think — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited think (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Step-by-step reasoning chains with model execution.
/think [problem]
/think [model] [problem]
/think [model1,model2] [problem]grok, gemini, openai, perplexity, kimi, qwen
When user invokes /think:
mcp__tachibot-mcp__nextThought({
thought: "[problem]",
model: "[model]",
executeModel: true,
contextWindow: "all",
nextThoughtNeeded: false
})// First model (fresh)
nextThought({ thought: "Analyze: [problem]", model: "[model1]", executeModel: true, contextWindow: 0, nextThoughtNeeded: true })
// Second model (sees previous)
nextThought({ thought: "Build on analysis", model: "[model2]", executeModel: true, contextWindow: "all", nextThoughtNeeded: false })Use gemini as default model.
/think why is my WebSocket disconnecting/think gemini optimize this query/think grok,kimi,gemini design a rate limiter~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.