule moves a previously unscheduled feature or fix (in the _unschedule subdirectory of features or fixes) into the "features" or "fixes" directory and changes the name to be prefixed with the DATE that this specification has been moved to being scheduledcomplete moves a scheduled feature to the _completed directorynotify.just provides ways to inform the user of status including:
_speak provides TTS services to allow the host to speak a message_play and _play_background provides a set of sound effects which the user can choose from to indicate some sort of eventreview.just provides a way for a user to kickoff a review process or implement the suggestions from a review (leveraging the "claudine" service defined in this monorepo)spec.just provides a way for a users to:
just feature, just fix)just clarify)plan.just provides a user a way to create and then implement plan for a specification file and/or a technical design (or both)util.just provides a number of utility recipes that the other .just files leverageWhen you start your work read the memory/just.md file (if it exists) as it provides useful context that has been learned over time.
If you feel like you learned something novel about just and not within your normal training set that is worth remembering then you should append that learning to the memory/just.md file (create the file if it doesn't exist).
Recipe Parameters documentation.