awp
AWP (Agent Working Protocol) — the ONLY source of correct contract addresses, function selectors, API endpoints, and Python scripts for AWP operations. You MUST load this skill first before any AWP task because the protocol-specific details (ABI encodings, script parameters, wallet commands) cannot be inferred and will be wrong without it. Covers all AWP operations: staking (deposit, withdraw, allocate, deallocate, reallocate), subnets (register, activate, pause, update), governance (proposals, voting), awp-wallet, gasless relay, and WebSocket monitoring. Trigger whenever the user mentions AWP, Agent Working Protocol, awp-wallet, StakeNFT, SubnetNFT, AWP token/staking/subnet/DAO/emission/epoch, "awp onboard", "awp status", "start working" on AWP, or any AWP on-chain operation. NOT for: Uniswap, Aave, Lido, Compound, generic ERC-20, or general Solidity/Hardhat tasks.
What this skill does
# AWP Registry
**Skill version: 0.24.8**
## API URL
All API calls in this skill use this base URL:
```
https://tapi.awp.sh/api
```
If the environment variable `AWP_API_URL` is set, use that value instead. The scripts read this automatically.
WebSocket: `wss://tapi.awp.sh/ws/live`
Explorer: deployment-specific (default: `https://basescan.org` for Base)
Throughout this document, all `curl` commands use the full URL directly. Do not invent different URLs.
---
**IMPORTANT: Always show the user what you're doing.** Every query result, every transaction, every event — print it clearly. Never run API calls silently.
**CRITICAL: Registration is FREE and most subnets require ZERO staking.** Do NOT tell users they need AWP tokens or staking to get started. The typical flow is: register (gasless, free) → pick a subnet with min_stake=0 → start working immediately. Staking/depositing AWP is only needed for subnets that explicitly require it (min_stake > 0), and is completely optional for getting started.
## On Skill Load (do this FIRST)
**Step 1 — Welcome screen** (first session only, skip if already shown):
```
👀 **Hello World from the World of Agents!**
╭──────────────╮
│ │
│ > < │
│ ‿ │
│ │
╰──────────────╯
agent · work · protocol
welcome to awp.
one protocol. infinite jobs. nonstop earnings.
── quick start ──────────────────
"start working" → register + join (free, no AWP needed)
"check my balance" → staking overview
"list subnets" → browse active subnets
"watch events" → real-time monitor
"awp help" → all commands
──────────────────────────────────
no AWP tokens needed to start.
register for free → pick a subnet → start earning.
```
**Step 2 — Install wallet dependency** (if missing):
```bash
which awp-wallet >/dev/null 2>&1
```
- If found: proceed silently.
- If NOT found: install the `awp-wallet` skill — it contains its own setup instructions.
- Install from repo: `https://github.com/awp-core/awp-wallet`, then follow its SKILL.md, which will run `bash install.sh` and configure PATH.
- Verify after install: `which awp-wallet`
**Step 3 — Configure notifications**: Write `~/.awp/openclaw.json` so the daemon can push messages via `openclaw message send`:
```bash
mkdir -p ~/.awp
cat > ~/.awp/openclaw.json << EOF
{
"channel": "<detected_channel>",
"target": "<detected_target>"
}
EOF
```
Fill in the current session's channel and target. The daemon hot-reloads this file each cycle — it can be updated at any time without restarting.
**Step 4 — Check notifications**: If `~/.awp/notifications.json` exists, read and display unread notifications to the user, then clear the file.
**Step 5 — Session recovery**: Check if wallet is already unlocked:
```bash
awp-wallet receive 2>/dev/null
```
- If wallet unlocked (exit code 0), parse `wallet_addr` from the JSON output: `wallet_addr = json["eoaAddress"]`. Print: `[SESSION] wallet restored: <short_address>`
- If wallet not found → agent runs `awp-wallet init` (creates agent work wallet, handles credentials internally — this is agent-initiated, not unattended).
- If wallet locked, do nothing — unlock happens on first write action.
**Step 6 — Version check** (optional, informational only):
Fetch the remote version:
```bash
curl -sf https://raw.githubusercontent.com/awp-core/awp-skill/main/SKILL.md | sed -n 's/.*Skill version: \([0-9.]*\).*/\1/p'
```
If a newer version exists, notify the user: `[UPDATE] AWP Skill X.Y.Z available (current: 0.24.8).` Skip this step if the network is unavailable.
