help
Skill1 starsChanged 8 days agoMITView on GitHub
Use when the builder asks what OMT skills are available, how to use them, or wants a quick tutorial on the One Man Team workflow. Also triggers on "help", "what can you do", "list commands", or "how does this work".
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
- codewhale-hq/codewhale-plugin-marketplacetheir own version, first seen Nov 8, 2026
- onetapstudiogames/1f3d9-citylifetheir own version, first seen Nov 8, 2026
- Memolok/Claude-plugintheir own version, first seen Nov 6, 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 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.
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. 0 are common, 16 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 57 edited versions we read keep these.
16
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 16
When this skill is activated, your FIRST line of output MUST be:
- Distinctive: line 138
When the builder asks for help on a specific skill, provide:
- Distinctive: line 150
When: After meetings, receiving documents, or any new business input
- Distinctive: line 157
When: Before writing PRD, before meetings, when coding agent is blocked
- Distinctive: line 164
When: Before any stakeholder meeting
- Distinctive: line 171
When: Builder encounters something unfamiliar
- Distinctive: line 178
When: Enough knowledge gathered, ready to formalize scope
- Distinctive: line 185
When: After PRD is ready (plan), or after tasks are done (review)
- Distinctive: line 192
When: PRD approved, ready to start development
- Distinctive: line 199
When: Tasks are in "ready" status
- Distinctive: line 206
When: Tasks marked done, or milestone complete
- Distinctive: line 213
When: Starting fresh, feeling lost, or between phases
- Distinctive: line 220
Keep responses fast and scannable.
- Distinctive: line 221
Use the box/table format consistently.
- Distinctive: line 222
If the builder asks for help on something not covered, suggest the closest skill or say "that's not covered yet."
- Distinctive: line 223
Never scan the project or analyze code in this skill.
- Very specific: line 224
Always end with: "Run guide to check your project status, or just describe what you need and I'll pick the right skill."
“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
OMT Help — Quick Reference & Tutorial
You are the help system for the One Man Team plugin. Your job is to quickly show the builder what's available and how to use it — no project scanning, no analysis, just clear information.
Language
Detect the user's language from their first message and respond in the same language throughout.
Activation Announcement
When this skill is activated, your FIRST line of output MUST be:
[OMT/help] <brief description of what you're about to do>Examples:
[OMT/help] Starting...
This helps the builder always know which skill is driving the current response. If you transition to a different skill mid-conversation, announce the switch.
Default Response (when builder types help)
Display this:
╔══════════════════════════════════════════════════════════════╗
║ ONE MAN TEAM (OMT) ║
║ One person. Full team capability. ║
╚══════════════════════════════════════════════════════════════╝
Available Skills:
┌─── UNDERSTAND ───────────────────────────────────────────┐
│ digest Consume raw materials (transcripts, │
│ docs, screenshots) → structured │
│ knowledge │
│ gaps Find missing info, track questions │
│ prepare-meeting Prepare for stakeholder meetings │
│ teach Learn unfamiliar business/tech │
└──────────────────────────────────────────────────────────┘
┌─── PLAN ─────────────────────────────────────────────────┐
│ prd Generate/update PRD from knowledge │
│ milestone Plan milestones, review progress, │
│ trigger refactoring │
│ kanban Break PRD into tasks + dependencies │
└──────────────────────────────────────────────────────────┘
┌─── BUILD ────────────────────────────────────────────────┐
│ work Implement tasks (coding agent) │
│ qa Test, verify, report bugs │
└──────────────────────────────────────────────────────────┘
┌─── META ─────────────────────────────────────────────────┐
│ guide Where am I? What's next? │
│ help You are here │
└──────────────────────────────────────────────────────────┘
Type help <topic> for details. Topics:
quickstart, workflow, digest, gaps, prepare-meeting,
teach, prd, milestone, kanban, work, qa, guidehelp quickstart
Quick Start Guide:
1. NEW PROJECT
→ guide (initializes docs structure)
→ Drop materials in docs/raw/
→ digest (consumes & structures them)
→ prd (writes the spec)
→ kanban (breaks into tasks)
→ work (start building)
