Slash Commands

All available Candid commands.

/candid-review

Run a code review on your changes.

/candid-review

Options

Flag	Description
`--harsh`	Use brutal honesty tone
`--constructive`	Use caring directness tone
`--focus <mode>`	Focus on security, performance, architecture, or edge-case
`--auto-commit`	Auto-commit applied fixes
`--re-review`	Compare against previous review
`--merge-target <branch>`	Specify the branch to diff against
`--exclude <pattern>`	Exclude files matching pattern

Examples

/candid-review --harsh --focus security
/candid-review --constructive --auto-commit
/candid-review --re-review

/candid-loop

Run code review in a loop until all issues are resolved.

/candid-loop

Options

Flag	Description
`--mode <auto\|review-each\|interactive>`	Execution mode (default: auto)
`--max-iterations <N>`	Maximum loop iterations (default: 5)
`--categories <list>`	Categories to enforce: critical, major, standards, smell, edge_case, architectural, or all (default: all)

Modes

auto (default): Automatically applies all fixes until clean
review-each: Go through each fix one by one (Yes/No for each)
interactive: Full control with skip, ignore, and batch options

Examples

/candid-loop
/candid-loop --mode review-each
/candid-loop --mode interactive
/candid-loop --max-iterations 3
/candid-loop --categories critical,major

/candid-init

Generate a Technical.md file by analyzing your codebase.

/candid-init

Options

Flag	Description
`--template <name>`	Use a specific template (minimal, react, node, python)
`--effort <level>`	Analysis depth: quick (~30s), medium (~1-2min), thorough (~5-10min, default)
`--output <path>`	Custom output path (default: .candid/Technical.md)
`--optimize`	Run `/candid-optimize` after generation with interactive apply
`--auto-optimize`	Run `/candid-optimize` after generation and apply all recommendations without prompting

Effort Levels

quick: Fast analysis - framework detection, directory structure, file suffixes
medium: Balanced - adds naming conventions, error patterns, reads 5-8 key files
thorough: Comprehensive - launches sub-agents to read ALL files in parallel (default)

Examples

/candid-init
/candid-init --template react
/candid-init --effort quick
/candid-init --effort thorough
/candid-init --optimize         # Audit and tighten the generated context
/candid-init --auto-optimize    # Same, but apply all recommendations automatically

/candid-ship

Ship your branch — review, build, test, create PR, and optionally auto-merge.

/candid-ship

Options

Flag	Description
`--auto-merge`	Auto-merge the PR after creation
`--no-auto-merge`	Disable auto-merge even if config enables it
`--skip-review`	Skip the candid-loop review step
`--skip-build`	Skip build verification
`--skip-tests`	Skip test execution
`--dry-run`	Show plan without executing

Examples

/candid-ship
/candid-ship --auto-merge
/candid-ship --skip-review
/candid-ship --dry-run
/candid-ship --skip-review --skip-build --skip-tests

/candid-fast-ship

Ship low-risk changes — only the steps you enable in fastShip config will run.

/candid-fast-ship

Options

Flag	Description
`--auto-merge`	Enable auto-merge after PR creation
`--no-auto-merge`	Disable auto-merge even if config enables it
`--dry-run`	Show plan without executing

Examples

/candid-fast-ship
/candid-fast-ship --auto-merge
/candid-fast-ship --dry-run

Configure which steps run in .candid/config.json under the fastShip key. See Candid Fast Ship for full documentation.

/candid-chrome-qa

Drive a real Chrome session against your running web app and write structured findings JSON to .context/findings/.

/candid-chrome-qa

Options

Flag	Description
`--url <url>`	App URL to test (skips the URL prompt)
`--mobile-only`	Skip the desktop pass and run mobile-only

Examples

/candid-chrome-qa
/candid-chrome-qa --url http://localhost:3000
/candid-chrome-qa --mobile-only

See Candid Chrome QA for full documentation.

/candid-chrome-qa-fix

Read the latest candid-chrome-qa findings JSON, pick which findings to fix, and dispatch fixes — batched PR, one PR per finding via Conductor deep links, local-only, or issues-only. Optionally files Linear issues per finding.

/candid-chrome-qa-fix

Options

Flag	Description
`--file <path>`	Use a specific findings file
`--severity P0,P1`	Only consider these severities
`--category bug,a11y`	Only consider these categories
`--strategy <name>`	One of `batched`, `per-finding`, `local`, `issues-only`
`--max-parallel N`	Per-finding deep-link launch batch size (default 4)
`--print-links`	In per-finding mode, print deep links instead of opening them
`--fast`	In batched mode, hand off to `/candid-fast-ship` instead of `/candid-ship`
`--create-issues`	Force-enable Linear issue creation
`--no-create-issues`	Force-disable Linear issue creation
`--tracker-team <KEY>`	Override `issueTracker.teamKey` for this run

Examples

/candid-chrome-qa-fix
/candid-chrome-qa-fix --severity P0,P1
/candid-chrome-qa-fix --strategy issues-only
/candid-chrome-qa-fix --strategy per-finding --print-links
/candid-chrome-qa-fix --strategy batched --create-issues --tracker-team ENG

See Candid Chrome QA Fix for full documentation.

/candid-validate-standards

Check your Technical.md for issues.

/candid-validate-standards

Options

Flag	Description
`--fix`	Auto-fix issues where possible

What It Checks

🌫️ Vague rules without clear criteria
📏 Missing thresholds or limits
🔧 Rules that overlap with linters

Slash Commands

/candid-review

Options

Examples

/candid-loop

Options

Modes

Examples

/candid-init

Options

Effort Levels

Examples

/candid-ship

Options

Examples

/candid-fast-ship

Options

Examples

/candid-chrome-qa

Options

Examples

/candid-chrome-qa-fix

Options

Examples

/candid-validate-standards

Options

What It Checks

See Also