AC openpump-solana-mcp
Solana token launch and trading tools via the OpenPump MCP server. Creates tokens on pump.fun, buys and sells tokens, runs market-making bots, snipes new token launches, sets stop-loss orders, generates vanity addresses, manages custodial wallets, transfers SOL and SPL tokens, checks balances, gets price quotes, monitors portfolio positions and creator fees. Use when the user asks to launch a token, trade a memecoin, buy or sell on pump.fun, check wallet balance, transfer SOL, set up a sniper, run a market maker, create wallets, get a price quote, claim creator fees, or do anything with pump.fun tokens. Also use for bundle launches, Jito bundles, bonding curve queries, and spam launches. Do not use for general Solana RPC queries, non-pump.fun DeFi (Raydium, Jupiter, Orca), NFT operations, or importing external private keys.
As a process C 53/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- 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
-
medium Broad scope
meta-agent-memory-dumpworkspace-template/HEARTBEAT.mdAgent memory / workspace files bundled with the skill (2) — likely a workspace dump with personal data or tokensworkspace-template/HEARTBEAT.md, workspace-template/SOUL.md
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 20 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 23 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3198 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Description length 835: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 31 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (14 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.