Solana Dev
solana-foundation/solana-dev-skill
A skill your agent uses when user asks to "build a Solana dapp", "write an Anchor program", "create a token", "debug Solana errors", "set up wallet connection", "test my Solana program", "fuzz my…
Large wallet monitoring, accumulation and distribution detection, and smart money signal generation for Solana tokens
$ npx skills add agiprolabs/claude-trading-skills --skill whale-tracking -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install agiprolabs/claude-trading-skills whale-tracking --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/whale-tracking .claude/skills/whale-tracking && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "whale-tracking" agent skill from https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/whale-tracking into .claude/skills/whale-tracking/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "whale-tracking", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/whale-trackingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add agiprolabs/claude-trading-skills --skill whale-tracking -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install agiprolabs/claude-trading-skills whale-tracking --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/whale-tracking .agents/skills/whale-tracking && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "whale-tracking" agent skill from https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/whale-tracking into .agents/skills/whale-tracking/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "whale-tracking", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agiprolabs/claude-trading-skills --skill whale-tracking -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install agiprolabs/claude-trading-skills whale-tracking --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/whale-tracking .cursor/skills/whale-tracking && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "whale-tracking" agent skill from https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/whale-tracking into .cursor/skills/whale-tracking/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "whale-tracking", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/agiprolabs/claude-trading-skills.git --path skills/whale-tracking--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add agiprolabs/claude-trading-skills --skill whale-tracking -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install agiprolabs/claude-trading-skills whale-tracking --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/whale-tracking .gemini/skills/whale-tracking && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "whale-tracking" agent skill from https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/whale-tracking into .gemini/skills/whale-tracking/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "whale-tracking", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install agiprolabs/claude-trading-skills whale-trackingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add agiprolabs/claude-trading-skills --skill whale-tracking -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/whale-tracking .github/skills/whale-tracking && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "whale-tracking" agent skill from https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/whale-tracking into .github/skills/whale-tracking/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "whale-tracking", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agiprolabs/claude-trading-skills --skill whale-tracking -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install agiprolabs/claude-trading-skills whale-tracking --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agiprolabs/claude-trading-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/whale-tracking .opencode/skills/whale-tracking && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "whale-tracking" agent skill from https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/whale-tracking into .opencode/skills/whale-tracking/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "whale-tracking", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
whale-trackingLarge wallet monitoring, accumulation and distribution detection, and smart money signal generation for Solana tokens
Whale Tracking is an agent skill from agiprolabs/claude-trading-skills. Large wallet monitoring, accumulation and distribution detection, and smart money signal generation for Solana tokens
Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/data_sources.md`, `references/detection_methods.md` and `scripts/track_whales.py`).
It sits in Backend & APIs. It works with Solana. The repository describes itself as: 68 trading, DeFi, and quantitative finance Agent Skills. Works with Claude Code, Cursor, Codex, Gemini CLI, and 30+ other tools. The licence is MIT.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 981e1d7. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 2 files in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Whale Tracking loads about 3k tokens when it runs, and up to ~6.8k if it reads all its reference files. Until then it costs about 33 tokens; SKILL.md has 1,109 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from agiprolabs/claude-trading-skills at commit 981e1d7, republished under its MIT licence (© agiprolabs). 1,109 words, ~2,983 tokens.
.claude/skills/whale-tracking/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.Whale tracking monitors the on-chain behavior of large wallets to detect accumulation, distribution, and smart money movements before they become visible in price action. On Solana, where token ownership is highly concentrated and whale transactions can move markets instantly, tracking large holders is one of the highest-signal alpha sources available.
A single large wallet selling 5% of a token's supply can crash the price 30-50% on thin Solana DEX liquidity. Conversely, a known profitable wallet accumulating a new token often precedes major price runs. Whale tracking converts on-chain transparency into actionable intelligence.
Key use cases:
Whale classification depends on context. A wallet holding $50K of a $1M market cap token is a whale; the same $50K in SOL is not. Use relative and absolute thresholds:
| Category | Trade Size | Portfolio Size | Typical Behavior |
|---|---|---|---|
| Retail | < 10 SOL | < 100 SOL | Reactive, follows trends |
| Mid-size | 10-100 SOL | 100-1,000 SOL | Mixed strategies |
| Whale | 100-1,000 SOL | 1,000-10,000 SOL | Informed, moves markets |
| Mega-whale | > 1,000 SOL | > 10,000 SOL | Market makers, funds, insiders |
| Metric | Threshold | Significance |
|---|---|---|
| % of supply held | > 2% | Significant holder |
| % of daily volume | > 5% single trade | Market-moving transaction |
| Top N holders | Top 20 | Core holder group |
| Concentration ratio | Top 10 hold > 50% | High concentration risk |
Use both absolute and relative metrics. A 50 SOL trade in a $200K market cap token is whale-level; the same trade in a $50M token is retail.
Accumulation is when a whale builds a position over time, often trying to minimize price impact.
