Menu
SkillsMP has collected 495 skills from Kayforkind/skill-slice. Open a skill to review its source and details.
Showing 40 of 495 collected skills.
Open a creative mind on the current context and invent a leap the user did not know to ask for — a feature, protocol, CLI, demo, architecture, product move, prose, experiment, or visual. Use when they run /awe-me or /inspire-me, say “awe me” or “inspire me”,…
Design, power, run, and analyze statistically valid A/B/N product experiments (sample size, duration, SRM, sequential monitoring, multiple comparisons). Use when pre-registering a test or reading out a controlled split. Not for event instrumentation, funnel…
Runs Astropy BoxLeastSquares (BLS) on photometric time series: autopower/power grids, depth SNR, odd/even vetting. Use for periodic box-shaped transit dips or eclipsing binaries (Kovács 2002). Not for Transit Least Squares limb-darkened templates,…
Implements Erlang/OTP behaviors: gen_server, gen_statem, supervisor, and gen_event with typed callbacks and child_spec helpers. Use when writing OTP processes, supervision trees, or replacing raw spawn/receive. Not for Elixir GenServer/Phoenix, deprecated…
Extracts locational marginal prices (LMPs) as DC-OPF nodal-balance duals (CVXPY + CLARABEL/OSQP), plus reserve MCP. Use for nodal electricity prices, congestion, or transmission counterfactuals. Not for AC-OPF (voltage/Q), unsolved duals, inventory EOQ…
Models Google OR-Tools 9.9+ pickup-and-delivery (PDPTW, dial-a-ride, courier): AddPickupAndDelivery plus same-vehicle and precedence constraints. Use when each job is a coupled pickup/dropoff pair. Not for single-stop VRP, MIP subtour cuts…
Queries PubChem via PUG-REST or PubChemPy: name/CID/SMILES/InChI search, properties, similarity/substructure, bioactivity. Use for public compound lookups. Not for proprietary chemistry (use local RDKit), biomacromolecules (PDB), quantum jobs (Gaussian/ORCA),…
Operates Weaviate Cloud or self-hosted collections with weaviate-client v4: list/create, import, semantic/hybrid/keyword search, Query Agent. Use when the user names Weaviate. Not for local Chroma (chroma), Pinecone serverless (pinecone), or FAISS-only kNN.…
Runs local GGUF inference with llama.cpp (llama-cli, llama-server, optional llama-cpp-python) on CPU, Metal, CUDA, ROCm, or Intel GPU, including Hugging Face -hf Hub downloads. Use when the user wants llama.cpp, GGUF files, llama-cli, or llama-server. Not for…
Use when generating, building, creating, designing, or repairing ComfyUI API-format workflow JSON from a natural-language description (txt2img, img2img, inpainting, ControlNet, LoRA stacking, upscaling, face detailing, FLUX, Wan I2V). Load when the user asks…
Audits a folder of SVGs for XML integrity, executable-script risk, and visual quality via Chrome headless render plus a free vision-language model. Use when asked to analyze, check, or audit SVG quality, or before shipping a generated SVG batch. Not for…
Runs full-cycle research: scope, multi-source collection, source evaluation, claim triangulation, contradiction resolution, and cited deliverables. Use when the user asks for research, deep research, investigate, literature review, competitive analysis,…
Authors in-repo hermes-agent SKILL.md files: frontmatter validator rules, peer-matched metadata, writing quality, and git placement under the package skills tree. Use when adding or reviewing a skill that ships with hermes-agent. Not for user-local…
Drives Node's V8 inspector from the terminal: node inspect / --inspect-brk, ndb, or chrome-remote-interface for breakpoints, scopes, watches, and CPU/heap. Use when console.log cannot reach closure state or a Node test/TUI worker needs step-through. Not for…
Debugs Python with breakpoint()/pdb, python -m pdb, pytest --pdb, and debugpy DAP attach to long-lived processes. Use when a test value is wrong, a daemon misbehaves, or step-through inspection is required. Not for print/logging or pytest --showlocals that…
Drives 1Password CLI (op) for service-account, desktop-app, or Connect auth, then op read, op inject, and op run so secrets stay out of plaintext env files. Use when installing op, signing in, resolving op:// references, injecting templates, or wrapping…
Runs on-device semantic plus keyword search and Swanson-ABC connection-discovery over the user's Apple Notes via the apple-notes MCP. Use when finding, recalling, synthesizing, or bridging notes on macOS. Not for Obsidian, SiYuan, Notion, or Apple Reminders.
