help
Skill25 starsChanged 7 months agoMITView on GitHub
Show all available Studio Engine commands with descriptions. Displays command list organized by category, current edition features, and quick start guide. Use when the creator asks "help", "commands", "what can I do", or "how does this work".
82 other projects use a version of this.
Adopted by
Most recently taken up by
- krystaleicher/claude-skillstheir own version, first seen Nov 16, 2026
- rzaaeeff/agent-ledgertheir own version, first seen Nov 16, 2026
- tatashbar/Economic-Modeling-Studiotheir own version, first seen Nov 16, 2026
- finolabs/finolabs-vibecodetheir own version, first seen Nov 16, 2026
- chuanglibs/Claude-Code-Game-Studios-Codextheir own version, first seen Nov 15, 2026
- finolabs/vibecodetheir own version, first seen Nov 15, 2026
Used with
Projects with it also use create-stories, story-done and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
lilangMaxSkillcreate-stories
Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.
Also in 9 projects that use this
lilangMaxSkillstory-done
End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.
Also in 9 projects that use this
- +10 more from lilangMax
Other versions82 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 82
- Donchitos/Claude-Code-Game-Studios★ 39ksame name
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- agenticnotetaking/arscontexta★ 3.5ksame name
- indranilbanerjee/digital-marketing-pro★ 934same name
- bitwize-music-studio/claude-ai-music-skills★ 668same name
- waynesutton/markdown-site★ 628same name
- andrew-shwetzer/career-ops-plugin★ 501same name
- andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2-★ 500same name
72 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 63 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
Read creator.yaml — load name, profile.type, technical_level, workflow_style, language
- Very specific: line 23
Read STATE.yaml — version, products count
- Very specific: line 33
No creator.yaml → warm welcome, suggest /onboard
- Very specific: line 105
After the command table, read creator.yaml → profile.type.
- Distinctive: line 136
If creator asks "platform principles", "how does Claude Code work", "optimization tips", or "why does my product cost tokens", display:
- Distinctive: line 158
If creator asks "what types are there?" or "show me all types", display:
“Common” is measured: kept by at least 6 in 10 of the 63 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Help
Display all available commands and quick start guide.
Activation Protocol
- Shared preamble: Load
references/quality/activation-preamble.md— context assembly, persona adaptation, deterministic routing rules. - Read
creator.yaml— load name, profile.type, technical_level, workflow_style, language - Read
STATE.yaml— version, products count - Load UX stack (in order):
references/ux-experience-system.md§1 Context Assembly, §2.1 Experience Level Scaling, §2.2 Archetype-Awarereferences/ux-vocabulary.md— translate type names and pipeline termsreferences/quality/engine-voice-core.md— vocabulary, three tones, ✦ signature, six anti-patterns, error voicesreferences/quality/engine-voice.md— brand DNA, box frame (load only when rendering the PRO edition box frame, a peak moment)
- Adapt output based on creator context:
- Non-dev → use human type names from ux-vocabulary.md, non-dev pipeline terms
- Beginner → show full pipeline with descriptions
- Expert → compact reference, skip obvious descriptions
- No creator.yaml → warm welcome, suggest /onboard
Core Instructions
Detect edition first, then display:
MyClaude Studio Engine v{version from STATE.yaml} — Command Reference
**IMPORTANT:** Read `creator.yaml → profile.type`. If NOT developer, use the non-dev descriptions below. If developer, use dev descriptions.
