SKILLEMALL.ai
GitHub ↗ RU Sign in

BC predictclash

Predict Clash - join prediction rounds, answer questions about crypto prices, stocks, and more. Compete for rankings and earn Predict Points. Use when user wants to participate in prediction games.

modbender/skill-library-mcp Agent Skills author: modbender MIT 2 files body ≈ 4 056 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Predict Clash - join prediction rounds, answer questions about crypto prices, stocks, and more.

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

IntegrationSoftware developmentAI 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
B
78/100
safety, quality, tests
Safety 60%
75
Quality 40%
82
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
When it triggers w 12
20
Inputs and preconditions w 11
30
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

    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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • medium Exfiltration net-credential-use SKILL.md:67
      Credential used in a network call (verify the destination is the intended service)
      VERIFY_CODE=$(curl -s -o /dev/null -w "%{http_code}" "$API/agents/me" -H "Authorization: Bearer $TOKEN")
    • medium Exfiltration net-credential-use SKILL.md:97
      Credential used in a network call (verify the destination is the intended service)
      ROUNDS_RESP=$(curl -s "$API/rounds/current" -H "Authorization: Bearer $TOKEN")
    • medium Exfiltration net-credential-use SKILL.md:124
      Credential used in a network call (verify the destination is the intended service)
      ROUND=$(curl -s "$API/rounds/\$ROUND_ID" -H "Authorization: Bearer $TOKEN")
    • medium Exfiltration net-credential-use SKILL.md:227
      Credential used in a network call (verify the destination is the intended service)
      ROUNDS_LIST=$(curl -s "$API/rounds?state=revealed&limit=3" -H "Authorization: Bearer $TOKEN")
    • medium Exfiltration net-credential-use SKILL.md:244
      Credential used in a network call (verify the destination is the intended service)
      MY_PREDS=$(curl -s "$API/rounds/$LATEST_ID/my-predictions" -H "Authorization: Bearer $TOKEN")

    Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "tools"
    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 59/100

    • 0Result and completion. Does not say what the result is
    • 20When it triggers. No condition that starts the skill
    • 30Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 2 mutating operations with no state check
    • 50Failures and branches. 0 branches, has a failure section
    • 70Execution cost. Instruction body is 4056 tokens
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 38 steps
    • 100Consistency. Name and required fields are in place
    • 100Progress reporting. Reports progress
    • low 13 top-level sections: this looks like several domains in one skill
    • low The response is described with custom markup (8 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
    • +1No license
    • +2Single-language instructions
    • +3Description length 197: enough signal without eating the budget
    • +4Structure: 14 headings
    • +3Step-by-step instructions: 38 items
    • +4Has examples (9 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.