just
Design, inspect, debug, and maintain justfile command workflows.
Skill by William Cygan
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/wcygan-just
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/just
What's inside
- Skill name
just- Description
- Design, inspect, debug, and maintain justfile command workflows. Use when adding or changing just recipes, parameters, dependencies, modules, environment loading, shells, working directories, or project command entrypoints.
- License
- MIT
- Compatibility
- Requires just. Verify version-sensitive syntax against the installed command.
- Metadata
- author: William Cygan · version: 0.1.0
- Instructions
- 144 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- manual.md · references/
SKILL.md (first lines)
# Use just effectively
Treat the `justfile` as the public command surface for a project. Keep each
recipe focused on one project outcome.
Read `references/manual.md` when exact syntax, version requirements, shell
behavior, argument passing, environment rules, or multi-file composition
affect the task.
## Establish current evidence
Locate the active `justfile` and relevant repository instructions. Inspect the recipes and underlying commands that determine the requested behavior. Use `just --list` or `--summary` for discovery, `--show <recipe>` for a known target, and `--dump` when the parsed configuration matters. Check `just --version` for version-sensitive syntax.
Inspect expressions before using `just --evaluate` or `--dry-run`: evaluating variables can execute commands even when recipe bodies do not run. Avoid exposing secrets through evaluated output.
Complete this step when the command surface, tool version, underlying commands,
and possible side effects are known.
## Preserve authority
- Keep explanation, review, and diagnosis work read-only.
- For combined diagnosis and implementation requests, continue the authorized changes once the cause is understood.
- Inspect unfamiliar recipes before execution.
- Use existing authorization for deploy, publish, cleanup, reset, or user-state changes; ask only if the requested operation is not covered.
- Preserve the underlying tool as the source of command behavior.
- Keep secrets in process environment variables.
## Design the public command surface
1. Name recipes after stable project outcomes.
2. Add one documentation comment before each public recipe.
3. Choose a safe default recipe or list the available recipes.
4. Use parameters for explicit user input.
5. Use environment variables for process configuration.
6. Use aliases only for established alternative names.
7. Keep a recipe as a thin wrapper around one authoritative command.
Complete this step when each public recipe has a clear name, input contract,
side-effect boundary, and completion result.
## Compose the recipe graph
- Use dependencies for required prior work.
- Pass dependency arguments explicitly.
- Use subsequent dependencies only for required follow-up work.
- Run parallel dependencies only when they have no shared mutable state.
- Start with one `justfile`.
- Use imports when files must share one recipe namespace.
- Use modules when command groups need separate namespaces and settings.
- Invoke another directory's `justfile` when it owns an independent command surface.
Prefer a shallow graph. Move complex control flow into a tested script or
application command.
## Handle values safely
- Quote every substitution that can contain spaces or shell characters.
- Use exported parameters or positional arguments for arbitrary values.
- Use a shebang recipe when commands must share shell state.
- Use `cd <directory> && <command>` for one directory-bound command.
- Select a custom shell only when the project requires it.
- Load environment files explicitly.
- Use required environment loading when missing configuration must stop execution.
- Keep secrets out of substitutions, command echoes, and tracked files.
- Select syntax supported by the project's minimum `just` version.
- Treat list support as unstable until the project accepts that compatibility risk.
## Reusable patterns
### Safe discovery default
```just
# List supported project commands.
default:
@just --list
```
### Local quality gate
```just
# Run all local validation.
check: format-check lint test
# Check justfile formatting.
format-check:
just --fmt --check
# Check source quality.
lint:
./scripts/lint
# Run the test suite.
test:
./scripts/test
```
### Safe parameter forwarding
```just
# Build one named target.
build $TARGET:
./scripts/build "$TARGET"
```
### Stateful multi-step recipe
```just
# Check one prepared artifact.
artifact-check:
#!/usr/bin/env bash
set -euo pipefail
cd dist
../scripts/check-artifact
```
### Monorepo namespaces
```just
# API commands.From wcygan/agent-skills, MIT.
More from wcygan/agent-skills
- 0.570score
maintain-verification-skill
wcygan
Check and repair a project verification skill against source and live behavior.
SkillAFreshness: AClaude Code +9 - 0.570score
coordinate-work
wcygan
Assign independent units, control shared writes, and reconcile results.
SkillAFreshness: AClaude Code +9 - 0.570score
create-verification-skill
wcygan
Create a project skill that launches, exercises, and verifies real application behavior.
SkillAFreshness: AClaude Code +9 - 0.570score
compare-solutions
wcygan
Compare competing solutions and verify a coherent synthesis.
SkillAFreshness: AClaude Code +9 - 0.569score
implement-change
wcygan
Implement a bounded feature or refactor in verifiable steps.
SkillAFreshness: AClaude Code +9 - 0.567score
decision-log
wcygan
Keep an auditable record of consequential choices and evidence.
SkillAFreshness: AClaude Code +9 - 0.567score
deliver-change
wcygan
Present or publish a verified result within authorized scope.
SkillAFreshness: AClaude Code +9 - 0.567score
design-loop
William Cygan
Design, style, or redesign websites and apps through investigation, layout, design-system creation, implementation, validation, and delivery.
SkillAFreshness: AClaude Code +9 - 0.567score
design-options
wcygan
Compare designs and sketch interfaces before implementation.
SkillAFreshness: AClaude Code +9 - 0.567score
improve-workflow
wcygan
Find evidence-backed improvements to an engineering process.
SkillAFreshness: AClaude Code +9 - 0.567score
explain-history
wcygan
Explain the evidence behind a design decision or past failure.
SkillAFreshness: AClaude Code +9 - 0.567score
explain-code
wcygan
Explain subsystem behavior and ownership from evidence.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 11, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 0.1.0
- License
- MIT
- Repository
- github.com/wcygan/agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from William Cygan
- 0.567score
design-loop
William Cygan
Design, style, or redesign websites and apps through investigation, layout, design-system creation, implementation, validation, and delivery.
SkillAFreshness: AClaude Code +9 - 0.565score
discover-ambitious-goals
William Cygan
Find valuable project outcomes and stretch goals from product and engineering evidence.
SkillAFreshness: AClaude Code +9 - 0.561score
maintain-outcome
William Cygan
Maintain a measurable application or engineering outcome through repeated observation, prioritized fixes, and post-delivery verification.
SkillAFreshness: AClaude Code +9
Cite this page
just skill. Agent Mart. https://agentmart.dev/skills/wcygan-just (last updated 2026-10-24)