AI & ML

hairyf Bundle

Aderyn — Rust-based Solidity static analyzer; CLI, config, detectors, report formats, and MCP tools for agents.

hairyf Bundle

Anchor framework for Solana programs — program structure, PDAs, CPI, IDL, errors, events, zero-copy, constraints, account types, and CLI for agent-driven tooling.

hairyf Bundle

Agent-oriented reference for the circom language and compiler—circuits, constraints, signals, templates, compilation, and safety.

barkleesanders Bundle

Stop hook that keeps the agent working until all plans and user requests are 100% complete. Fires when the agent tries to stop, re-examines the plan and task list, and forces continuation if anything is unfinished. Prevents premature stopping on multi-step tasks.

barkleesanders Bundle

Phased super-skill that turns a web app (improvebayarea.com or any Cloudflare Workers / SPA / PWA site) into a store-ready native iOS app with Capacitor — end to end. Use when the user wants to "make this an iOS app", "wrap the site", "ship improvebayarea to the App Store", add camera/geolocation/push to a web app, set up live web updates without App Store resubmission, build/run/test the app on the iOS Simulator, or asks how the web↔app update loop works. Detects the active phase and loads only that phase's reference file, the way /carmack loads only the relevant mode. Orchestrates the installed Capgo 48 capacitor-skills, awesome-ionic-mcp, XcodeBuildMCP + /xcode-test, /ios-ship (greenlight + privacy manifest), context7, sosumi, app-store-screenshots and aso-audit. Triggers: "capacitor", "wrap web app", "make it an iOS app", "ship to app store", "live updates / OTA", "Capgo".

jankneumann Bundle

Ingest raw session transcripts from coding-agent harnesses via vendor-specific adapters, normalize to a common event schema, triage for struggle signals, and write structured findings to episodic memory

jankneumann Bundle

Curates the right context for an agent at the right time. Loaded by orchestrator skills (plan-feature, implement-feature, validate-feature) when a worker is about to start a task and needs to decide which rules, specs, source files, errors, and conversation history to surface. Covers the 5-level context hierarchy, named packing strategies, and the most common failure modes (starvation, flooding, stale context, missing examples, implicit knowledge, silent confusion). Tied to this repo's coordinator, work-packages.yaml scope rules, worktree branching, and OPENSPEC_BRANCH_OVERRIDE handoff conventions.

jankneumann Bundle

HTTP fallback bridge for coordinator when MCP transport is unavailable

hairyf Bundle

Solana blockchain development — core concepts, clients, RPC, tokens, and payments for agent-driven tooling.

hairyf Bundle

Moralis — Web3 Data API, Streams, Auth API, and Cortex (AI/MCP) for EVM and Solana.

barkleesanders Bundle

Polish a generated CLI to pass verification and become publish-ready. Runs diagnostics (dogfood, verify, scorecard, go vet, gosec), automatically fixes all issues (verify failures, static-analysis findings, dead code, descriptions, README, MCP tool quality), reports the before/after delta, and offers to publish. Use after any /printing-press run, or on any CLI in $PRESS_LIBRARY/. Trigger phrases: "polish", "improve the CLI", "fix verify", "make it publish-ready", "clean up the CLI", "get this ready to ship".

barkleesanders Bundle

Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.

jankneumann Skill

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. This is an infrastructure skill loaded by other testing/debugging skills; it is not directly user-invocable. Trigger phrases (when called by another skill): "verify in the browser", "capture console errors", "screenshot the page", "profile Core Web Vitals", "inspect the DOM".

hairyf Bundle

Arbitrum Nitro L2 stack—architecture, ADRs, gas model, BOLD dispute protocol, and repo conventions.

hairyf Bundle

W3C DID Core specification—DID/DID URL syntax, data model, core properties, verification methods, services, representations, and DID methods.

nvidia-tao Bundle

DINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with denoising training, multi-scale features, and optional distillation support. Use when training, evaluating, exporting, distilling, quantizing, or running inference for a TAO DINO detector. Trigger phrases include "train DINO", "DETR object detection", "TAO 2D detection", "DINO with distillation".

nvidia-tao Bundle

Person re-identification (ReID). Learns discriminative embeddings to match the same person across different camera views, based on metric learning. Use when training, evaluating, exporting, or running inference for a TAO person re-identification model. Trigger phrases include "train ReID", "person re-identification", "cross-camera person matching", "ReID embeddings", "person re-id".

nvidia-tao Bundle

Co-DETR (CoDINO) for object detection. A DETR-family detector with collaborative hybrid assignment — auxiliary one-to-many heads supervise the encoder during training, giving strong closed-set accuracy at high inference cost. Use when training, evaluating, or running inference for a TAO Co-DETR model. Trigger phrases include "train Co-DETR", "run CoDINO", "codetr inference", "collaborative DETR", "autolabel detections with Co-DETR".

nvidia-tao Bundle

DINOv3 continual self-supervised pre-training. Domain-adapts public DINOv3 ViT backbones on unlabeled images via teacher-student self-distillation (DINO + iBOT + KoLeo, optional Gram anchoring) and converts the EMA teacher into a timm-format backbone for downstream tasks. Trigger phrases include "train DINOv3", "DINOv3 SSL", "domain-adapt a foundation backbone", "continual pretraining", "self-supervised finetune DINOv3".

