SKILLEMALL.ai
GitHub ↗ RU Sign in

CD bloom

Bloom Taste Finder — discover your builder taste across 4 spectrums and get a personalized tool stack. For indie devs, vibe coders, and AI builders.

modbender/skill-library-mcp Agent Skills author: modbender MIT 80 files · 6 scripts body ≈ 2 668 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Bloom Taste Finder — discover your builder taste across 4 spectrums and get a personalized tool stack.

As a process D 45/100 · Unfinished process — weak spots: when it triggers, inputs and preconditions, failures and branches

ProcedureGitHubSoftware developmenttype 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
66/100
safety, quality, tests
Safety 60%
68
Quality 40%
64
Run on models
none yet
Process rating
D
45/100
Unfinished process
Inputs and preconditions w 11
0
Failures and branches w 10
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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 · 24

✓ No critical or high findings

Medium and low: 24
  • medium Obfuscation obf-base64-blob DASHBOARD_LINK_IMPLEMENTATION.md:225
    Long base64-looking blob
    https://preview.bloomprotocol.ai/dashboard?token=…
  • medium Exfiltration net-redirectable-api-key src/blockchain/agent-wallet.ts:433
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • low Exfiltration read-dotenv CONVERSATION-CONTEXT-INTEGRATION.md:123
    Reads a .env file
    cp .env.example .env
  • low Exfiltration read-dotenv execute.sh:48
    Reads a .env file (code comment)
    # Copy .env.example if it exists
    comment
  • low Secrets in code secret-high-entropy-token LOCAL-WALLET-IMPLEMENTATION.md:41
    High-entropy token-like string (may be an id, hash or a credential)
    ✅ New local wallet created: 0x5B…313
  • low Secrets in code secret-high-entropy-token LOCAL-WALLET-IMPLEMENTATION.md:61
    High-entropy token-like string (may be an id, hash or a credential)
    ✅ Loaded existing wallet: 0x5B…313
  • low Secrets in code secret-high-entropy-token LOCAL-WALLET-IMPLEMENTATION.md:100
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "walletAddress": "0x5B…313",
    quoted
  • low Secrets in code secret-high-entropy-token LOCAL-WALLET-IMPLEMENTATION.md:117
    High-entropy token-like string (may be an id, hash or a credential)
    ✅ Created wallet: 0x5B…313
  • low Secrets in code secret-high-entropy-token LOCAL-WALLET-IMPLEMENTATION.md:125
    High-entropy token-like string (may be an id, hash or a credential)
    ✅ First run: Created 0x5B…313
  • low Exfiltration read-dotenv LOCAL-WALLET-IMPLEMENTATION.md:150
    Reads a .env file
    cp .env.example .env
  • low Secrets in code secret-high-entropy-token OUTPUT_FORMAT_V2.md:21
    High-entropy token-like string (may be an id, hash or a credential)
    Address: 0x90…C7B
  • low Secrets in code secret-private-key PER_USER_WALLET_IMPLEMENTATION.md:256
    Private key material (placeholder value)
    "privateKey": "-----BEGIN PRIVATE KEY----- …"
    placeholder
  • low Obfuscation obf-base64-blob PERFORMANCE_ANALYSIS.md:38
    Long base64-looking blob (quoted — discussed, not commanded)
    "privateKey": "PHI8…bfC+XR2M…gyD/a8Ir…jhA=="
    quoted
  • low Secrets in code secret-private-key PERFORMANCE_ANALYSIS.md:46
    Private key material (placeholder value)
    "privateKey": "-----BEGIN PRIVATE KEY----- …\n"
    placeholder
  • low Secrets in code secret-private-key PERFORMANCE_ANALYSIS.md:180
    Private key material (placeholder value)
    "privateKey": "-----BEGIN PRIVATE KEY----- …\n"
    placeholder
  • low Secrets in code secret-high-entropy-token scripts/erc8004-poc.ts:13
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    IDENTITY_REGISTRY: '0x80…432',
    quoted
  • low Secrets in code secret-high-entropy-token scripts/erc8004-poc.ts:14
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    REPUTATION_REGISTRY: '0x80…b63',
    quoted
  • low Secrets in code secret-high-entropy-token scripts/erc8004-poc.ts:17
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    IDENTITY_REGISTRY: '0x80…D9e',
    quoted
  • low Secrets in code secret-high-entropy-token scripts/erc8004-poc.ts:18
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    REPUTATION_REGISTRY: '0x80…713',
    quoted
  • low Exfiltration read-dotenv scripts/health-check.sh:29
    Reads a .env file (quoted — discussed, not commanded)
    ISSUES+=("Environment file not configured (copy .env.example to .env)")
    quoted
  • low Secrets in code secret-private-key SETUP_CDP_CREDENTIALS.md:28
    Private key material (placeholder value)
    "privateKey": "-----BEGIN PRIVATE KEY----- …\n"
    placeholder
  • low Secrets in code secret-high-entropy-token SOLUTION-SUMMARY.md:122
    High-entropy token-like string (may be an id, hash or a credential)
    ✅ Wallet Created: 0x29…0F2
  • low Secrets in code secret-high-entropy-token src/blockchain/contract-client.ts:11
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const CONTRACT_ADDRESS = '0x33…B9E';
    quoted
  • low Exfiltration read-dotenv TESTING_GUIDE.md:34
    Reads a .env file (test fixture / example file)
    cp .env.example .env
    fixture

Files scanned: 80. 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")
  • note frontmatter-key unknown frontmatter key "command-dispatch"
  • note frontmatter-key unknown frontmatter key "permissions"

Process rating: all ten parameters 45/100

  • 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. 3 mutating operations with no state check
  • 40Consistency. Frontmatter name (bloom) differs from the folder (bloom-taste-finder)
  • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 85Steps. 57 steps, 2 vague phrases
  • 100Execution cost. Instruction body is 2668 tokens
  • low 17 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)
  • -241 emoji in the instructions: noise for the model
  • -43 reference files, but SKILL.md never points to them: the model will not open them
  • -311 of 13 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 148: enough signal without eating the budget
  • +4Structure: 24 headings
  • +3Step-by-step instructions: 57 items
  • +3Output format is stated explicitly
  • +4Has examples (7 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.