Claude Skills by vamseeachanta

Deep reconnaissance of an engineering solver domain (OrcaWave, OrcaFlex, CalculiX, OpenFOAM, etc.) across a multi-repo ecosystem — map infrastructure, issues, skills, data artifacts, machine constraints, and solver queue state before planning work.

Clone and analyze an external open-source repo (best practices, frameworks,

Set up GitHub authentication for the agent using git (universally available) or the gh CLI. Covers HTTPS tokens, SSH keys, credential helpers, and gh auth — with a detection flow to pick the right method automatically.

Prevent shell-quoting and command-substitution bugs when posting GitHub issue/PR comments or editing bodies with gh CLI.

Lock down public GitHub repositories so only collaborators can interact with issues, PRs, comments, discussions, and other user-generated surfaces using repository interaction limits; includes expiry verification and renewal handling.

Use when building GitHub issue classifiers, dashboards, closeout verifiers, or queue/report automation that depends on comments, approval evidence, or linked PR handoff state.

Close GitHub issues without losing the evidence comment when multiple agents or races may close the issue concurrently.

Safely turn drafted issue bodies into reusable gh issue create commands by auditing repo labels, exact duplicates, and auth first.

Prevent GitHub issue creation failures by auditing exact label existence, duplicate titles, and partial-create risk before calling gh issue create.

Class-level GitHub issue lifecycle operations: issue creation, planning/execution routing, labels, evidence fields, roadmap anchors, closeout races, and visual planning.

Create, manage, triage, and close GitHub issues. Search existing issues, add labels, assign people, and link to PRs. Works with gh CLI or falls back to git + GitHub REST API via curl.

Full pull request lifecycle — create branches, commit changes, open PRs, monitor CI status, auto-fix failures, and merge. Works with gh CLI or falls back to git + GitHub REST API via curl.

Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.

Reuse and reopen existing roadmap/epic GitHub issues instead of fragmenting work across duplicate replacement epics; retarget children and link active issues for continuity.

Create review-friendly GitHub planning issues that supersede stale/seasonal issues and include source-backed image thumbnails for faster human review.

Triage and rank GitHub issues across a workspace-hub style multi-repo ecosystem using machine-readiness, provider-utilization, and leverage scoring.

Scan a Python repo's package structure, count classes/functions, classify module maturity (PRODUCTION/DEVELOPMENT/SKELETON/GAP), and generate architecture reports with Mermaid diagrams. Use when asked to analyze codebase structure, find untested packages, or assess module maturity.

Review external LinkedIn posts and fold reusable insights into ACE-style

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.

Search and download GIFs from Tenor using curl. No dependencies beyond curl and jq. Useful for finding reaction GIFs, creating visual content, and sending GIFs in chat.

Spotify: play, search, queue, manage playlists and devices.

Fetch YouTube video transcripts and transform them into structured content (chapters, summaries, threads, blog posts). Use when the user shares a YouTube URL or video link, asks to summarize a video, requests a transcript, or wants to extract and reformat content from any YouTube video.

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

Self-hosted no-code automation platform with visual flow builder, type-safe

Python DAG workflow orchestration using Apache Airflow for data pipelines,

Patterns for creating, testing, debugging, and maintaining cron-driven

CI/CD automation and workflow orchestration using GitHub Actions for

Open-source workflow automation platform with visual node-based editor,

Developer-first workflow engine that turns scripts into workflows and

"Cross-platform hardware assessment and system maintenance \u2014 assess\

Diagnose local machine slowness and apply CPU/IO/governor tuning. Use when work feels slow on ace-linux-1 / ace-linux-2 — Hermes lagging, git operations taking minutes, builds dragging, Codex feeling sluggish. Runs perf-bench.sh, identifies the dominant bottleneck (CPU governor, filesystem driver, NUMA, memory pressure, I/O contention), and applies fixes from the perf-tuning runbook.

Assess and report on AI tool subscriptions, usage patterns, and cost-effectiveness.

Create and manage long-running background processes with start/stop/status

Essential CLI tools and shell productivity patterns for efficient terminal

Complete Docker containerization patterns with multi-stage builds for

Advanced git workflows including rebase, worktrees, bisect, hooks, and

macOS launcher automation with Raycast extensions (TypeScript/React)

VS Code productivity optimization with essential extensions, settings

Airtable REST API via curl. Records CRUD, filters, upserts.

Gmail, Calendar, Drive, Contacts, Sheets, and Docs integration via Python. Uses OAuth2 with automatic token refresh. No external binaries needed — runs entirely with Google's Python client libraries in the Hermes venv.

Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.

Notion API for creating and managing pages, databases, and blocks via curl. Search, create, update, and query Notion workspaces directly from the terminal.

Extract text from PDFs and scanned documents. Use web_extract for remote URLs, pymupdf for local text-based PDFs, marker-pdf for OCR/scanned docs. For DOCX use python-docx, for PPTX see the powerpoint skill.

Jailbreak API-served LLMs using G0DM0D3 techniques — Parseltongue input obfuscation (33 techniques), GODMODE CLASSIC system prompt templates, ULTRAPLINIAN multi-model racing, encoding escalation, and Hermes-native prefill/system prompt integration. Use when a user wants to bypass safety filters, jailbreak a model, or red-team model robustness.

Scan job boards to identify consulting opportunities by matching hiring demand to a practitioner's capabilities. Build a GTM outreach campaign from job postings. Reusable scanner at scripts/gtm/job-market-scanner.py.

Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency.

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 citation verification workflows.