Expert guidance for Just, a command runner with syntax inspired by make. Use this skill for creating justfiles, writing recipes, configuring settings, and implementing task automation workflows.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versioncli-justExecute the skills CLI command in your project's root directory to begin installation:
Fetches cli-just from paulrberg/agent-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate cli-just. Access via /cli-just in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
0
total installs
0
this week
42
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
42
stars
Expert guidance for Just, a command runner with syntax inspired by make. Use this skill for creating justfiles, writing recipes, configuring settings, and implementing task automation workflows.
Key capabilities:
set allow-duplicate-recipes # Allow recipes to override imported ones
set allow-duplicate-variables # Allow variables to override imported ones
set shell := ["bash", "-euo", "pipefail", "-c"] # Strict bash with error handling
set unstable # Enable unstable features (modules, script attribute)
set dotenv-load # Auto-load .env file
set positional-arguments # Pass recipe args as $1, $2, etc.
| Attribute | Purpose |
|---|---|
[arg("p", long, ...)] |
Configure parameter as --flag option (v1.46) |
[arg("p", pattern="…")] |
Constrain parameter to match regex pattern |
[group("name")] |
Group recipes in just --list output |
[no-cd] |
Don't change to justfile directory |
[private] |
Hide from just --list (same as _ prefix) |
[script] |
Execute recipe as single script block |
[script("interpreter")] |
Use specific interpreter (bash, python, etc.) |
[confirm("prompt")] |
Require user confirmation before running |
[doc("text")] |
Override recipe documentation |
[positional-arguments] |
Enable positional args for this recipe only |
The [arg()] attribute configures parameters as CLI-style options:
# Long option (--target)
[arg("target", long)]
build target:
cargo build --target {{ target }}
# Short option (-v)
[arg("verbose", short="v")]
run verbose="false":
echo "Verbose: {{ verbose }}"
# Combined long + short
[arg("output", long, short="o")]
compile output:
gcc main.c -o {{ output }}
# Flag without value (presence sets to "true")
[arg("release", long, value="true")]
build release="false":
cargo build {{ if release == "true" { "--release" } else { "" } }}
# Help string (shown in `just --usage`)
[arg("target", long, help="Build target architecture")]
build target:
cargo build --target {{ target }}
Usage examples:
just build --target x86_64
just build --target=x86_64
just compile -o main
just build --release
just --usage build # Show recipe argument help
Multiple attributes can be combined:
[no-cd, private]
[group("checks")]
recipe:
echo "hello"
Terminal formatting constants are globally available (no definition needed):
| Constant | Description |
|---|---|
CYAN, GREEN, RED, YELLOW, BLUE, MAGENTA |
Text colors |
BOLD, ITALIC, UNDERLINE, STRIKETHROUGH |
Text styles |
NORMAL |
Reset formatting |
BG_* |
Background colors (BG_RED, BG_GREEN, etc.) |
HEX, HEXLOWER |
Hexadecimal digits |
Usage:
@status:
echo -e '{{ GREEN }}Success!{{ NORMAL }}'
echo -e '{{ BOLD + CYAN }}Building...{{ NORMAL }}'
# Require executable exists (fails recipe if not found)
jq := require("jq")
# Get environment variable with default
log_level := env("LOG_LEVEL", "info")
# Get justfile directory path
root := justfile_dir()
Display formatted status during multi-step workflows:
@_run-with-status recipe *args:
echo ""
echo -e '{{ CYAN }}→ Running {{ recipe }}...{{ NORMAL }}'
just {{ recipe }} {{ args }}
echo -e '{{ GREEN }}✓ {{ recipe }} completed{{ NORMAL }}'
alias rws := _run-with-status
Pair check (verify) and write (fix) recipes for code quality tools:
[group("checks")]
@biome-check +globs=".":
na biome check {{ globs }}
alias bc := biome-check
[group("checks")]
@biome-write +globs=".":
na biome check --write {{ globs }}
alias bw := biome-write
Aggregate all checks with status reporting:
[group("checks")]
@full-check:
just _run-with-status biome-check
just _run-with-status prettier-check
just _run-with-status tsc-check
echo ""
echo -e '{{ GREEN }}All code checks passed!{{ NORMAL }}'
alias fc := full-check
[group("checks")]
@full-write:
just _run-with-status biome-write
just _run-with-status prettier-write
echo ""
echo -e '{{ GREEN }}All code fixes applied!{{ NORMAL }}'
alias fw := full-write
| Recipe | Alias | Recipe | Alias |
|---|---|---|---|
| full-check | fc | full-write | fw |
| biome-check | bc | biome-write | bw |
| prettier-check | pc | prettier-write | pw |
| mdformat-check | mc | mdformat-write | mw |
| tsc-check | tc | ruff-check | rc |
