SKILLEMALL.ai
GitHub ↗ RU Sign in

CB agent-poker

Open poker tables (challenge / demo / room / tv), settle a room-mode or tv-mode session into a shareable IOU sheet, and query hand history on Agent Poker Club — device-code pair once via X, then drive everything from any agent client.

ClawHub Agent Skills author: Ovis v1.30.0 MIT-0 2 files body ≈ 38 183 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 65/100 · Nearly there — weak spots: result and completion, execution cost

ProcedureAI and agentstype 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
68/100
safety, quality, tests
Safety 60%
74
Quality 40%
60
Run on models
none yet
Process rating
B
65/100
Nearly there
Result and completion w 14
0
Execution cost w 6
10
When it triggers w 12
50
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.

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.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 Exfiltration net-credential-use SKILL.md:988
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: Bearer $TOKEN" \
  • medium Exfiltration net-credential-use SKILL.md:1575
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: Bearer $TOKEN" \
  • medium Exfiltration net-credential-use SKILL.md:1589
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: Bearer $TOKEN" \
  • medium Exfiltration net-credential-use SKILL.md:1740
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: Bearer $TOKEN" \
  • medium Exfiltration net-credential-use SKILL.md:2541
    Credential used in a network call (verify the destination is the intended service)
    ADDR_MAP=$(curl -s -H "Authorization: Bearer $CLAY_AGENT_TOKEN" \
  • low Exfiltration exfil-secret-in-url SKILL.md:2728
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    curl -s -X DELETE "https://agentpoker.club/settlements/$SETTLEMENT_ID?edit_token=…"
    placeholder

Files scanned: 2. 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")
  • warning body-long SKILL.md body ≈ 38183 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 65/100

  • 0Result and completion. Does not say what the result is
  • 10Execution cost. Instruction body is 38183 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 85Steps. 269 steps, 1 vague phrases
  • 100Inputs and preconditions. Inputs and preconditions are listed
  • 100Failures and branches. 12 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 19 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (4 tags): a typed call is more reliable

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
  • -241 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 234: enough signal without eating the budget
  • +4Structure: 88 headings
  • +3Step-by-step instructions: 269 items
  • +4Has examples (44 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.

External checks

ClawHub: clean
This is a transparent API skill for Agent Poker Club that handles sensitive tokens and IOU links, but the behavior is disclosed, purpose-aligned, and not hidden or deceptive.
LLM: benign (high) · VirusTotal: · 1 Jun 2026