SKILLEMALL.ai
GitHub ↗ RU Sign in

BC solana-compression

For client and program development on Solana ~160x cheaper and without rent-exemption for per-user state, DePIN registrations, or custom compressed accounts. Create, update, close, burn, and reinitialize compressed accounts.

modbender/skill-library-mcp Agent Skills author: modbender MIT 5 files body ≈ 2 130 tokens Open the sourcegithub.com↗ analyzed 2 d ago

For client and program development on Solana ~160x cheaper and without rent-exemption for per-user state, DePIN registrations, or custom compressed accounts.

As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

ProcedureGitHubSoftware developmentAI and agentsWriting and documentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
90
Quality 40%
88
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Obfuscation medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

How to improve

    For the model run — optional
    • 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 · 6

    ✓ No critical or high findings

    Medium and low: 6
    • medium Obfuscation obf-base64-blob references/nullifier-pdas.md:12
      Long base64-looking blob
      | **Example Tx** | [Solana Explorer](https://explorer.solana.com/tx/38fA…rpB) |
    • low Secrets in code secret-high-entropy-token references/compressed-pdas.md:75
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      declare_id!("Your…111");
      quoted
    • low Secrets in code secret-high-entropy-token references/compressed-pdas.md:78
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      derive_light_cpi_signer!("Your…111");
      quoted
    • low Secrets in code secret-high-entropy-token references/compressed-pdas.md:137
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      declare_id!("Hps5…qcS");
      quoted
    • low Secrets in code secret-high-entropy-token references/compressed-pdas.md:140
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      derive_light_cpi_signer!("Hps5…qcS");
      quoted
    • low Secrets in code secret-high-entropy-token references/nullifier-pdas.md:9
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | **Program ID** | `NFLx…BoT` |
      table

    Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 59/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 9 mutating operations with no state check
    • 40Consistency. Frontmatter name (solana-compression) differs from the folder (solana-compression-dev)
    • 50When it triggers. No condition that starts the skill
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 45 steps
    • 100Failures and branches. 1 branches, has a failure section
    • 100Execution cost. Instruction body is 2130 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
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 224: enough signal without eating the budget
    • +4Structure: 14 headings
    • +3Step-by-step instructions: 45 items
    • +4Has examples (4 code blocks)
    • +4Reference files are cited in the instructions (4 of 4)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.