Results for “pre-pr”

Run a pre-mortem — imagine the project has already failed one year from now and work backward to find the root causes before they happen. Load when the user asks for a pre-mortem, wants to imagine failure before committing, asks "what could go wrong before we start", "assume this fails — why", "risk analysis before launch", "what kills this project", "what could go wrong", or when deep-thinking diagnoses a pre-mortem frame. Based on Gary Klein's prospective hindsight method, which surfaces failure causes more effectively than forward risk analysis. Most useful right before a major commitment.

Provides battle-tested PyTorch training recipes for LLMs, vision, diffusion, and biomedical domains, covering training loops, optimizer selection, LR scheduling, mixed precision, and debugging.

Generates premium, app-native mobile screen images and flow images for iOS, Android, and cross-platform products, with strong emphasis on readability, consistency, and art-directed design.

Create professional Marp presentation slides with 7 beautiful themes (default, minimal, colorful, dark, gradient, tech, business). Use when users request slide creation, presentations, or Marp documents. Supports custom themes, image layouts, and "make it look good" requests with automatic quality improvements.

Detect and analyze Linux persistence mechanisms including crontab entries, systemd service units, LD_PRELOAD hijacking, bashrc modifications, and authorized_keys backdoors using auditd and file integrity monitoring.

Implement server-side rendering and hydration in Angular v20+ using @angular/ssr. Use for SSR setup, hydration strategies, prerendering static pages, and handling browser-only APIs. Triggers on SSR configuration, fixing hydration mismatches, prerendering routes, or making code SSR-compatible.

Monitors a watchlist of Kalshi prediction markets for price moves, volume spikes, resolution proximity, and kill-criterion triggers, with cross-venue arbitrage detection against paired Polymarket markets adjusted for fees and slippage.

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

Prepares Hart-Scott-Rodino Act premerger notification filings for FTC/DOJ submission under 15 U.S.C. § 18a and 16 C.F.R. Parts 801-803. Covers threshold verification, NAICS revenue breakdowns, Item 4(c)/(d) document collection, competitive overlap analysis, prior acquisitions disclosure, and filing assembly. Use when an M&A deal may meet HSR size thresholds and requires antitrust clearance, premerger notification, or FTC/DOJ merger review.

Provides a pre-built Salesforce B2B Commerce data model as a Mermaid flowchart with color coding and relationship indicators, plus an optional script to enrich the diagram with live org metadata.

Enforces a disciplined, evidence-based debugging protocol. Use when the user reports a bug, an unexpected behavior, a broken test, or asks "why is X not working?". Prevents premature fixes and treats symptoms. Blocks code changes until a root cause is confirmed.

Live application prep for Heath Barnett. Given a role name or a job application URL, renders the real application form, reads every field including the bespoke custom questions, drafts each answer grounded in Heath's receipts and resume master, and returns a copy-paste breakdown plus the submit window in the hiring manager's timezone. Built for the hot window: Heath is at the keyboard, this gets him ready to paste and submit in minutes. Trigger on "prep [company/role]", "apply prep", "get me ready to apply to [company]", "prep my application for [role]", "extract the questions for [role]", "what does the [company] application ask", or Heath pasting an application URL with intent to apply. Never submits the form. Never fabricates. No em dashes.

Use to plan and run peak-season support — what to freeze, pre-stage and measure daily so volume spikes do not become quality and attrition crises. Trigger for "peak season readiness", "holiday staffing plan", "Black Friday prep", freeze policy or KB changes before peak, pre-hire and ramp for surge, daily war room metrics, peak post-mortem, or when last year's peak broke SLA and attrition.

Enables agents to place pre-launch buy orders for Bankr tokens on Base and to launch new tokens with coordinated demand and distribution via the AutoBoy REST API.

Runs Google Workspace cross-service workflows via the gws CLI, with helpers for standup reports, meeting prep, email-to-task conversion, weekly digests, and file announcements.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Keep sessions focused and efficient — prune stale outputs, preserve active state, recommend compaction

The single highest-leverage convention in code review is prefixing every comment

Pre-commit/ship code review: Codex default; optional Claude, Pi, Droid, Copilot, Cursor, or OpenCode.

Present HTML on connected MarketingClaw node canvases, navigate/eval/snapshot, and debug canvas host URLs.

Mathematical AI interpretability with sheaf cohomology, spectral analysis, causal inference, and hallucination prevention

Use for writing, reviewing, debugging, testing, or diagnosing Bayesian regression and hierarchical models built with Bambi formulas, Model, Family/Likelihood/Link, Prior, fit, prior predictive, and predict. Trigger on common versus group-specific terms, categorical coding, family/link choice, automatic prior scaling, missing rows, PyMC backend settings, and InferenceData predictions. Do not use for hand-built PyMC graphs, NumPyro programs, ArviZ-only analysis of existing draws, frequentist statsmodels formulas, or generic pandas work.

Prepare release readiness notes, version checks, test checklist, and local issue drafts.

Translate text faithfully into a target language while preserving meaning, register, and intent.

Use when content is verbose, repetitive, or padded and needs tightening while preserving meaning

Optimize context window usage — compact stale data, compress via summarization, preserve active state

Prepare implementation handoffs with states, flows, assets, edge cases, and acceptance criteria.

Design and format publication-quality tables: column order, row grouping, notes, precision, reproducibility.

Process large ML datasets in parallel across CPU or GPU clusters, with streaming execution, multi-format I/O, and integration with Ray Train, PyTorch, and TensorFlow for batch inference and preprocessing pipelines.

Detects and eliminates AI writing tropes that make text sound artificial or formulaic. Use when generating text content, writing documentation, creating code comments, or reviewing writing style. Supports four-tier JSON preferences (global/project x shared/local office.json) read via load-preferences.sh.

Prediction market arbitrage & alpha scout. Searches Polymarket and Kalshi for the same event, runs cross-platform arb math (including fees), and ranks opportunities by profitability. Use when asked to "find arb", "scout markets", "find edge", or scan a specific topic across prediction markets.

Configures pre-created scratch org pools for parallel CI testing, reducing pipeline wait times by claiming pre-warmed orgs instead of provisioning on demand. Covers CumulusCI pool commands, Dev Hub limits, and CI integration.

Predicts tissue or cell-type gene expression (log TPM and TPM) from a TSS-centered DNA sequence using the hosted Genomic Intelligence G0 Expression model, conditioned on a free-text cell-type description.