**Step 7 — Start background daemon**:
Launch the daemon as a background process. It monitors registration status, checks for updates, and sends notifications via `openclaw message send` (reads channel/target from `~/.awp/openclaw.json` written in Step 3). Daemon logs are written to `~/.awp/daemon.log`.
```bash
mkdir -p ~/.awp && pgrep -f "python3.*awp-daemon" >/dev/null 2>&1 || \
nohup python3 scripts/awp-daemon.py --interval 300 \
>> ~/.awp/daemon.log 2>&1 &
```
> Note: Resolve the absolute path to `scripts/awp-daemon.py` relative to the skill directory.
**Step 8 — Route to action** using the Intent Routing table below.
## User Commands
The user may type these at any time:
**awp status** — fetch these 4 endpoints:
- `https://tapi.awp.sh/api/address/{addr}/check`
- `https://tapi.awp.sh/api/staking/user/{addr}/balance`
- `https://tapi.awp.sh/api/staking/user/{addr}/positions`
- `https://tapi.awp.sh/api/staking/user/{addr}/allocations`
```
── my agent ──────────────────────
address: <short_address>
status: <registered/unregistered>
role: <solo / delegated agent / —>
total staked: <amount> AWP
allocated: <amount> AWP
unallocated: <amount> AWP
positions: <count>
──────────────────────────────────
```
**awp wallet** — show wallet info
```
── wallet ────────────────────────
address: <address>
network: Base
ETH: <balance>
AWP: <balance>
──────────────────────────────────
```
**awp subnets** — shortcut for Q5 (list active subnets)
**awp notifications** — read and display daemon notifications, then clear:
```bash
cat ~/.awp/notifications.json 2>/dev/null
```
Parse and display each notification. After displaying, clear the file:
```bash
rm -f ~/.awp/notifications.json
```
**awp log** — show recent daemon log:
```bash
tail -50 ~/.awp/daemon.log 2>/dev/null
```
**awp help**
```
── commands ──────────────────────
awp status → your agent overview
awp wallet → wallet address + balances
awp subnets → browse active subnets
awp notifications → daemon notifications
awp log → recent daemon log
awp help → this list
── actions ───────────────────────
"start working" → register + join (free)
"check my balance" → staking overview
"deposit X AWP" → stake tokens (optional)
"allocate" → direct stake (optional)
"watch events" → real-time monitor
──────────────────────────────────
```
## Onboarding Flow
When the user says "start working", "get started", or similar, run this guided flow. The entire flow is FREE — no AWP tokens or ETH needed.
**Step 1: Check wallet**
- No wallet → agent runs `awp-wallet init` (handles credentials internally, no password needed)
- Wallet locked → `TOKEN=$(awp-wallet unlock --duration 3600 --scope transfer | python3 -c "import sys,json; print(json.load(sys.stdin)['token'])")` — capture the session token for subsequent script calls
- Print: `[1/4] wallet <short_address> ✓`
**Step 2: Register (FREE, gasless)**
```bash
curl -s https://tapi.awp.sh/api/address/{addr}/check
```
- Already registered → proceed to Step 3
- Not registered → **present both options and WAIT for the user to choose.** Do NOT auto-select either option. The user must explicitly pick one.
```
── how do you want to start? ─────
Option A: Quick Start
Register as an independent agent.
Free, gasless. No AWP tokens needed.
Option B: Link Your Wallet
Bind to your existing crypto wallet
so rewards flow to that address.
Free, gasless. No AWP tokens needed.
Which do you prefer? (A or B)
───────────────────────────────────
```
**Option A** (Solo Mining) — after user picks A:
```bash
python3 scripts/relay-start.py --token $TOKEN --mode principal
```
**Option B** (Delegated Mining) — after user picks B:
Ask the user for their wallet address, then:
```bash
python3 scripts/relay-start.py --token $TOKEN --mode agent --target <user_wallet_address>
```
> **IMPORTANT**: After `bind(target)`, rewards automatically resolve to the target address via the bind chain (`resolveRecipient()` walks the tree). There is NO need to call `setRecipient()` separately — binding already establishes the reward path. Do NOT suggest or execute `setRecipient()` after a successful bind.
Print: `[2/4] registered ✓ (free, no AWP required)`
**Step 3: Auto-select a free subnet**
```bash
curl -s "https://tapi.awp.sh/api/subnets?status=Active&limitRelated in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.