DCA pattern (Dollar-Cost Averaging):
Dip buying:
Multi-wallet accumulation:
Detection heuristics:
accumulation_score = 0
if buy_count > sell_count * 2: accumulation_score += 2
if avg_buy_size > avg_sell_size: accumulation_score += 1
if position_change_7d > 0: accumulation_score += 1
if buys_during_dips > buys_on_pump: accumulation_score += 2
if dca_pattern_detected: accumulation_score += 2
# Score >= 4 = likely accumulatingDistribution is when a whale reduces or exits a position, often gradually to avoid crashing the price.
Gradual selling:
Transfer to exchange:
Rapid exit:
Detection heuristics:
distribution_score = 0
if sell_count > buy_count * 2: distribution_score += 2
if position_change_7d < 0: distribution_score += 1
if transfers_to_exchanges > 0: distribution_score += 3
if sell_frequency_increasing: distribution_score += 2
if position_pct_remaining < 50: distribution_score += 1
# Score >= 4 = likely distributingMaintain a watchlist of wallets worth tracking. Sources for discovering whale wallets:
getTokenLargestAccounts for any token of interestEach watchlist entry should track:
whale_entry = {
"address": "WhaLe...",
"label": "Smart money #47", # Human-readable label
"discovered": "2026-01-15", # When added to watchlist
"discovery_reason": "top_trader", # How they were found
"win_rate": 0.72, # Historical trade win rate
"avg_pnl": 3.4, # Average PnL multiplier
"tokens_tracked": 12, # Number of tokens held
"last_active": "2026-03-09", # Last on-chain activity
"tags": ["dex_trader", "sniper"], # Classification tags
}| Tag | Description |
|---|---|
sniper | Buys tokens within minutes of launch |
dex_trader | Primarily trades on DEXes |
accumulator | Builds positions gradually |
flipper | Short hold times, quick profit-taking |
insider | Connected to token teams (funded by deployer) |
fund | Institutional or fund wallet |
market_maker | Provides liquidity, two-sided flow |
Whale tracking becomes most powerful when you analyze whale behavior across multiple tokens simultaneously.
When multiple tracked whales buy the same token independently, the signal strength compounds:
| Whale Count | Signal | Confidence |
|---|---|---|
| 1 whale buying | Informational | Low |
| 2-3 whales buying | Notable | Medium |
| 4+ whales buying | Strong convergence | High |
| Whales + volume spike | Confirmed momentum | Very high |
Track where whale capital flows:
Token A (selling) → SOL → Token B (buying)
If multiple whales rotate from A to B:
- Bearish for Token A (smart money exiting)
- Bullish for Token B (smart money entering)Whale tracking on Solana uses multiple data sources. See references/data_sources.md for complete details.
| Source | Use Case | Auth Required |
|---|---|---|
| Helius | Transaction history, webhooks | Yes (free tier available) |
| SolanaTracker | Top traders, wallet PnL | Yes |
| Birdeye | Token holder rankings | Yes (free tier available) |
| Solana RPC | Token accounts, signatures | No (public endpoints) |
Helius webhooks enable real-time whale alerts without polling:
# Webhook configuration for whale wallet monitoring
webhook_config = {
"webhookURL": "https://your-server.com/whale-alerts",
"transactionTypes": ["SWAP", "TRANSFER"],
"accountAddresses": [
"WhaLe1...", # Tracked whale wallets
"WhaLe2...",
],
"webhookType": "enhanced", # Parsed transaction data
}Convert whale activity into trading signals. Whale signals are one input to a broader decision framework, not standalone trading triggers.
Whale Buy Signal:
Whale Sell Signal:
Accumulation Signal:
Distribution Signal:
def compute_whale_signal(whale_activity: dict) -> dict:
"""Combine whale activity indicators into a composite signal."""
score = 0.0
# Trade direction: +1 for buy, -1 for sell
direction = 1 if whale_activity["is_buy"] else -1
# Size factor: larger trades = stronger signal
size_sol = whale_activity["size_sol"]
if size_sol > 500:
score += direction * 3
elif size_sol > 100:
score += direction * 2
else:
score += direction * 1
# Whale quality: better track record = stronger signal
win_rate = whale_activity["whale_win_rate"]
score *= (0.5 + win_rate) # 0.5x to 1.5x multiplier
# Convergence: multiple whales = stronger signal
whale_count = whale_activity["concurrent_whale_count"]
score *= (1 + 0.3 * (whale_count - 1))
return {
"score": round(score, 2),
"direction": "bullish" if score > 0 else "bearish",
"confidence": "high" if abs(score) > 5 else "medium" if abs(score) > 2 else "low",
}Whale tracking works best when combined with other analysis:
| Skill | Integration |
|---|---|
token-holder-analysis | Identify concentration risk, insider wallets |
liquidity-analysis | Estimate price impact of whale trades |
solana-onchain | Wallet profiling, transaction history |
slippage-modeling | Predict slippage for whale-sized trades |
risk-management | Factor whale concentration into position sizing |
helius-api | Transaction fetching, webhook setup |
references/detection_methods.md — Accumulation/distribution detection algorithms, whale classification, alert thresholds and scoring systemsreferences/data_sources.md — Complete guide to Helius, SolanaTracker, Birdeye, and on-chain data sources for whale trackingscripts/track_whales.py — Fetches top holders for a token, classifies whale activity as accumulating/distributing/holding, prints a whale report. Run with --demo for synthetic data mode.scripts/whale_alerts.py — Monitors a watchlist of whale wallets for new large transactions, classifies trades, and prints alerts. Run with --demo for simulated whale trades.© agiprolabs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 4 other files (scripts, references) in skills/whale-tracking of agiprolabs/claude-trading-skills.