nvidia-tao Bundle

OCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a differentiable binarization approach. Use when training, evaluating, exporting, pruning, quantizing, retraining, or running inference for a TAO OCDNet model. Trigger phrases include "train OCDNet", "scene text detection", "arbitrary-oriented text boxes", "differentiable binarization detector".

hairyf Bundle

The Graph — subgraph manifest, schema, mappings, GraphQL API, templates, Substreams, and performance practices for agent-driven indexing.

hairyf Bundle

Agent skill for java-tron — TRON Protocol Java implementation (FullNode, build, run, APIs, modular architecture, custom actuators).

nvidia-tao Bundle

OCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC and attention-based decoders. Use when training, evaluating, exporting, pruning, quantizing, retraining, or running inference for a TAO OCRNet model. Trigger phrases include "train OCRNet", "scene text recognition", "OCR cropped text", "CTC / attention text decoder".

nvidia-tao Bundle

RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with competitive accuracy and supports distillation and quantization for deployment optimization. Use when training, evaluating, distilling, quantizing, exporting, or running inference for a TAO RT-DETR model. Trigger phrases include "train RT-DETR", "real-time DETR", "low-latency object detection", "RT-DETR distillation / quantization".

nvidia-tao Bundle

CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment. Use when fine-tuning or training CLIP, running zero-shot classification, computing image embeddings, or deploying CLIP to ONNX/TensorRT. This is a single-action model skill; do not use it for an iterative weak-attribute improvement loop that keeps retraining and evaluating until progress stops, which belongs to tao-run-deft-pas.

nvidia-tao Bundle

NVDINOv2 for self-supervised visual representation learning. Trains vision transformers via self-distillation (teacher-student) without labels and produces general-purpose visual features. Use when training, exporting, or running inference for a TAO NVDINOv2 backbone. Trigger phrases include "train NVDINOv2", "self-supervised ViT pretraining", "DINOv2 backbone", "visual representation learning".

frumu-ai Skill

Profile and explore a dataset to understand its shape, quality, and patterns

fakhriaditiarahman Skill

Specialist in deploying, fine-tuning, and monitoring Large Language Models (LLMs). Expert in RAG pipelines, vector databases, prompt engineering, and maintaining robust AI infrastructure.

hairyf Bundle

Solana Kit (JavaScript SDK) — RPC, signers, transactions, accounts, codecs, instruction plans, and program clients for agent-driven Solana tooling.

hairyf Bundle

Agent-oriented skills for the Anchor framework—Solana program structure, accounts, CPI, IDL, clients, and tooling.

microsoft Bundle

Use this skill to run a four-panel adversarial advisory review on any pull request that touches the OpenAPM specification artifact (docs/src/content/docs/specs/openapm-*.md), its inline / sidecar JSON Schemas (docs/src/content/docs/specs/schemas/*.schema.json), or the conformance fixture seed (tests/fixtures/spec-conformance/**). The panel fans out to four spec-ecosystem reviewers (swagger-openapi-editor, oci-distribution-editor, pkgmgr-registry-contract-editor, w3c-tag-architect), each running in its own agent thread, and a spec-editor synthesizer that produces a fold-now / defer-v0.1.1 / defer-v0.2 / reject list plus a ship decision keyed off a 1..10 shocked_meter scale. The orchestrator is the sole writer to the PR: ONE consolidated comment, no verdict labels, no merge gating. The panel is advisory -- it surfaces findings, prioritizes folds, and renders a ship recommendation that the maintainer weighs.

microsoft Bundle

Use this skill to run a holistic regrounding pass on the entire microsoft/apm documentation corpus against current source code, page-by-page, and emit surgical fixes for stale claims. Activate when the maintainer wants a WHOLE-CORPUS audit (not per-PR review) -- typical triggers include "audit the docs", "reground the corpus", "check every page against code", "pre-release docs sweep", "the docs have drifted everywhere", or "we just reshaped the TOC, find dead links". Wave-batched and S7-verified; scales to the full ~112-page corpus in ~10 minutes wall-time. This is a SIBLING to docs-sync, not a replacement: docs-sync is per-PR (triggered by a diff); this skill is per-corpus (triggered by a maintainer ask). They share agent personas, schemas, and the docs index, but their triggers MUST NOT collide. Does NOT auto-merge, does NOT push without maintainer review, and does NOT replace per-PR drift detection.

microsoft Bundle

Use this skill to write the PR description (PR body) for any pull request opened against microsoft/apm. Produces one self-sufficient GitHub-Flavored Markdown artifact: TL;DR, Problem (WHY), Approach (WHAT), Implementation (HOW), 1-3 validated mermaid diagrams, explicit trade-offs, validation evidence, and a How-to-test section -- with every WHY-claim backed by a verbatim quote from PROSE or Agent Skills. Activate when the user asks to "write a PR description", "draft a PR body", "open a PR", "fill in the PR template", or any equivalent.

hairyf Bundle

Agent skills for WalletConnect v2—Sign Client, sessions, namespaces, Universal Provider, Ethereum Provider, security and debugging.

lifecycle-innovations-limited Bundle

OPS on-demand: This skill should be used when the user asks to "MCP down", "reconnect MCP", or…

frumu-ai Skill

Manages connected MCP sources for Tandem search. Detects available sources, guides users to connect new ones, handles source priority ordering, and manages rate limiting awareness.