Nagi 凪
Bringing clarity to chaos
Nagi

Nagi 凪

Bringing clarity to chaos.
Bringing clarity to chaos. Nagi turns messy thoughts, screenshots, notes, and raw context into agent-ready prompts. Capture the rough version, find the signal, and generate structured instructions your agents can execute.
Start with the storm.

Paste the mess. Pick a mode and target. Hit Transform.
Nagi compiles it into a structured, agent-ready prompt.

Target:
Saved prompts
Debug / Fix
Compiler mode
Settings
Builder mode
Building as: Operational Builder
Intent describe your goal
Start from a builder template guided prompts
Starter templates that shape the prompt for the current builder mode.
Start from an assistant workflow complete prompts
Ready-made end-to-end prompts for inbox, calendar, planning, follow-ups, and personal ops.
Output
Guardrails What "done" looks like, deadline, who depends on this.
Agent actions turn prompt into action
Append directives so the agent doesn't just answer — it captures and proposes next moves.
Data Sources
Skill metadata SKILL.md
AI tool tool spec
GitHub repo path or local script to use as a starting point.
Claude Code plugin marketplace
Checkpoint roadmap
Generated output — Operational Builder
Prompt
Signals
Click to toggle. Signals are never auto-applied.
Copied!

Identity context

About you
Preferences
凪 Prompt Craft
The Storm Principle

Start messy. Nagi's compiler is designed to extract signal from noise. Don't overthink your input — paste the raw thought, error log, Slack thread, or half-formed idea. The compiler will structure it.

Be Specific About What, Not How

Good: "Login form submits but shows blank page instead of /dashboard"

Weak: "Fix the login"

Name the behavior you see, the behavior you expect, and where it happens. Nagi fills in the engineering structure.

Include File Paths

When you mention files (src/components/Auth.tsx, styles/nav.css), Nagi detects them and routes them into the right context section. This dramatically improves the output.

One Task Per Prompt

Compound requests ("fix the login AND redesign the nav AND add tests") produce diluted output. Split them into focused prompts. Each transform should have one clear objective.

Use Templates for Structure

When the prompt strength bar shows below 60%, Nagi suggests a template. Templates aren't bureaucracy — they're the fields that make agents perform. Fill the starred fields at minimum.

State Constraints Explicitly

Good: "Don't change the auth flow, just fix the redirect"

Constraints prevent agents from over-engineering. Tell them what NOT to do and they'll stay focused.

Refine After Transform

After compiling, use the refine chips (Deeper, Shorter, Code only, Ship-ready) to adjust the output. You can also add context and recompile without starting over.

Mode Selection

Auto — Nagi detects the right mode from your input. Works 90% of the time.

Claude Code — Full directive with Explore/Plan/Implement/Verify structure and guardrails.

Refine — Clean up and restructure an existing prompt.

Compress — Strip noise from verbose context while keeping signal.

Audit — Find quality issues in a prompt and get a rewrite.

Personal Ops — Life admin: triage, scheduling, drafting messages.

Shorten — Maximum brevity while preserving intent.

Saved prompts

Signal reference