SKILLEMALL.ai
GitHub ↗ RU Sign in

CD cabin-sol

Solana development tutor and builder. Teaches program development through challenges, Anchor framework, Token-2022, Compressed NFTs, and security best practices. "Return to primitive computing."

modbender/skill-library-mcp Agent Skills author: modbender MIT 19 files · 1 script body ≈ 2 444 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Solana development tutor and builder.

As a process D 48/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureSoftware developmentLearningtype 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
C
70/100
safety, quality, tests
Safety 60%
73
Quality 40%
66
Run on models
none yet
Process rating
D
48/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
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.

Dangerous commands 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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 23

✓ No critical or high findings

Medium and low: 23
  • medium Dangerous commands cmd-pipe-to-shell knowledge/challenges/02-nft-metaplex.md:192
    Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)
    bash <(curl -sSf https://sugar.metaplex.com/install.sh)
    security skill
  • low Secrets in code secret-high-entropy-token CLAUDE.md:160
    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 CLAUDE.md:359
    High-entropy token-like string (may be an id, hash or a credential)
    spl-token create-token --program-id Toke…uEb
  • low Secrets in code secret-high-entropy-token data/addresses/programs.json:8
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "Toke…5DA"
    quoted
  • low Secrets in code secret-high-entropy-token data/addresses/programs.json:12
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "Toke…uEb"
    quoted
  • low Secrets in code secret-high-entropy-token data/addresses/programs.json:16
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "ATok…knL"
    quoted
  • low Secrets in code secret-high-entropy-token data/addresses/programs.json:20
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "meta…x1s"
    quoted
  • low Secrets in code secret-high-entropy-token data/addresses/programs.json:24
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "BGUM…PUY"
    quoted
  • low Secrets in code secret-high-entropy-token knowledge/challenges/05-token-2022.md:22
    High-entropy token-like string (may be an id, hash or a credential)
    SPL Token Program:     Toke…5DA
  • low Secrets in code secret-high-entropy-token knowledge/challenges/05-token-2022.md:23
    High-entropy token-like string (may be an id, hash or a credential)
    Token-2022 Program:    Toke…uEb
  • low Secrets in code secret-high-entropy-token knowledge/challenges/05-token-2022.md:33
    High-entropy token-like string (may be an id, hash or a credential)
    --program-id Toke…uEb \
  • low Secrets in code secret-high-entropy-token knowledge/challenges/05-token-2022.md:40
    High-entropy token-like string (may be an id, hash or a credential)
    --program-id Toke…uEb
  • low Secrets in code secret-high-entropy-token knowledge/challenges/05-token-2022.md:44
    High-entropy token-like string (may be an id, hash or a credential)
    --program-id Toke…uEb
  • low Exfiltration exfil-secret-in-url knowledge/challenges/06-compressed-nfts.md:95
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    `https://mainnet.helius-rpc.com/?api-key=…
    placeholder
  • low Secrets in code secret-high-entropy-token knowledge/challenges/06-compressed-nfts.md:139
    High-entropy token-like string (may be an id, hash or a credential)
    Bubblegum:           BGUM…PUY
  • low Secrets in code secret-high-entropy-token knowledge/challenges/06-compressed-nfts.md:140
    High-entropy token-like string (may be an id, hash or a credential)
    Account Compression: cmtD…NCK
  • low Secrets in code secret-high-entropy-token knowledge/challenges/06-compressed-nfts.md:141
    High-entropy token-like string (may be an id, hash or a credential)
    Noop:                noop…MmV
  • low Secrets in code secret-high-entropy-token knowledge/challenges/07-oracle-pyth.md:79
    High-entropy token-like string (may be an id, hash or a credential)
    SOL/USD:  H6AR…JEG
  • low Secrets in code secret-high-entropy-token knowledge/challenges/07-oracle-pyth.md:80
    High-entropy token-like string (may be an id, hash or a credential)
    BTC/USD:  GVXR…oMU
  • low Secrets in code secret-high-entropy-token knowledge/challenges/07-oracle-pyth.md:81
    High-entropy token-like string (may be an id, hash or a credential)
    ETH/USD:  JBu1…WdB
  • low Secrets in code secret-high-entropy-token knowledge/challenges/07-oracle-pyth.md:82
    High-entropy token-like string (may be an id, hash or a credential)
    USDC/USD: Gnt2…otD
  • low Secrets in code secret-high-entropy-token SKILL.md:160
    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 SKILL.md:359
    High-entropy token-like string (may be an id, hash or a credential)
    spl-token create-token --program-id Toke…uEb

Files scanned: 19. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 48/100

  • 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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 4 mutating operations with no state check
  • 85Steps. 29 steps, 1 vague phrases
  • 100Tools and files. No external tools needed
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2444 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 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)
  • +3Output format is not stated: the model decides each time
  • -42 reference files, but SKILL.md never points to them: the model will not open them
  • -31 of 1 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 194: enough signal without eating the budget
  • +4Structure: 40 headings
  • +3Step-by-step instructions: 29 items
  • +4Has examples (16 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.