Other · Learning & explanation
help
/help
Use when the user asks about Ship commands, workflow, or how to use the framework
For whom
Assessment and security
87/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content22 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
Deprecation
No signals detected. Repository changed on 25.10.2026, without references to retired models or APIs.
Licence
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Use when the user asks about Ship commands, workflow, or how to use the framework
Original author description
Use when the user asks about Ship commands, workflow, or how to use the framework
How it works
SKILL.md has no level-two headings · 48 lines, 275 words
SKILL.md preview
---
name: help
description: Use when the user asks about Ship commands, workflow, or how to use the framework
effort: low
allowed-tools: []
---
Display the Ship command reference:
```
Ship — Feature-centric development framework for Claude Code
Commands:
/ship:start "idea" Start brainstorming a new feature or fix
/ship:design Compare architecture approaches and let user choose (optional)
/ship:plan Create implementation plan from CONTEXT.md
/ship:plan-verify Verify plan against codebase patterns before building
/ship:build Execute the plan with atomic commits
/ship:verify Verify acceptance criteria + adversarial bug hunt (writes tests)
Per-criterion verdicts: PASS / FAIL / INCONCLUSIVE (no runnable verify command).
/ship:go Auto-run remaining steps (plan → plan loop → build → verify)
Use --auto to skip the "Ready to build?" approval gate.
/ship:finish Complete a feature (create PR, merge, or keep branch)
Use --accept-inconclusive "reason" to override INCONCLUSIVE verdicts.
/ship:status Show all features and their status
/ship:resume Pick up where you left off on a feature
/ship:ledger Show the planned-feature ledger (.planning/LEDGER.md)
add <idea> | <slug> now|next|someday|top | drop <slug>
/ship:help Show this reference
Flow:
start → [design →] plan → plan-verify → build → verify → finish
(or just: start → go → finish)
/ship:go runs the plan revision loop (review → replan → re-review, max 5
rounds) and the build→verify spine in background Workflows (agent output
stays out of the main context); round-1 planning, the build-approval gate
(skipped with --auto), and finish run interactively. The plan loop
interrupts only when the replanner needs a decision you must make.
On verify FAIL: fix tasks are appended to PLAN.md; resume runs build again.
On INCONCLUSIVE: /ship:finish requires --accept-inconclusive "reason" to proceed.
Feature directory: .planning/features/{name}/
CONTEXT.md Brainstorm output (problem, decisions, acceptance criteria)
PLAN.md Implementation plan with tasks
REVIEW.md Per-phase review findings (build)
VERIFY.md Verification report (criteria + bug hunt)
```
$ARGUMENTS
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · dilhanz/ship | 87 | MIT |
| Ovich/charrette | 100 | MIT |
| davepoon/buildwithclaude | 100 | MIT |
| crisandrews/clawcode | 100 | MIT |
| lamngockhuong/aiteamkit | 100 | MIT |
| The01Geek/prflow | 100 | MIT |
| Cruna-Noise-To-Signal/cruna-plugins | 100 | Apache-2.0 |
| wookiya1364/scv-claude-code | 100 | MIT |
| oliver-kriska/claude-elixir-phoenix | 100 | MIT |
Database snapshot: 13.11.2026 · package version abefc9b85c64 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 95ponytail-help
Quick reference for ponytail levels, skills and commands. One-shot display. Use for /ponytail-help, "ponytail help", "how do I use ponytail". - 100ddw-help
Getting-started guide for DDW. Use it when the user asks "how do I use DDW", "how do I start / install DDW", "what is DDW", or "what commands does DDW have". Trigger: /ddw-help. - 85st-help
Pick the right skill from this pack for a task, and explain how the pack fits together. Use when the user asks which skill to use, what the pack contains, or types /st-help. - 81tool-catalog
Show Arch Studio help, available skills, agents and host-specific commands. Use for help, how do I use Arch Studio, what is Norma, or a capability directory. - 100daw-help
Getting-started guide for DAW. Use it when the user asks "how do I use DAW", "how do I start / install DAW", "what is DAW", or "what commands does DAW have". Trigger: /daw-help. - 100squad-commands
Categorized catalog of common Squad operations. Coordinator reads this file and presents it as an interactive menu when the user asks for available commands or help.