Skip to content

feat: improve skill scores for binance-skills-hub#188

Open
popey wants to merge 1 commit intobinance:mainfrom
popey:improve/skill-review-optimization
Open

feat: improve skill scores for binance-skills-hub#188
popey wants to merge 1 commit intobinance:mainfrom
popey:improve/skill-review-optimization

Conversation

@popey
Copy link
Copy Markdown

@popey popey commented Mar 16, 2026

Hullo @binance 👋

I ran your skills through tessl skill review at work and found some targeted improvements.

score_card

Here's the full before/after in text form:

Skill Before After Change
assets 29% 79% +50%
spot 36% 75% +39%
alpha 40% 79% +39%
derivatives-trading-usds-futures 41% 75% +34%
trading-signal 75% 83% +8%
square-post 77% 83% +6%
query-token-audit 83% 89% +6%
meme-rush 83% 83% 0%
crypto-market-rank 96% 96% 0%
query-address-info 94% 94% 0%
query-token-info 94% 94% 0%
Changes made

binance/ skills (assets, spot, alpha, derivatives-trading-usds-futures, margin-trading)

These five skills all had the same core issue: their frontmatter descriptions were extremely generic (e.g. "Binance Assets request using the Binance API") with no specific actions listed and no "Use when..." trigger guidance. This caused agents to have no idea when to select these skills.

What changed:

  • Rewrote each description to list specific concrete actions (e.g. "Place spot market/limit orders, cancel orders, query order status, view trade history")
  • Added explicit "Use when users ask about..." clauses with natural trigger terms users would actually say
  • Included domain-specific keywords (e.g. "perpetual contracts", "leverage", "cross margin", "isolated margin") for better skill selection

trading-signal

  • Expanded trigger terms to include "whale tracking", "wallet monitoring", "crypto signals", "on-chain analysis"
  • Removed duplicate curl examples (were listed both inline and in a separate "Example Requests" section)

square-post

  • Expanded description with additional trigger terms ("share on Binance", "publish trading updates", "share market analysis")
  • Added content optimization and error handling as explicit capabilities

query-token-audit

  • Replaced vague "Result Validity" section with a clear decision tree for handling hasResult/isSupported combinations
  • Added explicit step-by-step guidance for each risk level

meme-rush

  • Added "Common Workflows" section showing how to combine Meme Rush and Topic Rush APIs for practical trading scenarios

Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch - just saw room for improvement and wanted to contribute.

Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at this Tessl guide and ask it to optimize your skill. Ping me - @popey - if you hit any snags.

Thanks in advance 🙏

Hullo @binance 👋

I ran your skills through `tessl skill review` at work and found some targeted improvements. Here's the full before/after:

| Skill | Before | After | Change |
|-------|--------|-------|--------|
| assets | 29% | 79% | +50% |
| spot | 36% | 75% | +39% |
| alpha | 40% | 79% | +39% |
| derivatives-trading-usds-futures | 41% | 75% | +34% |
| margin-trading | 45% | 79% | +34% |
| trading-signal | 75% | 83% | +8% |
| square-post | 77% | 83% | +6% |
| query-token-audit | 83% | 89% | +6% |
| meme-rush | 83% | 83% | 0% |
| crypto-market-rank | 96% | 96% | 0% |
| query-address-info | 94% | 94% | 0% |
| query-token-info | 94% | 94% | 0% |

<details>
<summary>Changes made</summary>

### binance/ skills (assets, spot, alpha, derivatives-trading-usds-futures, margin-trading)

These five skills all had the same core issue: their frontmatter descriptions were extremely generic (e.g. "Binance Assets request using the Binance API") with no specific actions listed and no "Use when..." trigger guidance. This caused agents to have no idea when to select these skills.

**What changed:**
- Rewrote each description to list specific concrete actions (e.g. "Place spot market/limit orders, cancel orders, query order status, view trade history")
- Added explicit "Use when users ask about..." clauses with natural trigger terms users would actually say
- Included domain-specific keywords (e.g. "perpetual contracts", "leverage", "cross margin", "isolated margin") for better skill selection

### trading-signal
- Expanded trigger terms to include "whale tracking", "wallet monitoring", "crypto signals", "on-chain analysis"
- Removed duplicate curl examples (were listed both inline and in a separate "Example Requests" section)

### square-post
- Expanded description with additional trigger terms ("share on Binance", "publish trading updates", "share market analysis")
- Added content optimization and error handling as explicit capabilities

### query-token-audit
- Replaced vague "Result Validity" section with a clear decision tree for handling `hasResult`/`isSupported` combinations
- Added explicit step-by-step guidance for each risk level

### meme-rush
- Added "Common Workflows" section showing how to combine Meme Rush and Topic Rush APIs for practical trading scenarios

</details>

Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch - just saw room for improvement and wanted to contribute.

Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at [this Tessl guide](https://docs.tessl.io/evaluate/optimize-a-skill-using-best-practices) and ask it to optimize your skill. Ping me - [@popey](https://github.com/popey) - if you hit any snags.

Thanks in advance 🙏
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant