tracking-token-launches
Track new token launches across DEXes with risk analysis and contract verification. Use when discovering new token launches, monitoring IDOs, or analyzing token contracts. Trigger with phrases like "track launches", "find new tokens", "new pairs on uniswap", "token risk analysis", or "monitor IDOs".
83
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Quality
Discovery
89%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 is a well-structured skill description with strong trigger term coverage and explicit 'Use when' and 'Trigger with' clauses that make it highly actionable for skill selection. The main weakness is that the capability descriptions could be more specific—listing concrete actions like 'check liquidity locks, verify contract source code, detect honeypot patterns' would strengthen specificity. Overall, it's a solid description that clearly carves out a distinct niche.
Suggestions
Expand the capability list with more concrete actions, e.g., 'check liquidity locks, detect honeypot contracts, analyze holder distribution, verify contract source code' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (DEX token launches) and some actions (track, risk analysis, contract verification), but doesn't list multiple concrete specific actions in detail—e.g., what does 'risk analysis' entail, what does 'contract verification' check? | 2 / 3 |
Completeness | Clearly answers both 'what' (track new token launches with risk analysis and contract verification) and 'when' (explicit 'Use when...' clause and 'Trigger with phrases like...' providing concrete trigger guidance). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'track launches', 'find new tokens', 'new pairs on uniswap', 'token risk analysis', 'monitor IDOs'—these are phrases users would naturally say in this domain. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche—new token launches on DEXes with risk analysis is a very specific domain unlikely to conflict with other skills. Trigger terms like 'new pairs on uniswap' and 'monitor IDOs' are uniquely tied to this skill. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid skill with strong actionability through concrete, executable commands and good progressive disclosure via well-organized sections with clear external references. The main weaknesses are moderate verbosity (reference tables and prerequisites that could be trimmed) and a lack of explicit validation checkpoints in the workflow, which is important given the risk-analysis nature of the tool.
Suggestions
Add explicit validation/decision checkpoints in the Instructions workflow, e.g., 'If risk score > 70, flag the token and do not proceed with interaction without user confirmation'.
Trim the Prerequisites section (Claude knows what Python and requests are) and consider moving the Supported Chains and Risk Indicators tables to a reference file to reduce token usage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some unnecessary sections like the 'Supported Chains' table and 'Risk Indicators' table that add bulk. The Prerequisites section explains things Claude would know (e.g., 'Python 3.8+ with requests library'). The Output section is somewhat redundant given the command descriptions already cover formats. | 2 / 3 |
Actionability | Commands are concrete and copy-paste ready with specific flags, options, and real example addresses. The Instructions section provides a clear step-by-step workflow with executable bash commands. Every command variant is shown with actual usage examples. | 3 / 3 |
Workflow Clarity | The Instructions section provides a reasonable sequence (check launches → get details → analyze risk), but there are no explicit validation checkpoints or feedback loops. For a tool dealing with risk analysis of potentially malicious contracts, there should be explicit verification steps (e.g., 'If risk score > X, do not proceed') and error recovery guidance inline rather than deferred to a separate file. | 2 / 3 |
Progressive Disclosure | The skill is well-structured with a clear overview, command reference, and instructions at the top level, with appropriate references to external files for errors, examples, and external documentation. References are one level deep and clearly signaled with descriptive labels. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
4dee593
- Reviewed
Table of Contents
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.