skill-retrieval-mcp

Delegate coding tasks to the OpenAI Codex CLI agent for implementation, refactoring, PR review, batch issue fixing, and autonomous repository work.

Configure, troubleshoot, and extend Hermes Agent itself: CLI setup, config, tools, skills, gateway, providers, plugins, MCP, cron, memory, and agent development.

Codex built-in skill for structural code search with ast-grep when queries depend on AST shapes, call patterns, decorators, scopes, or required child nodes.

Codex curated GitHub skill for general GitHub app workflows: repository metadata, issues, pull requests, comments, and connector-backed context.

Codex curated Hugging Face skill for preparing, running, and packaging community evaluation tasks and benchmark submissions.

Codex curated GitHub skill for addressing pull request review comments, resolving threads, applying requested changes, and reporting verification.

Codex curated GitHub skill for debugging and fixing failing GitHub Actions checks on pull requests with gh logs and focused patches.

Codex curated Hugging Face skill for building, debugging, and deploying Gradio demos and Spaces interfaces.

Codex curated Hugging Face skill for the Hub `hf` CLI: authentication checks, repository management, uploads, downloads, and metadata inspection.

Codex curated Hugging Face skill for Dataset Viewer API workflows: splits, first rows, paginated rows, search, filters, parquet URLs, size, and statistics.

Codex curated Hugging Face skill for managing Hugging Face Jobs, scheduled runs, job logs, hardware choices, and remote execution.

Codex curated Hugging Face skill for using Hugging Face paper pages, paper collections, related model/dataset links, and research discovery workflows.

Codex .system built-in skill for generating or editing raster bitmap images such as photos, illustrations, textures, sprites, mockups, transparent cutouts, or project visual assets.

Codex curated Hugging Face skill for training or fine-tuning language models with datasets, tokenizers, trainers, LoRA, metrics, and Hub checkpoints.

Codex built-in skill for lightweight NVIDIA GPU diagnostics and local CUDA visibility checks before running GPU-heavy experiments or benchmarks.

Codex .system built-in skill for current OpenAI product and API documentation, model selection, prompt upgrades, API migration, and official-doc citations.

Codex curated Hugging Face skill for publishing paper artifacts, model cards, datasets, Spaces, and Hub collections around a research release.

Codex built-in skill for reading, creating, or reviewing PDF files where rendering, page layout, typography, and visual fidelity matter.

Codex .system built-in skill for creating and scaffolding Codex plugin directories with .codex-plugin/plugin.json, optional skills, hooks, scripts, assets, MCP, apps, and marketplace entries.

Codex built-in skill for budgeted ripgrep-style repository search that avoids huge terminal output by narrowing files and bounded hit windows.

Codex .system built-in skill for creating or updating effective Codex skills with concise frontmatter, clear trigger descriptions, bundled resources, and validation guidance.

Codex .system built-in skill for installing Codex skills into CODEX_HOME/skills from curated OpenAI skills or GitHub repository paths, including private repos when credentials exist.

Codex plugin skill for inspecting structured artifacts, generated reports, JSON/HTML outputs, and viewer-backed evidence without losing provenance.

Codex curated Hugging Face skill for experiment tracking with Trackio logs, metrics, dashboards, and run comparisons.

Codex curated Hugging Face skill for Transformers.js browser or Node inference, model conversion constraints, pipelines, and web deployment.

Codex curated Hugging Face skill for training or fine-tuning vision models with image datasets, transforms, metrics, checkpoints, and Hub integration.

Codex curated GitHub skill for publishing local changes by confirming scope, staging, committing, pushing a branch, and opening a draft pull request.

Rewrite text to sound natural, specific, and human while removing AI-isms, generic filler, corporate tone, and robotic phrasing.

Consolidate multiple CSV spreadsheets into a normalized taxonomy with deduplication, column mapping, hierarchy alignment, and audit reports.

Set up, repair, and verify GitHub authentication with gh auth login, git credential helpers, SSH keys, and token scopes.

Review existing GitHub pull requests, patches, or git diffs for correctness, security, maintainability, and test coverage findings.

Search, create, triage, label, assign, comment on, and close GitHub issues without changing repository code.

Create branches, commit changes, push updates, open GitHub pull requests, update PR metadata, and monitor CI checks.

Clone, create, fork, configure, archive, transfer, release, and manage GitHub repositories, remotes, visibility, and settings.

Clip URLs, PDFs, arXiv pages, WeChat articles, and technical blog posts into llm-wiki raw notes with localized images and source metadata.

Maintain a layered LLM wiki and research note base with canonical raw notes, indexes, wikilinks, images, scoped verification, and deep organization passes.

Read, search, create, and update notes in an Obsidian vault, including backlinks, frontmatter, daily notes, and wikilinks.

Process Microsoft Teams meeting transcripts, recordings, speaker turns, summaries, action items, and follow-up notes through a local pipeline.

Search arXiv, retrieve arXiv paper metadata, resolve arXiv IDs, download PDFs, and inspect abstracts or categories.

Monitor blogs, RSS feeds, Atom feeds, newsletters, and release-note pages for new posts and summarize changes.