Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
Coding
DanceTempo
Try itDanceTempo / DanceTech Protocol — full repo context via public/llm-full.txt (or /llm-full.txt), tribal debugging via CLAWHUB.md, Tempo + MPP/x402 patterns, d...
What it does
**DanceTempo** is the reference **DanceTech Protocol** superapp: React hub + dedicated routes, Node/Express API, **Tempo** settlement, **MPP / x402** machine payments. This skill tells agents **where context lives** and **how to avoid known traps** (see ).
The skill document
DanceTempo · ClawHub context skill
DanceTempo is the reference DanceTech Protocol superapp: React hub + dedicated routes, Node/Express API, Tempo settlement, MPP / x402 machine payments. This skill tells agents where context lives and how to avoid known traps (see CLAWHUB.md).
Quick reference
| Situation | Action |
|---|---|
| Need one file with README + use cases + protocol + ClawHub | Load public/llm-full.txt or /llm-full.txt (running app). |
402 / MPP / wallet confusion | CLAWHUB.md + relevant route in server/index.js. |
| UI works but API 404 / HTML | Backend not running or stale process — restart npm run server (8787). |
| Verify live MPP handler exists | GET http://localhost:8787/api/dance-extras/live → JSON with flowKeys. |
| Which screens exist | src/hubRoutes.ts; hub /. |
| Changed markdown included in bundle | npm run build:llm (runs before npm run build). |
| EVVM (deploy, CLI, Tempo testnet) | docs/EVVM_TEMPO.md, /evvm; deep: https://www.evvm.info/llms-full.txt. |
| MPPScan / OpenAPI | GET /openapi.json; npm run discovery · docs/MPPSCAN_DISCOVERY.md |
| Promotion of a fix for future agents | Short entry under Successes or Failures in CLAWHUB.md (no secrets). |
When to activate (triggers)
Use this skill automatically when:
- The user @-mentions
llm-full.txt,CLAWHUB, DanceTempo, MPP, dance-extras, or Tempo testnet/mainnet. - The task touches
server/index.js,server/payments.js, orsrc/danceExtras*.ts. - Docs are edited that appear in
scripts/build-llm-full.mjs(bundle sources). - The user uploads ClawHub / OpenClaw / Copilot context questions.
Recommended: Cursor / IDE
@public/llm-full.txtfor broad changes;@CLAWHUB.mdwhen debugging past incidents.- Project rules: repo root
AGENTS.mdor.cursor/rulesif present — align withREADME.md.
See references/openclaw-dancetempo.md for OpenClaw workspace file hints.
Installation
From this repository (authoritative):
# Skill lives at:
.cursor/skills/clawhub/
Manual copy to OpenClaw skills dir (optional):
cp -r .cursor/skills/clawhub ~/.openclaw/skills/dancetempo-clawhub
ClawHub (publish): Zip clawhub/ (this folder) so the listing includes SKILL.md, references/, assets/, hooks/, scripts/. See README.md in this folder for a file manifest.
Repository map (where to look)
dancetempo/
├── public/llm-full.txt # Generated — do not hand-edit; run npm run build:llm
├── CLAWHUB.md # Tribal knowledge: successes, failures, checklists
├── README.md # Routes, stack, quick start
├── DANCETECH_USE_CASES.md # Flow-by-flow API contract
├── server/index.js # Express routes, integrations, MPP proxies
├── server/openapi.mjs # OpenAPI 3.1 for GET /openapi.json (MPPScan)
├── server/payments.js # Chain IDs, charge helpers
├── src/hubRoutes.ts # Hub directory of all /routes
├── src/danceExtrasLiveMpp.ts # Browser MPP helpers (live flows)
├── src/danceExtrasJudgeWire.ts # Judge-score wire snippets
├── .github/copilot-instructions.md
└── scripts/build-llm-full.mjs # Source list for llm-full.txt
First load (full orientation)
- Prefer
public/llm-full.txt(or/llm-full.txtfrom a running build) — includesCLAWHUB.mdin the bundle. - Regenerate after doc edits:
npm run build:llm.
Bundle sources
Exact list: assets/LLM-BUNDLE-SOURCES.md (mirrors build-llm-full.mjs).
EVVM: llm-full.txt vs llms-full.txt
| Artifact | Role |
|---|---|
public/llm-full.txt (singular) | DanceTempo-generated; committed; use first. |
https://www.evvm.info/llms-full.txt (plural) | Upstream EVVM protocol dump — attach for EVVM-only depth; do not duplicate into public/ unless you intend to maintain a fork. |
Debugging (tribal knowledge)
Read CLAWHUB.md for:
- What succeeded / failed (purl, AgentMail,
402loops, stale Express on 8787, etc.) - Repeatable checks (e.g.
GET /api/dance-extras/live)
Deeper: references/troubleshooting.md.