Quality upgrade pass on the current deliverable: scorecard, improve, review, verify with fresh evidence. Use when the user runs /better, /better deep, /better ship, /better <focus>, or asks to polish, harden, upgrade quality, or review-and-verify without…
Rewrites any input as a hyphen-only hierarchical bullet tree (lite, full, or ultra) with 2-space nesting and no prose bridges. Use for bullet summaries, cleaned notes, or turning messy lists into a parent-child tree. Never apply this format to stories,…
Delegates coding tasks to Anthropic Claude Code CLI (claude, claude -p, claude auth, tmux REPL) for autonomous edits, PRs, JSON print-mode, and CI. Use when invoking Claude Code from a shell. Not for Cursor-native agents, Codex/OpenCode CLIs, or using Claude…
Designs one-off local HTML artifacts — landing pages, decks, prototypes, component labs, motion studies — for CLI/API agents that lack hosted Claude Design. Use when the user wants a designed artifact with process and taste. Not for DESIGN.md token specs…
Installs, launches, and runs ComfyUI locally or on Comfy Cloud: comfy-cli lifecycle, custom nodes/models, REST/WebSocket prompt submit with parameter injection. Use when generating images, video, or audio via ComfyUI, SDXL, Flux, Wan, Hunyuan, ControlNet, or…
Builds and reviews React/Next.js/Tailwind interfaces under anti-generic taste: calibrated color, asymmetric layout, typography, motion, and loading/empty/error states. Use when creating or reviewing dashboards, heroes, landing pages, or feature sections that…
Runs a phased hard-bug workflow: invent a fast deterministic red-capable loop, minimise the repro, rank 3-5 falsifiable hypotheses, probe one variable, then land a seam-correct regression. Trigger on diagnose requests, stubborn flakes, throws, or performance…
Manages Docker Engine lifecycle: containers, images, volumes, networks, Compose stacks, logs/exec, prune, and Dockerfile layer review. Use when the user asks about docker run, compose up/down, container logs, image builds, or docker system df. Not for…
Classifies and repairs Drizzle Kit clashes in _journal.json, snapshots, and generated SQL after pull, merge, or rebase, including non-commutative drizzle-kit check failures. Use when migration artifacts conflict or a team needs regenerate-from-merged-schema…
Runs keyless DuckDuckGo search (text, news, images, videos) via the ddgs CLI or a verified Python DDGS import. Use when built-in web_search is unavailable, FIRECRAWL_API_KEY is unset, or DDG results are requested. Not for full-page extraction, arXiv lookup…
Applies Emil Kowalski design-engineering motion: custom cubic-bezier ease-out, origin-aware popovers, interruptible CSS transitions, clip-path reveals, spring gestures, and GPU-only transform/opacity. Trigger on UI polish, Framer Motion, drawers, toasts,…
Converts syllabi, past papers, or notes into an Easy-to-Medium-to-Hard High Score Roadmap plus flashcards, predicted papers, and readiness checks. Use when students ask for exam prep, revision plans, question prediction, or mock papers. Not for sitting a live…
Composes TypeScript async pipelines with fp-ts TaskEither: TE.tryCatch, chain vs map, Do/bind, sequenceT parallelism, orElse/retry, and typed API/DB/file errors. Use when wrapping Promises, replacing nested try/catch, or building TaskEither clients in fp-ts.…
Encodes TypeScript failures as fp-ts Either and TaskEither values: tryCatch at throw boundaries, chain and chainW pipelines, applicative field validation, and async orElse fallbacks. Use when callers need failure in the type, multi-field validation, or…
Adds a portable Lighthouse CI gate: lighthouserc.cjs Core Web Vitals budgets (LCP, CLS, TBT), category floors, median-of-N runs, and GitHub Actions artifacts against the production build. Use when adding performance gates, setting CWV budgets, or debugging…
Maps a failed GitHub Actions run onto the matching `.github/workflows` job and step, then emits a unified YAML diff for secrets env maps, deprecated action majors, runner/runtime skew, cache keys, flaky timeouts, or permissions. Use when CI is red, a step…
Outcome contract then autonomous loop. Use when the user runs /goal, /goal-loop, “capture goal”, “GOAL.md”, “until done”, or the work spans many files/steps and success must be falsifiable. Writes GOAL.md before wandering. /goal-loop is a mode of this skill…
Forces a written function contract, loop invariant, termination argument, and edge-case table before emitting loops or recursion (Boyer-Moore, leftmost binary search, QuickSelect traps). Use when writing or reviewing algorithms whose obvious implementation is…
Writes jq filters to query, reshape, aggregate, and pipeline JSON from APIs, CLIs, and logs. Use when parsing JSON, building jq one-liners, or explaining a jq expression. Not for in-memory DataFrames (pandas/polars), JSON Schema validation, or JavaScript…
Fixes Next.js App Router indexing issues: canonical and generateMetadata, noindex leaks, sitemap/robots routes, static rendering, internal linking, and Search Console coverage. Use when a Next.js site wastes crawl budget or shows discovered-not-indexed URLs.…
Stands up and repairs a Windows local Ollama server so models on a custom disk appear on localhost:11434 (/api/tags and /v1/models) and GPU KV-cache is not starved. Use when ollama list is empty, models vanish after reboot, port 11434 conflicts, or throughput…
Delegates coding tasks to the OpenHands CLI in headless JSON mode over any LiteLLM provider. Use when the user requests OpenHands, a vendor-unlocked coding agent, or multi-step file-plus-shell work on OpenRouter, Ollama, or vLLM. Not for Claude-native…
Searches Semantic Scholar and arXiv via the bundled papers.py CLI: metadata, citation/reference graphs, arXiv PDF download, and PyMuPDF text extract. Use when finding papers, analyzing citations, building reading lists, or summarizing arXiv preprints. Not for…