Menú
Skills en este repositorio
SkillsMP ha recopilado 3441 skills de vamseeachanta/workspace-hub. Abre una skill para revisar su origen y sus detalles.
vamseeachanta/workspace-hubMostrando 40 de 3441 skills recopiladas.
Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency.
Idioma del texto original: inglés
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…
Idioma del texto original: inglés
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…
Idioma del texto original: inglés
Auto-query llm-wiki domains for relevant context before executing domain tasks
Idioma del texto original: inglés
Generate clinical trial protocols for medical devices or drugs through a modular, waypoint-based architecture with research-only and full protocol modes.
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
Run nf-core bioinformatics pipelines (rnaseq, sarek, atacseq) on sequencing data for gene expression, variant calling, and chromatin accessibility analyses.
Idioma del texto original: inglés
Systematic framework for scientific problem selection, project ideation, troubleshooting stuck projects, and strategic research decisions.
Idioma del texto original: inglés
Deep learning for single-cell analysis using scvi-tools: data integration, batch correction, multi-modal analysis, reference mapping, and more.
Idioma del texto original: inglés
Performs quality control on single-cell RNA-seq data (.h5ad or .h5 files) using scverse best practices with MAD-based filtering and comprehensive visualizations.
Idioma del texto original: inglés
Prevent Codex/Gemini adversarial review dispatch failures caused by relative prompt-file paths and background workdir drift.
Idioma del texto original: inglés
Prevent adversarial review dispatch failures caused by relative prompt paths, superseded background sessions, and stale completion notices when launching Codex/Gemini review jobs.
Idioma del texto original: inglés
Prevent stale plan/code review prompts from being sent to Codex/Gemini after the underlying artifact changed.
Idioma del texto original: inglés
Prevent approval-stage adversarial review churn by keeping plans implementation-focused, schema-complete, and free of stale review-process narration.
Idioma del texto original: inglés
Run an approval-stage adversarial cross-review sweep across multiple GitHub issues, drafting any missing canonical plan artifacts before dispatching Codex/Gemini reviews.
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
Recover adversarial plan reviews when providers keep reading stale remote/main content instead of the revised local artifact.
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
Handle Gemini adversarial-review runs that emit repeated 429 capacity errors before either recovering with a real verdict or failing unavailable.
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
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…
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
Assess a multi-machine, multi-repo AI-enabled workspace for readiness, provider allocation, and issue prioritization.
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
Class-level workflow for plan-review hardening, adversarial review reruns, artifact grounding, approval hygiene, and prompt/path drift recovery.
Idioma del texto original: inglés
Plan mode for Hermes — inspect context, write a markdown plan into the active workspace's `.hermes/plans/` directory, and do not execute the work.
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
Generate live issue-specific Codex prompts for a single terminal, with repo-aware path contracts and plan-gate safety checks.
Idioma del texto original: inglés
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.
Idioma del texto original: inglés
Use when executing implementation plans with independent tasks. Dispatches fresh delegate_task per task with two-stage review (spec compliance then code quality).
Idioma del texto original: inglés
Deprecated alias for gh-work-execution.
Idioma del texto original: inglés
Run cross-agent memory bridge. Sync learnings between machine agents, update shared knowledge. Phase 5 of #1760.
Idioma del texto original: inglés
Import a GSD-2 (.gsd/) project back to GSD v1 (.planning/) format
Idioma del texto original: inglés