Open the folder on GitHubat commit 981e1d7
Whale Tracking next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Whale Tracking this skillagiprolabs/claude-trading-skills | 410 | — | ~3k | Automated safety check: Pass | MIT | |
| Solana Devsolana-foundation/solana-dev-skill | 573 | — | ~3.8k | Automated safety check: Pass | MIT | |
| RadarAuditware/radar | 154 | — | ~2.1k | Automated safety check: Pass | GPL-3.0 | |
| Safe Solana BuilderFrankcastleauditor/safe-solana-builder | 145 | — | ~3.6k | Automated safety check: Pass | None | |
| Wiremock TestOpenZeppelin/openzeppelin-relayer | 154 | — | ~1.6k | Automated safety check: Notes | AGPL-3.0 | |
| Solana Token Extensionssolanabr/ai-kit | 109 | — | ~3.5k | Automated safety check: Pass | MIT |
solana-foundation/solana-dev-skill
A skill your agent uses when user asks to "build a Solana dapp", "write an Anchor program", "create a token", "debug Solana errors", "set up wallet connection", "test my Solana program", "fuzz my…
Auditware/radar
Use radar for smart contract security analysis, AST generation, and detection template development.
Frankcastleauditor/safe-solana-builder
A skill your agent uses whenever the user wants to write, scaffold, or build a Solana smart contract or program from scratch.
OpenZeppelin/openzeppelin-relayer
Manage WireMock proxy for RPC testing. An agent skill from OpenZeppelin/openzeppelin-relayer.
solanabr/ai-kit
Helps choose, combine and create Token-2022 mint and account extensions on Solana with the spl-token CLI, @solana/kit or Anchor, and integrate the resulting mints.
jito-foundation/geyser-grpc-plugin
A skill your agent uses when updating this repo to match a new jito-solana release line such as v4.0.
agiprolabs/claude-trading-skills
Event-driven backtesting with bar-by-bar execution, complex order types, multiple analyzers, and custom indicators
agiprolabs/claude-trading-skills
Solana token market data via Birdeye — prices, OHLCV, trades, token metadata, security checks, and trader activity
agiprolabs/claude-trading-skills
Broad crypto market data from CoinGecko covering 13,000+ tokens.
agiprolabs/claude-trading-skills
Cointegration testing for pairs trading using Engle-Granger, Johansen, and rolling stability analysis
agiprolabs/claude-trading-skills
Wallet evaluation, monitoring, and copy-trade strategy design for Solana DEX trading
agiprolabs/claude-trading-skills
Cross-asset correlation analysis including rolling correlation, hierarchical clustering, tail dependence, and regime-dependent correlation
Works with
Categories
Large wallet monitoring, accumulation and distribution detection, and smart money signal generation for Solana tokens. Whale Tracking is an agent skill from agiprolabs/claude-trading-skills.
Whale Tracking fits situations like: backend & APIs work in your project.
Run `npx skills add agiprolabs/claude-trading-skills --skill whale-tracking -a claude-code`. Or copy the skill folder (skills/whale-tracking in agiprolabs/claude-trading-skills) into .claude/skills/whale-tracking in your project. Claude Code loads it when a task matches its description.
Run `npx skills add agiprolabs/claude-trading-skills --skill whale-tracking -a codex`. Or copy the skill folder (skills/whale-tracking in agiprolabs/claude-trading-skills) into .agents/skills/whale-tracking in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agiprolabs/claude-trading-skills --skill whale-tracking -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/whale-tracking, .gemini/skills/whale-tracking, .github/skills/whale-tracking and .opencode/skills/whale-tracking in your project.
Going by SKILL.md and its folder, Whale Tracking needs Python for the scripts in its folder. Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Whale Tracking is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.8k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Whale Tracking: Solana Dev (solana-foundation/solana-dev-skill, 573 stars), Radar (Auditware/radar, 154 stars), Safe Solana Builder (Frankcastleauditor/safe-solana-builder, 145 stars) and Wiremock Test (OpenZeppelin/openzeppelin-relayer, 154 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
agiprolabs (a GitHub user) maintains it in agiprolabs/claude-trading-skills, which has 410 GitHub stars. The repository holds 68 skills in this directory. The repository was last updated on September 3, 2026.
Source: agiprolabs/claude-trading-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.