pump-swarm

Coordinated multi-wallet trading on Pump.fun

Quality

36%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Critical

Do not install without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./src/skills/bundled/pump-swarm/SKILL.md

Quality

Discovery

22%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is extremely terse and lacks the detail needed for effective skill selection. It names a specific platform (Pump.fun) which helps with distinctiveness, but fails to enumerate concrete actions and entirely omits a 'Use when...' clause, making it difficult for Claude to know when to select this skill over others.

Suggestions

Add a 'Use when...' clause with explicit trigger terms, e.g., 'Use when the user asks about bundled trading on Pump.fun, sniping token launches, or coordinating multiple Solana wallets.'

List specific concrete actions the skill performs, e.g., 'Creates and manages multiple wallets, executes coordinated buy/sell orders, bundles transactions for token launches on Pump.fun.'

Include natural keyword variations users might say, such as 'Solana', 'memecoin', 'bundle', 'snipe', 'token launch', 'pump.fun bot'.

Dimension	Reasoning	Score
Specificity	The description names a domain (Pump.fun, multi-wallet trading) but does not list any concrete actions. 'Coordinated multi-wallet trading' is a single vague phrase rather than specific capabilities like 'execute buy/sell orders, manage wallet balances, snipe token launches'.	1 / 3
Completeness	The description only vaguely addresses 'what' (coordinated multi-wallet trading) and completely lacks any 'when' clause or explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also weak, so this scores a 1.	1 / 3
Trigger Term Quality	It includes some relevant keywords a user might say—'Pump.fun', 'multi-wallet', and 'trading'—but misses common variations and related terms like 'bundle', 'snipe', 'token launch', 'Solana', 'buy/sell', or 'memecoin'.	2 / 3
Distinctiveness Conflict Risk	'Pump.fun' is a fairly specific platform reference that helps distinguish this skill, but 'multi-wallet trading' could overlap with general crypto trading or wallet management skills. The lack of detail increases conflict risk.	2 / 3
	Total	6 / 12 Passed

Implementation

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable with concrete commands and examples, but suffers from significant verbosity and redundancy—execution modes, multi-DEX examples, and options are repeated across sections. The lack of validation checkpoints in financial trading workflows is a notable gap, and the monolithic structure would benefit from splitting detailed reference material into separate files.

Suggestions

Eliminate redundant sections: merge the execution modes table with the deep dive, remove duplicate multi-DEX examples, and cut obvious explanations (e.g., 'Signs all transactions locally') to reduce content by ~40%.

Add explicit validation checkpoints to the buy/sell workflows, such as confirming balances after trades, verifying bundle success before proceeding, and a validate-then-retry loop for failed transactions.

Split detailed reference content (execution modes deep dive, preset documentation, agent tools list, multi-DEX details) into separate linked files to keep SKILL.md as a concise overview.

Remove explanations of concepts Claude already knows (e.g., what Promise.all does, what MEV protection means) to respect token budget.

Dimension	Reasoning	Score
Conciseness	The content is extremely verbose at ~300+ lines with significant redundancy. Multi-DEX examples appear twice, execution modes are explained twice (once in the table and again in a 'deep dive'), and the document includes extensive tables for information Claude could infer. The buy/sell flow descriptions explain obvious steps like 'signs all transactions locally'.	1 / 3
Actionability	The skill provides concrete, copy-paste ready commands throughout with specific flags, options, and realistic examples. Environment variable setup, command syntax, and trading examples are all fully specified and executable.	3 / 3
Workflow Clarity	The buy and sell flows are documented with clear steps, and the 'refresh before sell' pattern is highlighted. However, there are no explicit validation checkpoints or error recovery feedback loops for what are essentially financial/destructive operations—the troubleshooting table is reactive rather than integrated into the workflow.	2 / 3
Progressive Disclosure	The content is a monolithic wall of text with no references to external files. Sections like the execution modes deep dive, full preset documentation, and multi-DEX details could be split into separate reference files. The structure uses headers well but everything is inline.	2 / 3
	Total	8 / 12 Passed

Validation

90%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: alsk1992/CloddsBot
Commit: e71a5f6

Reviewed: 11 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.