Results for “pre-pr”

Split an idea or active research path into two or more new research product-path stubs after alignment approval; preserves the source path by default and archives it only when --archive is passed

Create or refresh hierarchical AGENTS.md documentation for Claude Code, Codex/OMX, Gemini, and Antigravity/OMA projects, preserving manual notes while excluding runtime state such as root .omc, .omx, .survey, .codex, and generated build folders.

Production-grade multi-threaded Rust vanity address generator for Solana — 100K+ keys/sec using Rayon parallel iterators with solana-sdk, Base58 pattern matching, prefix/suffix support, security-hardened file output, and Criterion benchmarks.

Control Claude Code via MCP protocol. Trigger with "plan" to write a precise execution plan then feed it to Claude Code. Also supports direct commands, persistent sessions, agent teams, and advanced tool control.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Discover and use DFlow documentation, Agent CLI, Trading API, Metadata API, Proof KYC, prediction markets, and the hosted DFlow docs MCP. Use before implementing DFlow features or when field-level endpoint details are needed.

Design leakage-safe feature engineering strategies for tabular/time-series datasets. Use when: (1) preparing model-ready features, (2) selecting transformations and encodings, (3) documenting feature lineage. NOT for: model serving or infra provisioning.

Build, slice, concatenate, read, and write AnnData annotated data matrices (obs, var, X, layers, obsm, uns) — the scverse data STRUCTURE, not an analysis pipeline. Use when creating or wrangling .h5ad/zarr files, managing cell and gene annotations, concatenating batches, or handling layers/obsm/backed-mode; for the QC, normalization, clustering, UMAP, and differential-expression analysis pipeline prefer alterlab-scanpy instead, and for RNA velocity from spliced/unspliced layers prefer alterlab-scvelo instead. Part of the AlterLab Academic Skills suite.

Writes and manages professional bios for any platform and purpose, matching your voice and career stage, and keeps them current as your work evolves.

Use when forecasting resource needs, evaluating if current capacity is sufficient for planned work, or sizing systems for expected load. This skill provides procedures for estimating, planning, and monitoring capacity to prevent resource shortages.

Expert photography prompt engineer specializing in crafting detailed, evocative prompts for AI image generation. Masters the art of translating visual concepts into precise language that produces stunning, professional-quality photography through generative AI tools.

Information Security Management System (ISMS) audit expert for ISO 27001 compliance verification, security control assessment, and certification support. Use when the user mentions ISO 27001, ISMS audit, Annex A controls, Statement of Applicability (SOA), gap analysis, nonconformity management, internal audit, surveillance audit, or security certification preparation. Helps review control implementation evidence, document audit findings, classify nonconformities, generate risk-based audit plans, map controls to Annex A requirements, prepare Stage 1 and Stage 2 audit documentation, and support corrective action workflows.

Plan customer discovery interviews with the right goal, segment, constraints, and method for problem validation, churn research, or new product ideas.

Product execution specialist for SaaS, apps, AI tools, and internal software products. Trigger when user requests 'build SaaS', 'define features', 'create user flow', 'scope MVP', 'prepare build package', 'software product', 'app definition', or 'PRD creation'.

Pressure-tests AI Management Systems against ISO 42001 with six forcing questions for certification readiness, internal audits, and new-system onboarding.

Restructure code while preserving behavior: confirm tests are green, refactor in small steps, keep tests green, review, and commit with a gated workflow.

Operate across Google Drive, Docs, Sheets, and Slides as one workflow surface for plans, trackers, decks, and shared documents.

Keeps AI coding agents tightly scoped to only change what the user explicitly requested, using the simplest viable solution and asking before expanding scope.

Author and review GitHub Actions workflow YAML to ensure syntactic and structural correctness, preventing failures from unquoted expressions and other YAML-vs-Actions traps.

Upgrade GitHub Actions to supported runtimes by selecting safe action versions, preserving workflow behavior, and validating post-upgrade execution.

Parse PDFs, Office files, and images locally with layout-preserved text, bounding boxes, OCR, and page screenshots for RAG and multimodal agents.

Systematically remove malware, backdoors, and attacker persistence mechanisms from infected systems while ensuring complete eradication and preventing re-infection.

Generate high-quality speech from text using ElevenLabs' premium voices, with support for 32 languages, multiple models, and voice tuning parameters.

Train large-scale MoE models with FP8/INT4 low-precision RL, speculative decoding, and train-inference alignment using the miles framework.

Breaks a topic into a sequence of adaptive learning articles, adjusting depth and pace based on user feedback from the previous lesson.

Runs Semgrep static analysis with custom YAML rules, supporting taint tracking, metavariable comparisons, and pattern-not-inside exclusions for precise vulnerability detection.

Build, fit, validate, and compare Bayesian models using PyMC, including hierarchical models, MCMC sampling, variational inference, posterior predictive checks, and model comparison.

Extracts a YouTube transcript with yt-dlp, cleans it while preserving all substantive speech, and saves a structured markdown file with metadata, overview, and optional timestamps.

Analyzes evaluation results by requiring a stated hypothesis before examining data, then compares expectations to actual result files to prevent post-hoc rationalization.

Writes internal communications such as status reports, leadership updates, 3P updates, company newsletters, FAQs, and incident reports using company-preferred formats.

Injects intentional failures to test system resilience using Litmus and Chaos Monkey, with a prerequisite to validate detection before running experiments.

Guides analysis of Neuropixels recordings from raw data to curated units, covering preprocessing, motion correction, spike sorting, quality metrics, and export.

Controls IP cameras via RTSP for snapshots and recording, and ONVIF for PTZ movement, presets, and network discovery, with support for common camera brands.

Use `analysis-agent` to identify domain ownership, invariants, state transitions, and cross-context effects when rules change or ownership is unclear. Skip presentation-only or question-only work with no domain behavior.

Evaluate RAG pipelines with Ragas — measure faithfulness, answer relevancy, context precision/recall, and noise sensitivity using LLM-as-judge metrics; run automated test suite generation with TestsetGenerator; integrate with LangChain, LlamaIndex, and CI pipelines.

Scans a codebase for deepening opportunities, presents them as a visual HTML report, then grills through the chosen one. Use when the user wants to improve codebase architecture or find refactoring opportunities.