app-creator
Orchestrate iOS/macOS app scaffolding and optional skill adoption for existing projects. Use when users want a guided wizard that can scaffold with XcodeGen and optionally install xcode-makefiles and simple-tasks.
simple-tasks
Install a fast local task workflow for single-project planning with `scripts/task.sh` (claim, done, status, reporting) backed by `tasks/TASKS.md` and optional `tasks/details/` notes. Use for lightweight in-progress task coordination, not full team issue tracking.
xcode-makefiles
Install strict Xcode Makefile tooling for iOS/macOS projects, including build/run/test scripts with AGENT_NAME-based per-agent isolation under build/. Use when a project needs reproducible local CLI builds without full app scaffolding.
doc-refresh
Refresh a repo's documentation for a live production system — audit stale docs, rebuild a focused doc set with diagrams, update AI-agent knowledge bases, and improve code-level docstrings
ragsharp-build-code-graph
|
ragsharp-mcp-code-graph
|
ragsharp-query-code-graph
|
ammon
What time is it for Ammon? Looks up the current time in Denmark (Europe/Copenhagen timezone) and reports it.
gen-image
Analyze content and generate illustrations via Gemini image API
gist-image
Use when you need to host images (screenshots, diagrams, PNGs) on GitHub for use in PR descriptions, issues, or markdown docs. Solves the problem that `gh gist create` rejects binary files.
architect-review
Run iterative architect review passes on a design spec, tracking convergence. Use when a spec is written and needs hardening before implementation — each pass finds fewer issues until the design stabilizes.
background-usage
Check Claude Code plan usage in a throwaway background session — a herdr workspace under herdr, otherwise a hidden detached tmux session. Reports weekly usage percentage, time until reset, and pacing status.
build-bd-static
Build a static `bd` binary when Homebrew is unavailable or its dynamically-linked package is not portable enough for the machine.
bulk
Bulk-parallel CLIs — turn N sequential gh/bd/git/file tool calls into a single fan-out JSON call. Use when the session is about to fire ≥3 similar sequential calls (gh pr view, bd show, Read of small files, up-to-date diagnose across repos).
clock
Schedule recurring tasks in your session. Defaults to time check every 15 min.
cost-impact
Compute a Claude Code cost-impact report across a time window, grouped by repo with per-session detail. Prices per-turn per-model at published list rates (Fable 5 / Opus 5 & 4.x / Sonnet 4.x-5 / Haiku), includes subagent tokens, outputs markdown with clickable PR links and collapsible per-repo sections. Use when user asks "how much did I spend on Claude this week", "cost report", "/cost-impact", or wants a weekly retrospective on Claude usage.
delegate-to-other-repo
Use when the user asks to make a change in a different git repo than the current session's cwd, and wants it done without polluting the current conversation with that repo's context. Typical triggers — "also fix X in the blog", "delegate this to the dotfiles repo", cross-repo tasks mentioned alongside current work.
docs
Use when answering questions about or writing code against a named third-party library/framework. Fetches fresh, authoritative documentation via Context7 (`ctx7`) instead of relying on stale training data. Fires both reactively ("how do I X with library Y") and proactively (about to write library code and unsure of current API). Skip for language stdlib and general CS concepts.
explainers
Build an interactive explainer — a standalone web page that teaches one concept by letting the reader play with it. Use when the user says "build an explainer for X", "help me understand Y interactively", or "make a page that demonstrates Z". Ships a minimum HTML scaffold + methodology guide with pointers to reference implementations (dolt-explainer, larry-voice-samples, monitor-explainer, activation-energy-game, religion-evolution-explorer, how-long-since-ai). Prefers GitHub Pages + plain HTML by default; graduates to Vite + TypeScript + React only when interaction genuinely requires it.
gen-stt
Transcribe audio to text locally via NVIDIA Parakeet TDT 0.6B ONNX — single clip or batch parallel, no API key
gen-tts
Synthesize speech audio via Gemini 3.1 Flash TTS — single clip, batch parallel, voice + style presets
harden-telegram
Diagnose and recover the two-process Telegram MCP chain — run the doctor, hot-redeploy server.ts, reload plugins without bouncing MCP, restart telegram_bot.py, and walk through known failure modes. Use when Telegram stops working mid-session, messages aren't arriving, or the bot is silent.
herdr
Drive herdr (the terminal agent multiplexer) headlessly — create workspaces, start/prompt/wait-on coding agents in panes, read their output, and keep the claude/codex integrations healthy. Use when asked to create herdr workspaces or sessions, run or babysit another agent in a pane, check why an agent's status looks wrong, or install/repair herdr agent integrations.
