multi-tf-confluence — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited multi-tf-confluence (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
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.
You are performing systematic multi-timeframe analysis to identify where signals agree and where they conflict across the timeframe stack.
Read trader-profile.json from the project root. If it exists:
instruments.default_timeframe as the trading TF and instruments.higher_timeframes as the analysis stack instead of the generic table belowindicators.trusted and skip indicators.ignored. If the trader trusts VPA but ignores MACD, don't waste a row on MACD.indicators.custom_signals to interpret VPA or custom indicator signals in contextinstruments.primary as the symbol to scan (no need to ask)If no profile exists, use the defaults below and suggest running profile-setup.
Based on the user's trading timeframe, select the stack:
| Trading TF | Analysis Stack (high → low) |
|---|---|
| 1m / 5m | Daily → 1H → 15m → 5m |
| 15m | Weekly → Daily → 4H → 15m |
| 1H | Weekly → Daily → 4H → 1H |
| 4H | Monthly → Weekly → Daily → 4H |
| Daily | Monthly → Weekly → Daily |
If unclear, ask the user what timeframe they trade on. Default to the chart's current timeframe.
chart_get_state — note the current timeframe so you can restore it laterFor each timeframe in the stack:
chart_set_timeframe — switch to this timeframedata_get_study_values — capture all indicator readingsdata_get_ohlcv with summary: true — price action summarydata_get_pine_labels — any labeled levels (optional, skip if slow)Record for each timeframe:
chart_set_timeframe — switch back to the user's trading timeframe.
Compare signals across timeframes and identify:
Where 3+ timeframes agree on direction. This is a high-probability zone.
Where timeframes disagree. This means caution — the trade may work on one timeframe but fail on another.
Where support/resistance from multiple timeframes converge at similar prices. These are the strongest levels.
## Multi-Timeframe Confluence: [SYMBOL]
Trading Timeframe: [TF] | Scanned: [TF1, TF2, TF3, TF4]
### Timeframe Summary
| Timeframe | Trend | Momentum | RSI | Key Support | Key Resistance |
|-----------|----------|----------|------|-------------|----------------|
| Daily | UP | Bullish | 58 | 22,400 | 22,900 |
| 4H | UP | Neutral | 52 | 22,550 | 22,800 |
| 1H | SIDEWAYS | Bearish | 38 | 22,650 | 22,780 |
| 15m | DOWN | Bearish | 29 | 22,670 | 22,720 |
### Confluence Score: 6/10
### Agreement
- Higher timeframes (Daily, 4H) confirm uptrend
- Support cluster at 22,550-22,650 (multiple TFs)
### Conflict
- Lower timeframes (1H, 15m) showing bearish momentum
- RSI divergence: Daily bullish but 15m oversold
### Interpretation
[2-3 sentences: what this means for the trader's next decision]
### Actionable Levels
- **Strong support**: [price] (confirmed on [TF1, TF2])
- **Strong resistance**: [price] (confirmed on [TF1, TF2])
- **Decision zone**: [price range where trend could flip]summary: true and avoid verbose outputs~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.