Key implementation pointers
| Topic | Location |
|---|---|
| Live MPP dance flows | POST /api/dance-extras/live/:flowKey/:network — GET /api/dance-extras/live |
| Hub routes | src/hubRoutes.ts |
| Browser MPP | src/danceExtrasLiveMpp.ts, src/danceExtrasJudgeWire.ts |
| Server | server/index.js |
Concrete snippets: references/examples.md.
Copilot Chat integration
GitHub Copilot does not load this folder automatically. Options:
- Commit
/.github/copilot-instructions.md(already in DanceTempo repo). - Paste from
references/copilot-and-agents.mdinto chat or org instructions.
Quick prompts:
- “Use
llm-full.txtas context for this PR.” - “Scan
CLAWHUB.mdfor 8787 / MPP / purl before changing the server.” - “After this task, suggest one CLAWHUB Success or Failure line (no secrets).”
- “Regenerate
public/llm-full.txt— which files are inputs?” →assets/LLM-BUNDLE-SOURCES.md
Promotion: CLAWHUB vs llm-full
| Content | Where |
|---|---|
| Stable facts (routes, env names, ports) | README.md, DANCETECH_USE_CASES.md, or relevant docs/*.md — then npm run build:llm. |
| Incident / debugging narrative | CLAWHUB.md Successes / Failures. |
| EVVM upstream protocol | Link https://www.evvm.info/llms-full.txt; keep docs/EVVM_TEMPO.md for Tempo-specific steps. |
Verification script
From repo root (optional):
./.cursor/skills/clawhub/scripts/verify-dancetempo-context.sh
Checks that public/llm-full.txt exists and reminds you of the live MPP GET check.
OpenClaw hook (optional)
Parity with self-improving-agent: injects a virtual DANCETEMPO_CONTEXT_REMINDER.md on agent:bootstrap (skips sub-agents). No network I/O.
# From this skill folder (or repo: .cursor/skills/clawhub/)
cp -r hooks/openclaw ~/.openclaw/hooks/dancetempo-clawhub
openclaw hooks enable dancetempo-clawhub
hooks/openclaw/HOOK.md— metadata + enable/disable.hooks/openclaw/handler.js— CommonJS handler (primary).hooks/openclaw/handler.ts— TypeScript handler for OpenClaw (types fromopenclaw/hooksat runtime).
Full notes: references/openclaw-dancetempo.md.
Best practices
- Never paste real
.envsecrets into prompts — use.env.examplenames only. - After editing any file listed in
build-llm-full.mjs, runnpm run build:llmbefore claiming “docs are updated in the bundle.” - Prefer
GET /api/dance-extras/liveover guessing whether the server is new. - For EVVM, answer no to optional Sepolia registry registration until policy allows (see
docs/EVVM_TEMPO.md).
Files in this package
| Path | Purpose |
|---|---|
SKILL.md | This file — primary skill entry |
README.md | Package manifest + upload notes for ClawHub |
references/copilot-and-agents.md | Paste blocks for Copilot / chat |
references/openclaw-dancetempo.md | OpenClaw workspace alignment |
references/examples.md | Concrete @-mentions, curls, patterns |
references/troubleshooting.md | Common failures & fixes |
assets/LLM-BUNDLE-SOURCES.md | What feeds llm-full.txt |
assets/SKILL-TEMPLATE.md | Template for forking this skill |
scripts/verify-dancetempo-context.sh | Quick repo checks |
hooks/openclaw/HOOK.md | OpenClaw hook manifest |
hooks/openclaw/handler.js | Bootstrap injector (CommonJS) |
hooks/openclaw/handler.ts | Bootstrap injector (TypeScript) |
hooks/README.md | Hook folder index |
See also
- Upstream inspiration: self-improving-agent (structure: references, assets, scripts, hooks).
- DanceTempo repo:
README.md,CLAWHUB.md.
Related skills
Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.
Write, debug, and tune Playwright specs with locator strategy, trace diagnosis, and CI-aware timeouts.
Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.
More from arunnadarasa
Browse all skillsScaffold and deploy quantum apps using Quantinuum, Guppy circuits, Selene backend, and Fly.io.
Autonomously plans, develops, tests, and delivers full software projects from plain-English prompts using coordinated multi-agent roles and automated quality...
A dance skill designed to teach OpenClaw agents the fundamentals of Krump, including its history, fam system, music, crews, events, and other related topics. The knowledge base extends up to 2017, so some information may be outdated or inaccurate
Krump Knowledge and Personality Identity — embodies Asura's legacy, lineage, and technical expertise
Autonomous Krump dance agent automating daily posts, training labs, battles, league tracking, community engagement, feedback, and tournament prep via OpenCla...
Teaches OpenClaw agents to act as a Krump-inspired physiotherapy coach. Use when building or assisting physio/fitness agents, therapeutic movement scoring (j...