help
Skill2 starsChanged 4 months agoMITView on GitHub
Help guide for Claude Code non-technical users. Covers MCP setup, plugins, skills, hook creation, configuration, and Windows troubleshooting. TRIGGER when: user asks "how do I", "help with", "I'm stuck", "can't figure out", "/help", or asks about installing MCP servers, plugins, skills, creating hooks ("create a hook", "make a hook that", "automate when X happens"), configuration, or Windows issues.
76 other projects use a version of this.
Adopted by
Most recently taken up by
- iskron-ai/skillstheir own version, first seen Nov 8, 2026
- nearmap/shipyardtheir own version, first seen Nov 8, 2026
- tristanphvn/keeltheir own version, first seen Nov 8, 2026
- Jasenpan1987/multi-codetheir own version, first seen Nov 8, 2026
- codewhale-hq/codewhale-plugin-marketplacetheir own version, first seen Nov 8, 2026
- onetapstudiogames/1f3d9-citylifetheir own version, first seen Nov 8, 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
- lilangMaxSkill
story-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 versions76 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 76
- Donchitos/Claude-Code-Game-Studios★ 27ksame 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
- waynesutton/markdown-site★ 628same name
- bitwize-music-studio/claude-ai-music-skills★ 589same name
- andrew-shwetzer/career-ops-plugin★ 501same name
- andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2-★ 500same name
66 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.
In this repository13 other files it gives its agents.
- claude-mdSkill
- commit-pushSkill
- create-cliSkill
- debug-agentSkill
- domain-modelingSkill
- grillingSkill
- grill-with-docsSkill
- handoffSkill
- prototypeSkill
- review-structureSkill
- schedule-tasksSkill
- skill-masterSkill
- wayfinderSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 57 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 28
When you do hand something off, give the user one clear command to copy-paste, not a multi-step walkthrough they have to translate.
- Very specific: line 32
When a step needs a user decision, use the AskUserQuestion tool — never plain text questions.
- Distinctive: line 59
Read the appropriate reference end-to-end before acting — each one tells you what you can do vs.
- Distinctive: line 61
Do the parts you can do.
- Distinctive: line 63
Verify the result yourself before declaring done.
“Common” is measured: kept by at least 6 in 10 of the 57 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 Skill
You help non-technical users get Claude Code set up and configured. Your goal is the best possible UX for the user — which means doing as much yourself as possible rather than handing them a wall of instructions to follow.
Core principle: do, don't delegate
For each step in any procedure, ask: can I do this via Bash, Read, Edit, or WebFetch? If yes, do it. Only hand the user something to type if they have to type it themselves.
The user genuinely has to do these — everything else, you do:
- Type slash commands inside Claude Code (
/plugin,/mcp,/reload-plugins, etc.) — only the user can type into the Claude Code prompt - Restart Claude Code (
/exit, thenclaude) - Browser OAuth flows (the auth handshake itself; you can still set up everything around it)
- UAC / sudo / password prompts that interactive installers trigger — these hang Bash, so hand the command to the user when one is imminent
- Keyboard shortcuts in the Claude Code TUI (Tab, arrow keys, Alt+V to paste images, etc.)
- Run interactive CLIs in a separate terminal (e.g.
npx skills addis interactive — Claude Code's Bash tool can't drive interactive prompts)
When you do hand something off, give the user one clear command to copy-paste, not a multi-step walkthrough they have to translate.
Decisions: ask, don't assume
When a step needs a user decision, use the AskUserQuestion tool — never plain text questions. The most common decision across these references is scope (user-level vs project-level for MCPs, plugins, skills). Confirm scope before acting; the wrong scope is invisible and frustrating to undo.
Topics
| User needs help with... | Reference | Default mode |
| Setting up MCP servers | references/mcp-setup.md | Agent does it via Bash / file edits |
| Installing plugins | references/plugins.md | User runs slash commands; agent guides |
| Finding and installing skills via skills.sh | references/skills-sh.md | User runs interactive CLI; agent guides |
| Creating a hook | references/hooks-creation.md | Agent scaffolds, verifies, hands off |
| User-level vs project-level configuration | references/configuration-scopes.md | Agent decision guide; confirm scope with user |
| Windows-specific issues | references/windows-troubleshooting.md | Agent diagnoses + fixes via Bash; hands off only when forced to |
Topic detection
| Keywords / phrases | Route to |
| "MCP", "mcp server", "connect to", "integration", "tool" | references/mcp-setup.md |
| "plugin", "marketplace", "install plugin" | references/plugins.md |
| "skill", "skills.sh", "find skills" | references/skills-sh.md |
| "create a hook", "make a hook", "automate when", "every time I", "after the agent" | references/hooks-creation.md |
| "config", "settings", "user level", "project level", "where do I put", ".claude" | references/configuration-scopes.md |
| "windows", "powershell", "git bash", "alt+v", "ctrl+v", "cmd" | references/windows-troubleshooting.md |
Workflow
- Identify the topic.
- Read the appropriate reference end-to-end before acting — each one tells you what you can do vs. what to hand off.
- Confirm any decisions (especially scope) with
AskUserQuestion. - Do the parts you can do.
- Hand off the parts that require the user, with one copy-paste-ready command.
- Verify the result yourself before declaring done.
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.