SKILLEMALL.ai
GitHub ↗ RU Sign in

CD soul

Embody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.

aaronjmars/soul.md Agent Skills author: aaronjmars 80 files · 4 scripts body ≈ 1 097 tokens Open the sourcegithub.com↗ analyzed 4 d ago

Embody this digital identity.

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

ProcedureWriting and documentstype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
C
80/100
safety, quality, tests
Safety 60%
86
Quality 40%
72
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.

Broad scope 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 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.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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 · 10

✓ No critical or high findings

Medium and low: 10
  • medium Broad scope meta-agent-memory-dump examples/ansem/MEMORY.md
    Agent memory / workspace files bundled with the skill (8) — likely a workspace dump with personal data or tokens
    examples/ansem/MEMORY.md, examples/ansem/SOUL.md, examples/elon-musk/MEMORY.md, examples/elon-musk/SOUL.md, examples/garry-tan/MEMORY.md
  • low Dangerous commands cmd-background-process examples/garry-tan/tests/prediction_test.md:71
    Starts a background / autostarted process (test fixture / example file)
    Predicted take: yes, specifically the delivery. Not the underlying view that entrenched SF politicians were doing damage. Apologizes cleanly, once. Refuses the frame that he should disown the broader
    fixture
  • low Dangerous commands cmd-pipe-to-shell-known-host examples/karpathy/data/github/karpathy_char-rnn_README.md:17
    Pipe-to-shell installer from a well-known host (still executes remote code) (test fixture / example file)
    $ curl -s https://raw.githubusercontent.com/torch/ezinstall/master/install-deps | bash
    fixture
  • low Secrets in code secret-password-literal examples/karpathy/data/writing/blockchain.html:190
    Hard-coded password / key literal (may be an example) (test fixture / example file)
    <div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="c1"># secret_key = random.randrange(1, bitcoin_gen.n) # this is how you _would_ do it
    fixture
  • low Secrets in code secret-high-entropy-token examples/karpathy/data/writing/blockchain.html:887
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    <div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code>mnNc…fzQ
    fixture
  • low Secrets in code secret-high-entropy-token examples/karpathy/data/writing/blockchain.html:899
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    <div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code>'mrCD…C8r'
    fixturequoted
  • low Secrets in code secret-high-entropy-token examples/karpathy/data/writing/blockchain.html:917
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    3. Bitcoin address:  mnNc…fzQ
    fixture
  • low Secrets in code secret-high-entropy-token examples/karpathy/data/writing/blockchain.html:922
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    <p>It is now time to create a transaction. We are going to be sending some BTC from the address we generated above (mnNc…fzQ) to some second wallet we control. Let’s create t
    fixture
  • low Secrets in code secret-high-entropy-token examples/karpathy/data/writing/blockchain.html:938
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
    3. Bitcoin address:  mrFF…vx9
    fixture
  • low Obfuscation obf-hex-escape-chain examples/karpathy/data/writing/blockchain.html:1443
    Escaped/char-code string obfuscation (test fixture / example file; quoted — discussed, not commanded)
    Tx(version=1, tx_ins=[TxIn(prev_tx=b'$^-\x1f\x87AX6\xcb\xb7\xb0\xbc\x84\xe4\x0fL\xa1\xd2\xa8\x12\xbe\x0e\xda8\x1f\x02\xfb"$\xb4\xadi', prev_index=0, script_sig=Script(cmds=[b'0D\x02 \x19\x9aj\xa5c\x06
    fixturequoted

Files scanned: 79. 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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 2 mutating operations with no state check
  • 40Consistency. Frontmatter name (soul) differs from the folder (soul.md)
  • 100Tools and files. No external tools needed
  • 100Steps. 52 steps
  • 100Execution cost. Instruction body is 1097 tokens
  • 100Progress reporting. Reports progress

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 126: enough signal without eating the budget
  • +4Structure: 17 headings
  • +3Step-by-step instructions: 52 items
  • +4Has examples (2 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.