adjudication-framework
Stage 2 synthesis adjudication rules for specialist conflict resolution.
Skill by alakbarr
Chalk Labs
Need help deploying adjudication-framework?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/alakbarr-adjudication-framework
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: finance
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 2, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/adjudication-framework
What's inside
- Skill name
adjudication-framework- Description
- Stage 2 synthesis adjudication rules for specialist conflict resolution.
- License
- MIT
- Instructions
- 26 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Adjudication Framework — Stage 2 Synthesis Rules
## 1. Evidence Quality Hierarchy & Specialist Anti-Crowding Rule
1. **PRICE ACTION (Technical)**: Highest baseline weight ($45\%$). Price displacement, structural breaks (BOS/ChoCH), and unmitigated institutional zones define actual entry timing and risk boundaries.
2. **MACRO BRIEF (Macro)**: Sovereign directional tailwinds ($35\%$). High weight ($< 3\text{h}$ old), Medium ($3\text{--}5\text{h}$), Low ($> 5\text{h}$).
3. **POSITIONING (Sentiment)**: Non-blocking crowding/exhaustion gauge ($20\%$).
- **Specialist Anti-Crowding Rule**: `Technical == Macro` with `Sentiment` neutral or contrarian (`uncrowded_institutional_synergy`) is the highest-expectancy setup (`81.8%` 12h / `65.4%` 24h accuracy). Treat `Sentiment Specialist` as a non-blocking crowding/exhaustion gauge, NEVER as a primary directional blocker when retail positioning is moderate ($35\%\text{--}68\%$).
- **Crowded Tech+Sentiment Trap vs Macro (`crowded_tech_sent_trap_vs_macro`)**: When `Technical == Sentiment != Macro` (`CROWDED_TECH_SENT_TRAP_VS_MACRO`), retail sentiment and short-term price action are chasing into institutional opposition (`71.4%` 24h reversal rate). Reject (`avoid`/`wait`) trades aligned with the retail crowd against `Macro`; approve trades aligned with the `Macro Specialist` direction when supported by structure.
- **Crowded 3-of-3 Exhaustion Warning (`crowded_unanimous_exhaustion`)**: When `Technical == Macro == Sentiment` all agree in the same direction AND price is already extended past Equilibrium ($pos > 0.55$ for `BUY` or $pos < 0.45$ for `SELL`), beware late-stage trend exhaustion and default to `WAIT` or an outer pullback limit order.
## 2. Spatial, Regime & Institutional Synergy Protocol (3-Zone Dealing Range)
Calculate or inspect `dealing_range_pos` $pos = (\text{Close} - \text{Low}_{20}) / (\text{High}_{20} - \text{Low}_{20})$, `h4_impulse_atr`, and `regime_classification`:
1. **DISCOUNT (`DISCOUNT_ACCUMULATION_ZONE`, $pos \le 0.38$)**: Institutional accumulation zone; approve `BUY` setups when structural demand holds (even if lagging Stage 1 macro or unanimous specialists are bearish) or confirmed breakdown `SELL` when `BEARISH_IMPULSE_BREAKOUT` ($\text{h4\_impulse\_atr} \le -1.25$).
2. **PREMIUM ($pos \ge 0.65$)**: Institutional distribution or `UPPER_RANGE_TREND_CONTINUATION` zone; approve `SELL` setups at supply/rejection, or `BUY` when `BULLISH_IMPULSE_BREAKOUT` ($\text{h4\_impulse\_atr} \ge +1.25$) / `UPPER_RANGE_TREND_CONTINUATION`. Reject market-chasing `BUY` inside `OVEREXTENDED_RANGE_CEILING_PULLBACK_RISK` ($pos \ge 0.80$ without structure breakout).
3. **EQUILIBRIUM ($0.38 < pos < 0.65$)**: Reject (`WAIT` / `AVOID`) when `regime_classification == "EQUILIBRIUM_DEAD_ZONE_CHOP"` ($0.40 \le pos \le 0.60$ and $|\text{h4\_impulse\_atr}| < 0.25$). Otherwise, market or limit execution in `MID_RANGE_DIRECTIONAL_FLOW` is PERMITTED when `Technical == Macro` (`uncrowded_institutional_synergy`) or strong structural confluence ($\ge 10$) and H4/H1 price structure aligns.
