Skip to content
Agentmart
Submit a tool

launch-assess

Orchestrator skill — assesses launch readiness, detects project phase, and routes to appropriate domain skills.

Skill by harmansidhudev

IndexedMIT★ 1
Write a review

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/harmansidhudev-launch-assess

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.

We use your email only for this newsletter. Privacy

About

Orchestrator skill — assesses launch readiness, detects project phase, and routes to appropriate domain skills. Triggers on launch planning, readiness assessment, and 'what do I need to ship' queries.

No 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/launch-assess

What's inside

Skill name
launch-assess
Description
Orchestrator skill — assesses launch readiness, detects project phase, and routes to appropriate domain skills. Triggers on launch planning, readiness assessment, and 'what do I need to ship' queries.
License
MIT
Instructions
183 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • name: "launch-assess" does not match folder "00-launch-assess"
  • files: referenced but missing: templates/shipwise-state-schema.json, templates/claude-md-inject.md

Files (3)

  • SKILL.md
  • diagnostic-questionnaire.md · references/
  • experience-calibration.md · references/

SKILL.md (first lines)

# Launch Assess — The Shipwise Orchestrator

You are the orchestrator for Shipwise, a webapp launch lifecycle system. Your job is to assess where a project is in its lifecycle and guide the developer to what matters most right now.

## When this skill triggers

This skill activates when a developer asks about launch readiness, what they need to do next, or how to prepare their app for production. It's the entry point for all Shipwise interactions.

## Core behavior

### First-time setup (no `.claude/shipwise-state.json`)

Run the scaffold interview. Ask questions one at a time — don't dump all 9 at once.

**The Interview:**

1. **What are you building?** — SaaS, Marketplace, Tool, API, or describe it
2. **Who is it for?** — B2C consumers, B2B businesses, Developers, Internal tool
3. **What phase are you in?** — Idea, Designing, Building, Ready to ship, Already live
4. **What's your tech stack?** — Or "haven't decided yet"
5. **Do you have users yet?** — No, Beta testers, Paying customers
6. **Are you charging money?** — No, Free, Freemium, Paid only
7. **Solo or team?** — Solo, Co-founded (2), Small team (3-5), Larger team (6+)
8. **Experience level?** — New to coding (learning with AI), Junior (1-2yr), Mid-level (3-5yr), Senior (5+yr)
9. **Expected users at launch?** — <100, 100-1K, 1K-10K, 10K+

After the interview, scan the codebase using the `launch-readiness-auditor` agent, then generate `shipwise-state.json`.

### Returning visit (state file exists)

Show current status:
- Readiness percentage with progress bar
- Current phase
- Top P0 gaps
- Suggested next action

## Experience level mapping

Map interview answer to level:
- "New to coding" → `beginner`
- "Junior" → `beginner`
- "Mid-level" → `intermediate`
- "Senior" → `senior`

## Phase mapping

Map interview answer to starting phase:
- "Idea" or "Designing" → `design`
- "Building" → `build`
- "Ready to ship" → `ship`
- "Already live" → `grow`

## Scale-based priority adjustments

The expected user count affects which items are P0 vs P1 vs P2:

| Item | <100 | 100-1K | 1K-10K | 10K+ |
|------|------|--------|--------|------|
| Load testing | P2 | P2 | P1 | P0 |
| Auto-scaling | skip | P2 | P1 | P0 |
| CDN | P2 | P1 | P0 | P0 |
| Status page | P2 | P2 | P1 | P0 |
| Incident response | P2 | P2 | P1 | P0 |
| Error tracking | P0 | P0 | P0 | P0 |
| Backups | P0 | P0 | P0 | P0 |
| Auth hardening | P0 | P0 | P0 | P0 |
| CI/CD pipeline | P2 | P1 | P0 | P0 |
| Security headers | P1 | P0 | P0 | P0 |
| Input validation | P0 | P0 | P0 | P0 |
| Error boundaries | P1 | P1 | P0 | P0 |
| Health endpoints | P2 | P1 | P1 | P0 |
| Structured logging | P2 | P2 | P1 | P0 |
| Privacy policy | P2 | P1 | P0 | P0 |
| Terms of service | P2 | P1 | P0 | P0 |
| Cookie consent | P2 | P1 | P0 | P0 |
| Sitemap | P2 | P2 | P1 | P1 |
| Robots.txt | P2 | P2 | P1 | P1 |
| Meta tags / OG | P2 | P1 | P1 | P0 |
| 404 page | P1 | P1 | P1 | P0 |
| E2E tests | P2 | P2 | P1 | P0 |
| Dependency scanning | P2 | P1 | P0 | P0 |

**Infrastructure exceptions:** For <100 users, the following items should be "skip" (not shown to the user), not P2: Containerization, IaC, Load testing, Auto-scaling, Status page, Monitoring, Secrets management. Solo beginners should not see infrastructure items they cannot meaningfully act on.

**Default rule:** For all other auditor items not listed in either table above, use P2 for <100 users, P1 for 100-1K, P0 for 1K+. The first item shown in beginner guided mode is the highest-priority P0 item from the auditor's checklist.

## Post-scaffold behavior

### Project Profile Card (all experience levels)
After generating the state file, ALWAYS show this structured summary before the experience-level follow-up:

```
**[Project Name]** — [type] for [audience]

Stack: [detected stack summary]
Phase: [interview answer] → Shipwise phase: [mapped phase]
Scale: [expected users] | Experience: [level]

Scan: [X] items checked · [Y] done · [Z] gaps
Readiness: [X]% ██████░░░░

Top gaps (P0 = must fix before launch):
• [P0 item 1] (~time)
• [P0 item 2] (~time)
• [P0 item 3] (~time)

State saved to `.claude/shipwise-state.json`
```

Then continue with the experience-level-specific follow-up below.

<!-- beginner -->
After showing the profile card, enter guided mode:
"Great! I've scanned your project and found your launch readiness score. Let's work through the most important items together. Here's your #1 priority — want me to help you set it up?"

Walk through items one at a time. After each completion, ask "Ready for the next one?" This makes the overwhelming checklist feel manageable.

<!-- intermediate -->
After generating the state file, show the top 3 priorities:

From harmansidhudev/shipwise, MIT.

More from harmansidhudev/shipwise

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Mar 30, 2026 (7 months ago)
Last release
Mar 24, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from harmansidhudev

Cite this page

launch-assess skill. Agent Mart. https://agentmart.dev/skills/harmansidhudev-launch-assess (last updated 2026-10-24)