image-explore
Brainstorm multiple visual directions for a blog image, generate them in parallel, build a comparison page, and optionally publish as a shareable link (Surge.sh or gist).
image-read
Read (not generate) images via a subagent so the pixel payload stays out of the parent conversation. Dispatches Haiku by default, escalates to Sonnet/Opus when the caller flags ambiguity or needs load-bearing detail.
larry-voice
Speak text in Larry's voice via ElevenLabs → a Telegram voice note (opus/ogg). Use for any voice reply / ElevenLabs TTS. Charlie voice, eleven_flash_v2_5, IPv4-forced, optional blind-listen accent check.
learn-from-session
Extract durable lessons from a completed Claude session and codify them in the right CLAUDE.md files or skills. Use at the end of a long session, after a bug hunt that surfaced a non-obvious constraint, or when the user asks "what can we learn from this session". Discovers CLAUDE.md files dynamically, routes lessons by generic scope (project / shared conventions / environment / machine-local), enforces neutral voice, and asks for approval before editing.
machine-doctor
Diagnose and fix system health issues — rogue processes, Gas Town and Gas City runaway agents, resource exhaustion, stale dev servers, and orphaned git state — plus historical forensics ("who was hot at 7:16?") via the vendored machine_doctor.py recorder. Use when the machine is slow, unresponsive, or something feels wrong — now or earlier.
pr-hygiene
Surface open PRs that have genuinely unaddressed review feedback, filtering out CodeRabbit auto-summaries and CI-bot noise. Use before ending a session, when asked "which of my PRs need attention", or to gate a session close on unresolved review threads.
showboat
Create executable demo documents with screenshots using Showboat + Rodney. Use when the user wants to document an app, create a visual walkthrough, take screenshots of a deployed site, run an accessibility audit, or build self-verifying documentation.
up-to-date
Sync git repository with upstream. Use at the start of a session, when asked to sync, get up to date, check git status, or when working on a stale branch.
yolo
YOLO mode knowledge — what `--dangerously-skip-permissions` does and doesn't bypass, plus helpers to set up `additionalDirectories` correctly. Use when the user asks "why is Claude still prompting me in bypass mode," "set up YOLO," "skip all permissions," or reports unexpected permission prompts despite using `--dangerously-skip-permissions`.
whisper-lolo-audio-ingest
Build or modify the browser-side recording and upload pipeline for whisper-lolo. Use when implementing MediaRecorder + IndexedDB chunking, assembling audio blobs, or configuring Vercel Blob client uploads with progress and callbacks.
whisper-lolo-roadmap
Guide development of the whisper-lolo project based on specifications-projet.md. Use when planning or executing a sprint/PR, validating scope or constraints, or aligning architecture, statuses, and DoD for the Next.js + Vercel + Blob + Inngest + Whisper stack.
whisper-lolo-transcription-jobs
Implement or adjust background transcription jobs for whisper-lolo. Use when wiring Inngest events, handling long-running jobs, chunking before transcription, persisting transcripts, or maintaining the TranscriptionProvider abstraction.
exa-search
>
content-research-writer
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
scientific-slides
Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.
literature-review
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
zinc-database
Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.
zarr-python
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
venue-templates
Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
vaex
Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that don't fit in memory.
uspto-database
Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.
uniprot-database
Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For Python workflows with multiple databases, prefer bioservices (unified interface to 40+ services). Use this for direct HTTP/REST work or UniProt-specific control.
umap-learn
UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.
transformers
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
torchdrug
Graph-based drug discovery toolkit. Molecular property prediction (ADMET), protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis, GNNs (GIN, GAT, SchNet), 40+ datasets, for PyTorch-based ML on molecules, proteins, and biomedical graphs.
torch-geometric
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.
academic-chapter-writer
Comprehensive academic textbook chapter writing system for medical/scientific content. Use when the user wants to: (1) Write a full textbook chapter (5,000-15,000 words) on any medical/scientific topic, (2) Generate a detailed table of contents with section word counts, (3) Research topics via PubMed MCP and compile 20-30 references, (4) Write section-by-section with proper citations in Vancouver format, (5) Create publishable academic content with Eric Topol-inspired voice and authentic human prose, (6) Get approval at TOC stage before writing begins, (7) Export well-structured chapters for textbook publication.
Page 1196 of 1665 · 83215 results