| Scenario | Specialist / Regime Alignment | Synthesized Action | Sizing & Invariants |
|:---|:---|:---|:---|
| **Uncrowded Institutional Synergy** | `Tech == Macro` (BULL/BEAR), `Sent != Tech` (`uncrowded_institutional_synergy`) | **BUY / SELL** | Highest-expectancy alpha. Standard risk sizing ($1.0\times$). Net $R:R \ge 1.50$. |
| **Discount Accumulation Zone** | `DISCOUNT_ACCUMULATION_ZONE` ($pos \le 0.38$) with structural demand | **BUY** | Approve `BUY` even if lagging Stage 1 macro or unanimous specialists are bearish ($0.65\times\text{--}0.85\times$). |
| **Crowded Tech+Sent Trap vs Macro** | `Tech == Sent != Macro` (`CROWDED_TECH_SENT_TRAP_VS_MACRO`) | **Follow Macro / AVOID Trap** | Approve trade aligned with `Macro` direction; reject (`avoid`/`wait`) trade chasing `Tech+Sent` against `Macro`. |
| **Impulse Breakout** | `BULLISH_IMPULSE_BREAKOUT` / `BEARISH_IMPULSE_BREAKOUT` ($|\text{h4\_impulse\_atr}| \ge 1.25$) | **BUY / SELL** (Trend Continuation) | Follow active H4 displacement; never counter-trend fade an active impulse breakout. |
| **Overextended Range Ceiling** | `OVEREXTENDED_RANGE_CEILING_PULLBACK_RISK` ($pos \ge 0.80$, no breakout) | **WAIT / AVOID Chase** | Do not market-chase at range ceiling without a structure breakout. |
| **Equilibrium Dead-Zone Chop** | `EQUILIBRIUM_DEAD_ZONE_CHOP` ($0.40 \le pos \le 0.60$, $\|\text{h4\_impulse\_atr}\| < 0.25$) | **WAIT / AVOID** | Directionless mid-range chop; preserve capital. |
## 3. Zero-Arithmetic Bracket Adoption (`adopted_bracket`) & Intraday ADR R:R Compliance
- **Zero-Arithmetic Bracket Adoption (`adopted_bracket`)**: When submitting `BUY` or `SELL` via `submit_asset_analysis`, pass `adopted_bracket="LONG_OPTION_A"` (for `BUY`) or `adopted_bracket="SHORT_OPTION_B"` (for `SELL`) from the pre-computed `DETERMINISTIC INVARIANT ENGINE` block so verified `entry_condition`, `stop_loss`, and `take_profit` are populated without mental floating-point arithmetic errors.
- **Harmonized Intraday R:R Rule (`net R:R >= 1.50`)**: Any bracket with **net $R:R \ge 1.50$** and **$\text{SL} \ge 1.0\times\text{H4 ATR}$** (or ADR-harmonized floor $\ge 0.95\times\text{ATR}$ / $\le 0.50\times\text{ADR}$) is **100% compliant** with Monika's intraday ADR geometry (`TP = min(1.50x ATR, 0.68x ADR)`, `SL = TP / 1.50`). Never reject or downgrade a trade in Stage 2 or Stage 3 Investment Judge solely because $R:R$ is $1.50\text{--}1.70$ instead of $1.75 / 2.00$.
- **Score Sub-Threshold**: If `confluence_score < effective_threshold` $\rightarrow$ Decision MUST be `WAIT`.
- **Priced-In Exhaustion**: If `priced_in_score >= 8` $\rightarrow$ Prohibit trend-following market chase in direction of priced-in narrative. Stance is `WAIT` for pullback or re-evaluation at outer structural discount/premium.
- **RiskGate Invalidation**: If RiskGate returns an active blocking issue (drawdown, spread, news window) $\rightarrow$ Decision MUST be `WAIT` or `AVOID`.
- Output structured analysis strictly via `submit_asset_analysis`.
## 4. Structural Stop Loss Anchoring Invariant
- **Major H4 Swing Anchoring**: Stop Loss MUST be placed beyond the major H4 swing level or order block boundary, NOT minor M15 intraday noise.
- **Mandatory Structural Buffer & Floor**: Minimum SL distance MUST be $\ge 1.0\times\text{ ATR}(14, \text{H4})$ (or ADR-harmonized floor $\ge 0.95\times\text{ATR}$ / $\le 0.50\times\text{ADR}$) with harmonized intraday ceiling $\le \max(\text{ADR cap}, 1.35\times\text{H4 ATR})$ and net $R:R \ge 1.50$.