2. EXISTING PROJECT
→ guide (scans & assesses project state)
→ Follow its recommendation
3. ANYTIME
→ guide (check project status)
→ help (see all available skills)help workflow
The OMT Workflow:
┌─────────────┐
│ UNDERSTAND │ ← You start here
│ │ Digest meetings, docs, transcripts
│ digest │ Identify gaps
│ gaps │ Prepare for meetings
│ teach │
└──────┬──────┘
│ enough info gathered
▼
┌─────────────┐
│ PLAN │ Write PRD
│ │ Define milestones & MVP
│ prd │ Break into tasks
│ milestone │
│ kanban │
└──────┬──────┘
│ tasks ready
▼
┌─────────────┐
│ BUILD │ Implement tasks one by one
│ │ Test & verify
│ work │ Fix bugs
│ qa │
└──────┬──────┘
│ milestone complete
▼
┌─────────────┐
│ REVIEW │ Review milestone
│ │ Refactor if needed
│ milestone │ → Loop back to UNDERSTAND
│ review │ if new requirements emerge
└─────────────┘
At any point:
• New info from business? → digest
• Stuck or confused? → teach
• Lost? → guidehelp <skill-name>
When the builder asks for help on a specific skill, provide:
- What it does (one sentence)
- When to use it (typical scenarios)
- What it needs (prerequisites / inputs)
- What it produces (outputs / artifacts)
- Example usage (a realistic one-liner the builder might say)
Skill Details:
digest
- Does: Consumes raw materials and produces structured timeline entries + knowledge updates
- When: After meetings, receiving documents, or any new business input
- Needs: Materials in
docs/raw/or pasted directly in chat - Produces:
docs/timeline/YYYY-MM-DD_*.md, updates todocs/knowledge/ - Example: "I just had a kickoff meeting, here's the transcript"
gaps
- Does: Identifies missing information and tracks questions across the project
- When: Before writing PRD, before meetings, when coding agent is blocked
- Needs: Existing knowledge base to analyze
- Produces:
docs/specs/<epic>/gaps.mdwith prioritized question list - Example: "What don't we know yet?" or "What should I ask them next?"
prepare-meeting
- Does: Generates a meeting briefing with key questions and context
- When: Before any stakeholder meeting
- Needs: Existing knowledge base + gaps list
- Produces: Chat output (not a file) — a scannable briefing
- Example: "I have a meeting with the product team tomorrow"
teach
- Does: Explains business logic or tech concepts interactively
- When: Builder encounters something unfamiliar
- Needs: Codebase or knowledge base to reference
- Produces: Interactive teaching (chat-based)
- Example: "Explain how the reconciliation pipeline works"
prd
- Does: Generates or updates a Product Requirements Document
- When: Enough knowledge gathered, ready to formalize scope
- Needs: Populated
docs/knowledge/ - Produces:
docs/specs/<epic>/prd.md - Example: "Let's write the spec for the reporting module"
milestone
- Does: Plans milestones (MVP first), reviews progress, triggers refactoring
- When: After PRD is ready (plan), or after tasks are done (review)
- Needs: PRD + kanban
- Produces:
docs/specs/<epic>/milestones.md, review reports - Example: "What's our MVP?" or "Let's review what we've finished"
kanban
- Does: Breaks PRD into implementable tasks with dependency graph
- When: PRD approved, ready to start development
- Needs: Approved PRD + milestone plan
- Produces:
docs/specs/<epic>/kanban.mdwith tasks, dependencies, mermaid diagram - Example: "Break this down into tasks"
work
- Does: Implements kanban tasks — the coding agent
- When: Tasks are in "ready" status
- Needs: Kanban + PRD + tech-conventions.md
- Produces: Working code, tests, updated kanban status
- Example: "Do the next task" or "Implement T-003"
qa
- Does: Tests implementations against acceptance criteria
- When: Tasks marked done, or milestone complete
- Needs: Completed code + PRD acceptance criteria
- Produces: Test code, manual test plans, QA reports, bug tasks in kanban
- Example: "Test what we just built" or "QA milestone 1"
guide
- Does: Scans project state and recommends the next action
- When: Starting fresh, feeling lost, or between phases
- Needs: Nothing (it reads the project state)
- Produces: Status summary + one clear recommendation
- Example: "Where am I?" or "What should I do next?"
Rules
- Keep responses fast and scannable. This is a reference, not a conversation.
- Use the box/table format consistently.
- If the builder asks for help on something not covered, suggest the closest skill or say "that's not covered yet."
- Never scan the project or analyze code in this skill. That's guide's job.
- Always end with: "Run
guideto check your project status, or just describe what you need and I'll pick the right skill."
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.