**Developer descriptions:**
| Code | Command | Description | Next |
|------|---------|-------------|------|
| ON | /onboard | Set up creator profile | → /scout or /create |
| SC | /scout [domain] | Research domain + recommend setup | → /create |
| MA | /map [topic] | Extract domain knowledge | → /create |
| CR | /create [type] | Scaffold product with DNA | → /fill |
| FI | /fill [slug] | Guided content filling | → /validate |
| VA | /validate [opts] | 7-stage quality check | → /package |
| TE | /test [slug] | Sandbox test (worktree) | → /validate |
| PA | /package [slug] | Bundle triple manifest | → /publish |
| PU | /publish [slug] | Ship to marketplace | done |
| IM | /import [slug] | Bring existing skills in | → /validate |
| TH | /think [topic] | Brainstorm, evaluate, decide | — |
| EX | /explore [query] | Marketplace intel + gaps | — |
| AE | /aegis | Security audit + hardening | — |
| ST | /status | Dashboard + next actions | — |
| HE | /help | This reference | — |
**Non-developer descriptions (all other profile.type values):**
| Command | What it does | Next step |
|---------|-------------|-----------|
| /onboard | Set up your profile | → /scout or /create |
| /scout [domain] | Research your domain before building | → /create |
| /map [topic] | Capture your expertise | → /create |
| /create [type] | Start a new product | → /fill |
| /fill [slug] | Add your knowledge to the product | → /validate |
| /validate | Check quality before sharing | → /publish |
| /test [slug] | Try it out in a safe sandbox | → /validate |
| /package [slug] | Prepare for sharing | → /publish |
| /publish [slug] | Share on the marketplace | done |
| /import [slug] | Bring in existing work | → /validate |
| /think [topic] | Brainstorm or compare options | — |
| /explore [query] | See what others have built | — |
| /aegis | Check code for security issues | — |
| /status | See your dashboard | — |
| /help | This reference | — |
QUICK START (for developers):
/onboard → /scout {domain} → /create → /fill → /validate → /package → /publish
QUICK START (for non-developers — use when profile.type != developer):
/onboard → /scout {domain} → /create → /fill → /validate → /publish
(research → draft → refine → verify → launch)
Type any code or command to execute. Example: "CR skill" = "/create skill"
{if PRO}
PRO AGENTS (active):
Forge Master → orchestrates multi-agent creation flows
Domain Cartographer → deep domain analysis (/map)
Product Architect → architecture decisions (/create)
Quality Sentinel → MCS-2/3 deep review (/validate)
Market Scout → marketplace intelligence (/publish)
{/if}Persona-Aware Recommendations
After the command table, read creator.yaml → profile.type. Add a personalized recommendation:
If marketer/agency:
Recommended for you: /create minds → build an expert advisor for your domain
/create system → build a complete marketing toolkit
See example: references/exemplars/brand-voice-studio/If developer/prompt-engineer:
Recommended: /create skill → build a reusable tool
/create squad → build a team of specialized agents
See examples: references/exemplars/code-health-check/If domain-expert/operator:
Recommended: /create minds → package your expertise as an advisor
/create workflow → automate a step-by-step processIf hybrid or unknown:
Recommended: /scout {your domain} → discover what to build firstIf no creator.yaml exists: Show default quick start without recommendations. Append: "Run /onboard to personalize recommendations."
Platform Principles (show on request)
If creator asks "platform principles", "how does Claude Code work", "optimization tips", or "why does my product cost tokens", display:
10 Platform Principles — How Anthropic's Claude Code Processes Your Product:
1. Put critical rules LAST — Claude pays more attention to the end of files
2. Scope your rules with paths: frontmatter — zero cost when user edits unrelated files
3. Write directives, not suggestions — your rules ARE law (override semantics)
4. claude-md = expensive (always loaded) — every char costs tokens every turn
5. @include depth limit is 5 — deeper files silently ignored
6. hooks in projectSettings can't set permissions — use localSettings
7. Products compile once per session — changes need /clear or new session
8. Model sees WHERE your product came from — project vs personal authority
9. Only text files work in @include — binary files silently ignored
10. Structure by cognitive function — Identity→Knowledge→Execution→Constraints→Output
Full details: references/platform-principles-summary.md
Source evidence: references/cc-platform-contract.md §1-§9Type Reference (show on request)
If creator asks "what types are there?" or "show me all types", display:
13 Product Types:
For individuals: skill, agent, minds, claude-md, output-style
For teams: squad, system, workflow
For builders: application, design-system, hooks, statusline
For curators: bundle
Run /create to pick the right one for your goal.Anti-Patterns
- Wall of text — Keep it scannable. One line per command.
- Stale info — Always read STATE.yaml dynamically, don't hardcode.
- Missing commands — If new skills exist in .claude/skills/ that aren't listed, mention them.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