## 5. Sovereign Dollar Regime & Anti-Falling-Knife Invariants
- **Dynamic Dollar Momentum**: Prohibit commodity/crypto longs only when DXY has active upward momentum (DXY > 20 EMA and positive daily change > +0.3%). Static price levels alone (e.g. 101.00) do not invalidate technical setups if DXY is consolidating or pulling back.
- **Anti-Falling-Knife Rule**: When macro direction strongly opposes technical direction (e.g., strong macro bearish on BTC/Gold), touching a discount POI alone is INSUFFICIENT. A confirmed liquidity sweep of prior swing low (Turtle Soup) followed by displacement back above the sweep level is MANDATORY before any BUY is authorized. Never buy an untethered falling knife into an un-swept level.From alakbarr/Monika, MIT.
More from alakbarr/Monika
- 0.561score
os-terminal-automation
alakbarr
Universal Terminal & Process Execution Playbook: Controlled shell execution, process monitoring, background task supervision, and operator safety gating.
SkillAFreshness: AClaude Code +9 - 0.561score
database-analytics-and-reporting
alakbarr
Direct SQL & Analytical Query Playbook: Schema inspection, safe read-only SQL queries, performance joins, debate transcript exports, and custom metric…
SkillAFreshness: AClaude Code +9 - 0.561score
desktop-gui-computer-use
alakbarr
Desktop GUI Interaction & Computer Use Playbook: Screen inspection, MetaTrader 5 window snapping, mouse click automation, and keystroke dispatching.
SkillAFreshness: AClaude Code +9 - 0.558score
web-research-fallback
alakbarr
Web research cascade: API, RSS, WebSearch, DrissionPage browser, and PDF parsing.
SkillAFreshness: AClaude Code +9 - 0.558score
academic-literature
alakbarr
Synthesize mathematical formulations and alpha mechanics from quantitative papers.
SkillAFreshness: AClaude Code +9 - 0.558score
code-optimization
alakbarr
Minimal, dependency-light, async-first software architecture and code optimization.
SkillAFreshness: AClaude Code +9 - 0.558score
codebase-inspection
alakbarr
Monika codebase structure auditing, module navigation, and invariant verification.
SkillAFreshness: AClaude Code +9 - 0.558score
data-science-modeling
alakbarr
Vectorized data processing, TimesFM time-series forecasting, and statistical modeling.
SkillAFreshness: AClaude Code +9 - 0.558score
devops-automation
alakbarr
Monika daemon supervision, Docker VPS deployment, and graceful process management.
SkillAFreshness: AClaude Code +9 - 0.558score
financial-research
alakbarr
Cross-asset research, prediction market analysis, derivatives positioning, and sentiment distillation.
SkillAFreshness: AClaude Code +9 - 0.558score
institutional-document-reporting
alakbarr
Institutional document and pitch deck generation (Word .docx, PowerPoint .pptx, Excel .xlsx, PDF tearsheets).
SkillAFreshness: AClaude Code +9 - 0.558score
software-development
alakbarr
Surgical software engineering, safe refactoring, and quality invariants for Monika.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 12, 2026 (25 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/alakbarr/Monika
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from alakbarr
- 0.561score
os-terminal-automation
alakbarr
Universal Terminal & Process Execution Playbook: Controlled shell execution, process monitoring, background task supervision, and operator safety gating.
SkillAFreshness: AClaude Code +9 - 0.561score
desktop-gui-computer-use
alakbarr
Desktop GUI Interaction & Computer Use Playbook: Screen inspection, MetaTrader 5 window snapping, mouse click automation, and keystroke dispatching.
SkillAFreshness: AClaude Code +9 - 0.561score
database-analytics-and-reporting
alakbarr
Direct SQL & Analytical Query Playbook: Schema inspection, safe read-only SQL queries, performance joins, debate transcript exports, and custom metric…
SkillAFreshness: AClaude Code +9 - 0.558score
systematic-debugging
alakbarr
Scientific root-cause analysis, log inspection, and defect remediation for Monika.
SkillAFreshness: AClaude Code +9 - 0.558score
academic-literature
alakbarr
Synthesize mathematical formulations and alpha mechanics from quantitative papers.
SkillAFreshness: AClaude Code +9 - 0.558score
quant-math-verification
alakbarr
Institutional quantitative mathematics, formula verification, and statistical edge calculation standards.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get adjudication-framework running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
adjudication-framework skill. Agent Mart. https://agentmart.dev/skills/alakbarr-adjudication-framework (last updated 2026-10-24)