| test | t | build | b |
Just supports inline scripts in any language via two methods:
Use [script("interpreter")] for cross-platform compatibility:
[script("node")]
fetch-data:
const response = await fetch('https://api.example.com/data');
const data = await response.json();
console.log(data);
[script("python3")]
analyze:
import json
with open('package.json') as f:
pkg = json.load(f)
print(f"Package: {pkg['name']}@{pkg['version']}")
[script("bash")]
deploy:
set -e
npm run build
aws s3 sync dist/ s3://bucket/
Use #!/usr/bin/env interpreter at the recipe start:
node-script:
#!/usr/bin/env node
console.log(`Node ${process.version}`);
console.log(JSON.stringify(process.env, null, 2));
python-script:
#!/usr/bin/env python3
import sys
print(f"Python {sys.version}")
bash-script:
#!/usr/bin/env bash
set -euo pipefail
echo "Running on $(uname -s)"
When to use which:
[script()] - Better cross-platform support, cleaner syntaxset unstableInclude recipes from another file:
import "./just/settings.just"
import "./just/base.just"
import? "./local.just" # Optional (no error if missing)
Load submodule (requires set unstable):
mod foo # Loads foo.just or foo/justfile
mod bar "path/to/bar" # Custom path
mod? optional # Optional module
# Call module recipes
just foo::build
For projects using @sablier/devkit:
import "./node_modules/@sablier/devkit/just/base.just"
import "./node_modules/@sablier/devkit/just/npm.just"
Standard section header format:
# ---------------------------------------------------------------------------- #
# DEPENDENCIES #
# ---------------------------------------------------------------------------- #
Common sections (in order):
Always define a default recipe:
# Show available commands
default:
@just --list
Document required tools at the top:
# ---------------------------------------------------------------------------- #
# DEPENDENCIES #
# ---------------------------------------------------------------------------- #
# Bun: https://bun.sh
bun := require("bun")
# Ni: https://github.com/antfu-collective/ni
na := require("na")
ni := require("ni")
nlx := require("nlx")
# Usage: invoke directly in recipes (not with interpolation)
build:
bun next build
Note: require() validates the tool exists at recipe evaluation time. Use the variable name directly (e.g., bun), not with interpolation ({{ bun }}).
For Just features not covered in this skill (new attributes, advanced functions, edge cases), fetch the latest documentation:
Use context7 MCP with library ID `/websites/just_systems-man` to get up-to-date Just documentation.
Example topics to search:
modules import mod - Module system detailssettings - All available settingsattributes - Recipe attributesfunctions - Built-in functionsscript recipes - Script block syntaxFor detailed patterns and comprehensive coverage, consult:
references/settings.md - Settings configuration and module systemreferences/recipes.md - Recipe attributes, parameters, dependencies, and prefixesreferences/syntax.md - Constants, functions, variables, and CLI optionsreferences/patterns.md - Established conventions, section organization, helper patternsWorking justfile templates in examples/:
devkit.just - Minimal template importing @sablier/devkitstandalone.just - Full standalone template with all patterns/websites/just_systems-manDo not use just --fmt or just --dump. The user has bespoke formatting preferences that the built-in formatter does not respect. Preserve existing formatting as-is.
@ prefix to suppress command echo: @echo "quiet"+ for variadic parameters: test +args* for optional variadic: build *flagsGLOBS := "\"**/*.json\""[no-cd] in monorepos to stay in current directory_ or use [private]Make data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
ailabs-393/ai-labs-claude-skills
pproenca/dot-skills
I recommend cli-just for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
We added cli-just from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
cli-just reduced setup friction for our internal harness; good balance of opinion and flexibility.
cli-just has been reliable in day-to-day use. Documentation quality is above average for community skills.
cli-just fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Useful defaults in cli-just — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
Solid pick for teams standardizing on skills: cli-just is focused, and the summary matches what you get after install.
I recommend cli-just for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Registry listing for cli-just matched our evaluation — installs cleanly and behaves as described in the markdown.
cli-just reduced setup friction for our internal harness; good balance of opinion and flexibility.
showing 1-10 of 46