BF gmgn-market
Get crypto and meme token price charts (K-line, candlestick, OHLCV), trending meme coin rankings by volume, and newly launched tokens on launchpads (pump.fun, fourmeme, letsbonk, Raydium, etc.) via GMGN API on Solana, BSC, Base, or Ethereum. Use when user asks for price chart, trending tokens, what's pumping, hot coins, new launches, token signals, or wants to discover early-stage opportunities.
As a process F 61/100 · Will not run — References files that are not bundled: ../../docs/workflow-market-opportunities.md, ../../docs/workflow-token-research.md, ../../docs/workflow-early-project-screening.md
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:181High-entropy token-like string (may be an id, hash or a credential)--address 0xC0…Cc2 \
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 12461 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: ../../docs/workflow-market-opportunities.md - warning
missing-refreference to a missing file: ../../docs/workflow-token-research.md - warning
missing-refreference to a missing file: ../../docs/workflow-early-project-screening.md - warning
missing-refreference to a missing file: ../../docs/workflow-daily-brief.md
Process rating: all ten parameters 61/100
- 0Tools and files. 4 referenced file(s) missing: ../../docs/workflow-market-opportunities.md, ../../docs/workflow-token-research.md, ../../docs/workflow-early-project-screening.md
- 30Running it twice. 19 mutating operations with no state check
- 40Execution cost. Instruction body is 12461 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 53 steps
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 18 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 398: enough signal without eating the budget
- +4Structure: 42 headings
- +3Step-by-step instructions: 53 items
- +3Output format is stated explicitly
- +4Has examples (18 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.