Recently Added
Fresh skills just added to the collection. Be the first to try them out!
meeting-action-items
by magnusthovsland
"Turn meeting notes into cited decisions, owners, tickets."
docx
by magnusthovsland
Create, read, edit, template, and review Word .docx files.
document-to-action-items
by magnusthovsland
"Extract cited obligations, deadlines, tasks from documents."
communication-platform-integrations
by magnusthovsland
"Umbrella workflow for communication and social platform integrations: terminal email, X/Twitter via xurl, and Yuanbao group/DM interaction."
box
by magnusthovsland
Box manages cloud files, sharing, search, and metadata.
mlops-model-operations
by magnusthovsland
"Class-level umbrella for ML/LLM model operations: Hub assets, local/served inference, evaluation, experiment tracking, model surgery, and model-specific generation/vision workflows."
babysit-prs
by AlexanderMattTurner
How to sit on a set of already-open PRs and drive them to landed — building the watch set, reading GitHub's mergeability and queue state correctly, re-arming auto-merge, dispatching fixes for reds, and deciding which wake-ups deserve a reply. Activate when asked to "babysit", "watch", "monitor", "sit on", "keep an eye on", "drive to green", "land" or "merge" one or more open PRs (a named stack included), when asked to re-enable auto-merge on PRs that lost it, when a PR sits in a state you cannot explain (unknown mergeability, auto-merge silently off, a required check that never reports), or when a wake-up arrives from a PR you are already watching. The load-bearing rule is that babysitting lands PRs through the auto-merge path — a direct merge is reserved for a narrow, reproduced fix for a red on main.
evaluating-llms-harness
by magnusthovsland
"lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.)."
audiocraft-audio-generation
by magnusthovsland
"AudioCraft: MusicGen text-to-music, AudioGen text-to-sound."
petdex
by magnusthovsland
Install and select animated petdex mascots for Hermes.
document-productivity-workflows
by magnusthovsland
"Umbrella workflow for document-centric productivity: OCR/extraction, PDF edits, PowerPoint decks, and office file manipulation."
explore-plan
by AlexanderMattTurner
Drives the Explore -> Plan -> Critique -> Review -> Verify discipline for a written plan. Activate on entry to plan mode, before writing the plan — including the plan-mode requests "plan this", "scope this out", "figure out how to do X", "explore the codebase first" — in auto mode at the start of any non-trivial task, where no plan gate fires — and in any other mode when the task obviously needs a plan (several files, an unfamiliar subsystem, more than one PR), invoked informally without entering plan mode. A trivial edit (typo, single-line change) activates nothing, in any mode. Enforces a self-critiqued written plan, convergent setup work started in the background while design questions settle, and real verification instead of trusting a success claim.
defect-to-guard
by AlexanderMattTurner
Turn a defect class into a well-designed guard PROPOSAL (and, once a human promotes it, a well-built guard). Activate when writing a ## Proposed guards entry after fixing a bug, and when a human has explicitly approved implementing a lint, pre-commit hook, CI check, assertion, or ratchet — never to ship a guard inside a fix PR. Covers naming the defect CLASS rather than the instance, checking whether an existing guard should have fired (a gap in it is itself a bug), preferring a check that iterates the SSOT over a per-case assertion, naming the guard's HOME (this repo, or the shared ci-truth-serum pack) and what belongs in each, the inert-feature class that only a behavior-driving smoke test can catch, writing a repo-local checks/*.py line lint and dogfooding it against the real tree before shipping, the WATCHED-SURFACE question (when this goes red, who actually sees it?), the vacuous-green failure mode, and why mutation testing runs on CI and never locally.
hosted-model-cost-evaluation
by magnusthovsland
"Use when comparing hosted LLM costs, limits, or quotas."
media-content-workflows
by magnusthovsland
"Umbrella workflow for media tasks: YouTube transcript reuse, GIF search/download, audio analysis, songwriting prompts, and AI music generation."
advertising-platform-operations
by magnusthovsland
"Use for paid-ad campaign changes through platform APIs."
github-workflows
by magnusthovsland
"Class-level umbrella for GitHub work: auth, repositories, issues, pull requests, CI monitoring, and code review using gh, git, and REST fallbacks."
email-inbox-triage
by magnusthovsland
"Triage an inbox: prioritize threads, draft replies safely."
sdlc-review
by magnusthovsland
Review Kanban handoffs and route verified outcomes.
data-science-workflows
by magnusthovsland
"Class-level umbrella for data-science workflows: iterative Python/Jupyter exploration, notebook-backed REPL sessions, dataframe/API inspection, and clean verification of computational notebooks."
creative-visual-artifacts
by magnusthovsland
"Umbrella workflow for visual creative deliverables: HTML/SVG mockups, diagrams, infographics, ASCII art, p5.js/pretext demos, and design-system-inspired artifacts."
hermes-agent
by magnusthovsland
"Configure, extend, or contribute to Hermes Agent."
computer-use
by magnusthovsland
"Drive the desktop background-first; escalate on signal."
autonomous-coding-agent-clis
by magnusthovsland
"Class-level umbrella for orchestrating external autonomous coding CLIs such as Claude Code, Codex, and OpenCode from Hermes terminal/process tools."