Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency.
原文の言語: 英語
メニュー
このリポジトリの skills
SkillsMP は vamseeachanta/workspace-hub から 3,441 件の skill を収集しています。skill を開くとソースと詳細を確認できます。
vamseeachanta/workspace-hub収集済み skill 3,441 件中 40 件を表示しています。
Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency.
原文の言語: 英語
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and…
原文の言語: 英語
End-to-end pipeline for writing ML/AI research papers — from experiment design through analysis, drafting, revision, and submission. Covers NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Integrates automated experiment monitoring, statistical analysis, iterative…
原文の言語: 英語
Auto-query llm-wiki domains for relevant context before executing domain tasks
原文の言語: 英語
Generate clinical trial protocols for medical devices or drugs through a modular, waypoint-based architecture with research-only and full protocol modes.
原文の言語: 英語
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV for LIMS systems and data lakes.
原文の言語: 英語
Run nf-core bioinformatics pipelines (rnaseq, sarek, atacseq) on sequencing data for gene expression, variant calling, and chromatin accessibility analyses.
原文の言語: 英語
Systematic framework for scientific problem selection, project ideation, troubleshooting stuck projects, and strategic research decisions.
原文の言語: 英語
Deep learning for single-cell analysis using scvi-tools: data integration, batch correction, multi-modal analysis, reference mapping, and more.
原文の言語: 英語
Performs quality control on single-cell RNA-seq data (.h5ad or .h5 files) using scverse best practices with MAD-based filtering and comprehensive visualizations.
原文の言語: 英語
Prevent Codex/Gemini adversarial review dispatch failures caused by relative prompt-file paths and background workdir drift.
原文の言語: 英語
Prevent adversarial review dispatch failures caused by relative prompt paths, superseded background sessions, and stale completion notices when launching Codex/Gemini review jobs.
原文の言語: 英語
Prevent stale plan/code review prompts from being sent to Codex/Gemini after the underlying artifact changed.
原文の言語: 英語
Prevent approval-stage adversarial review churn by keeping plans implementation-focused, schema-complete, and free of stale review-process narration.
原文の言語: 英語
Run an approval-stage adversarial cross-review sweep across multiple GitHub issues, drafting any missing canonical plan artifacts before dispatching Codex/Gemini reviews.
原文の言語: 英語
Recover adversarial plan reviews on large or sandbox-hostile repos by embedding grounded facts + full plan text directly in a compact prompt and explicitly forbidding reviewer tool use.
原文の言語: 英語
Recover adversarial plan reviews when providers keep reading stale remote/main content instead of the revised local artifact.
原文の言語: 英語
Add Google-style docstrings to all public functions and classes in a Python package. Uses AST parsing for precise gap detection, priority ranking by coverage ratio, and multi-file patching.
原文の言語: 英語
Recover adversarial plan reviews in large or tool-constrained repos by using compact self-contained prompts that forbid tool use and rely only on embedded grounded facts plus the plan text.
原文の言語: 英語
Handle Gemini adversarial-review runs that emit repeated 429 capacity errors before either recovering with a real verdict or failing unavailable.
原文の言語: 英語
Compact live-execution checklist companion for approved GitHub issue work. Use during active implementation as a fast operational route; gh-work-execution remains the canonical source of truth.
原文の言語: 英語
Canonical GitHub issue execution route after plan approval — strengthened resource intelligence, TDD-first implementation, targeted validation, adversarial review, delegation controls for Codex agent teams, GitHub progress posting, future-issue capture, and…
原文の言語: 英語
Audit a repo's live GSD/get-shit-done workflow state against docs, issues, and runtime outputs to find stale issues, automation reliability gaps, parser drift, migration residue, and policy contradictions.
原文の言語: 英語
Assess a multi-machine, multi-repo AI-enabled workspace for readiness, provider allocation, and issue prioritization.
原文の言語: 英語
Dispatch parallel adversarial reviews to Codex and Gemini CLIs for plans or code artifacts. Use when the AI Review Routing Policy requires two- or three-provider review — architecture-heavy, security-affecting, cross-module, or high-stakes changes.
原文の言語: 英語
Design self-contained prompts for 3-5 terminals to run overnight without supervision. Ensures zero git contention, provider-optimal allocation, and a clear morning deliverable summary.
原文の言語: 英語
Build overnight parallel batches that close stale-open GitHub issues by proving landed work already satisfies the issue, instead of wasting implementation lanes on redoing completed work.
原文の言語: 英語
Launch approved GitHub issue implementation in parallel using isolated git worktrees, committed execution-pack prompts, local plan-approved markers, and direct background Codex runs when delegate_task workers are unreliable for real repo writes.
原文の言語: 英語
Keep iterative plan-review reruns truthful by syncing prompt files, canonical review artifacts, and the plan's own review-summary narrative after each adversarial wave.
原文の言語: 英語
Run a planning-only multi-terminal wave to harden blocked `status:plan-review` issues for fresh adversarial re-review, with zero implementation work and explicit path ownership.
原文の言語: 英語
Class-level workflow for plan-review hardening, adversarial review reruns, artifact grounding, approval hygiene, and prompt/path drift recovery.
原文の言語: 英語
Plan mode for Hermes — inspect context, write a markdown plan into the active workspace's `.hermes/plans/` directory, and do not execute the work.
原文の言語: 英語
Prevent adversarial review dispatch failures caused by sandbox/tmp path mismatches and provider CLI working-directory drift when launching Codex or Gemini with prompt files.
原文の言語: 英語
Prevent stale adversarial re-reviews by forcing Codex/Gemini to review the exact revised local plan artifact instead of stale GitHub issue text or default-branch content.
原文の言語: 英語
Generate live issue-specific Codex prompts for a single terminal, with repo-aware path contracts and plan-gate safety checks.
原文の言語: 英語
Write test suites for SKELETON packages (zero test coverage) to uplift them to DEVELOPMENT maturity. Handles non-importable modules, optional dependencies, separate sub-repos, and Flask/web packages without runtime.
原文の言語: 英語
Use when executing implementation plans with independent tasks. Dispatches fresh delegate_task per task with two-stage review (spec compliance then code quality).
原文の言語: 英語
Deprecated alias for gh-work-execution.
原文の言語: 英語
Run cross-agent memory bridge. Sync learnings between machine agents, update shared knowledge. Phase 5 of #1760.
原文の言語: 英語
Import a GSD-2 (.gsd/) project back to GSD v1 (.planning/) format
原文の言語: 英語