lifi
LI.FI cross-chain bridge and DEX aggregator. Swap tokens across 30+ blockchains with best rates and routes.
36
35%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./public/skills/0xterrybit/lifi/SKILL.mdQuality
Discovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a clear niche (LI.FI cross-chain bridging and DEX aggregation) and is distinctive, but it lacks explicit trigger guidance ('Use when...') and could benefit from more specific actions and natural user keywords. Adding when-clauses and expanding the list of concrete capabilities would significantly improve skill selection accuracy.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about bridging tokens, cross-chain swaps, finding best swap routes, or mentions LI.FI.'
List more concrete actions beyond just 'swap tokens', such as 'get swap quotes, compare bridge routes, check supported chains, estimate fees, execute cross-chain transfers'.
Include more natural trigger terms users might say, such as 'bridge tokens', 'cross-chain transfer', 'token swap', 'best bridge rate', specific chain names like 'Ethereum to Polygon', or file/protocol references like '.lifi'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (cross-chain bridge, DEX aggregator) and a key action (swap tokens across 30+ blockchains), but doesn't list multiple concrete actions like checking routes, comparing rates, getting quotes, or executing specific bridge operations. | 2 / 3 |
Completeness | Describes what it does (cross-chain bridge/DEX aggregation, swap tokens) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'when' is entirely absent, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'cross-chain', 'bridge', 'DEX aggregator', 'swap tokens', and 'blockchains', but misses common user variations like 'bridge tokens', 'token swap', 'cross-chain transfer', specific chain names, or 'LiFi'/'li.fi' alternate spellings. | 2 / 3 |
Distinctiveness Conflict Risk | The description targets a very specific niche — LI.FI cross-chain bridging and DEX aggregation — which is unlikely to conflict with other skills. The mention of 'LI.FI' as a named product and the specific domain of cross-chain swaps makes it clearly distinguishable. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
29%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides useful API examples with real endpoints and concrete curl commands, but suffers from a lack of clear workflow sequencing for what is a multi-step financial operation. The most critical step — actually executing a transaction — is left as pseudocode. The monolithic structure with extensive reference tables inline makes it harder to navigate, and the absence of validation checkpoints for operations involving real funds is a significant safety concern.
Suggestions
Add a clear, numbered end-to-end workflow section (e.g., '## Workflow: Cross-Chain Swap') that sequences: 1) Get quote, 2) Display details and confirm with user, 3) Approve token, 4) Verify approval, 5) Execute transaction, 6) Poll status until DONE/FAILED — with explicit validation at each step.
Provide a concrete, executable example for the 'Execute Transaction' step instead of pseudocode — even if it requires a specific tool like cast (foundry) or a Python script with web3.py.
Move static reference tables (supported chains, bridges, error codes, route options) into separate bundle files (e.g., CHAINS.md, REFERENCE.md) and link to them from the main skill to improve progressive disclosure.
Add explicit safety validation checkpoints: verify quote output amount before approval, confirm approval transaction succeeded before execution, and implement status polling with timeout/retry logic.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes useful reference tables (chains, bridges, status codes, errors) but is quite long with some redundancy. The supported bridges/chains tables are static data that could be queried via the API itself. The integrator fee section is verbose and the emoji usage adds visual noise without information. | 2 / 3 |
Actionability | The curl commands are mostly executable and copy-paste ready, but the critical 'Execute Transaction' section is incomplete — it shows pseudocode with '...' placeholders and says 'This requires a signing mechanism' without providing concrete guidance. Token approval also lacks a complete workflow. The quote and routes examples are strong, but the most important step (actually executing) is vague. | 2 / 3 |
Workflow Clarity | There is no clear end-to-end workflow sequence. The steps (get quote → approve token → execute → check status) are scattered across separate sections without explicit sequencing, numbering, or validation checkpoints. For a financial/destructive operation involving real funds, the lack of a unified workflow with verification steps (e.g., confirm quote before approval, verify approval before execution, poll status after execution) is a significant gap. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no bundle files to reference. All reference tables, API examples, chain lists, and bridge details are inlined in a single file. Content like supported chains, bridges, and error codes could be split into separate reference files, with the main skill focusing on the core workflow and quick-start examples. | 1 / 3 |
Total | 6 / 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 |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- Repository
- Demerzels-lab/elsamultiskillagent
- Commit
f45fcb5
- 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.