Top Agent Skills

Create, name, scope, assign, and close GitHub milestones. Use when adding a milestone, deciding whether work belongs in one, or naming the next one. One axis per project (release / date / theme); never as labels.

Create a README.md file for the project

Triage and resolve Arch Linux issues with pacman, systemd, and rolling-release best practices.

Refactor given method `${input:methodName}` to reduce its cognitive complexity to `${input:complexityThreshold}` or below, by extracting helper methods.

This skill guides the simultaneous measurement of serum and urine osmolarity to evaluate polyuria for central diabetes insipidus. It is triggered when a patient presents with polyuria exceeding 50 mL/kg/24 hours or 3.5 L/day in a 70‑kg individual.

This skill guides clinicians to assess whether a patient has achieved ≥5% weight loss at 3 months while on a weight‑loss medication and to determine continuation versus discontinuation based on efficacy and safety. It is triggered when a clinician asks, 'Has this patient lost enough weight at 3 months to continue lorcaserin?' or 'Should I stop phentermine/topiramate because the patient lost only 3% of body weight?'.

Determines levothyroxine dosing for central hypothyroidism to achieve serum free T4 in the mid to upper half of the reference range. Triggers include confirmed central hypothyroidism requiring thyroid hormone replacement when initiating L‑4 therapy.

Determines if primary aldosteronism is confirmed based on upright plasma aldosterone ≤6 ng/dL (170 nmol/L) on day 4 at 10 AM of fludrocortisone suppression test, provided plasma renin activity ≥1 ng/mL/h and plasma cortisol concentration lower than the 7 AM value to exclude ACTH confounding. Use when reviewing FST results to diagnose PA; triggers include "FST", "upright aldosterone ≤6 ng/dL", "PRA ≥1 ng/mL/h", and "cortisol drop".

Step-by-step meal planning for a patient with obesity — from diet recall to calorie prescription to macronutrient targets. Use when a clinician asks "how do I plan a diet for my obese patient", "what calorie target for weight loss", "how many calories should I prescribe", "meal plan for obesity", "diet plan for overweight patient", or needs to build an individualised dietary prescription at the clinic.

Suggests a 3- to 6‑month trial of testosterone dosing to achieve a mid‑normal premenopausal value in a reference assay for postmenopausal women with properly diagnosed HSDD and no contraindications. Triggered when a postmenopausal woman requests therapy for low sexual desire after appropriate HSDD workup and exclusion of contraindications.

Helps distinguish unilateral from bilateral adrenal disease based on 18-oxocortisol levels, which are typically higher in aldosterone-producing adenoma than idiopathic adrenal hyperplasia. Use when evaluating 18-oxocortisol results during PA workup to guide subtype classification after a positive ARR.

Recommends using the lowest tolerable hydrocortisone dose to potentially decrease risks of metabolic and cardiovascular disease in central adrenal insufficiency. Triggers include managing a patient with central adrenal insufficiency requiring glucocorticoid replacement.

Recommends using NSAIDs or DMARDs instead of glucocorticoids for chronic inflammatory disease (e.g., rheumatoid arthritis) to limit weight gain. Triggered when clinicians ask, “What anti‑inflammatory should I choose for this RA patient to avoid weight gain?” or “Should I avoid steroids in this obese patient with RA?”

ATA RAI Remnant Ablation / Adjuvant Therapy Decision Tool

Determines if PAC/PRA ratio and PAC levels indicate positive or provisionally positive screening for primary aldosteronism. Triggered when a clinician has PAC and PRA results and asks “Is this screening test positive for PA?” or needs to interpret borderline results.

Recommend continuing glucocorticoid replacement until hypothalamic-pituitary-adrenal (HPA) axis recovery after surgical resection of ACTH-secreting pituitary tumors. Use when managing postoperative patients following ACTH-secreting tumor surgery to prevent adrenal insufficiency during HPA axis recovery.

Teaches AI patients about stress-dosing and emergency glucocorticoid administration; instructs to obtain emergency card/bracelet/necklace and kit with injectable high-dose GC. Triggers when counseling any patient with adrenal insufficiency (e.g., "Use when counseling patient with adrenal insufficiency...").

Identifies patients with adrenal tumors on CT who should undergo dexamethasone suppression test to evaluate for autonomous cortisol co-secretion. Triggers include when a clinician finds an adrenal tumor on CT and asks 'Should I test for cortisol co-secretion?' or is planning AVS for a tumor >3.0 cm.

We need to output a SKILL.md file with the specified format.

Establishes age- and gender-specific blood pressure goals for pediatric patients with primary aldosteronism (PA) using published normative data to assess treatment adequacy and avoid over-treatment. Use when managing hypertension in children with PA to evaluate if BP is adequately controlled; triggers include pediatric PA hypertension, BP not normalized with glucocorticoid therapy, and need for age‑specific BP targets.

Assess bariatric surgery eligibility based on BMI/comorbidity

Avoid specific tests for TSHD diagnosis

Administers 100-mg hydrocortisone IV bolus followed by continuous IV infusion of 200 mg HC per 24 hours (alternatively 50 mg IV every 6 hours) for patients undergoing major surgical stress. Use when managing patient with major surgical stress; triggers include patient undergoing major surgery.

Identifies patients with normokalemia and no adrenal tumors on CT who likely have bilateral PA and may proceed directly to medical therapy without AVS. Triggers include when a clinician notes normokalemia and clean adrenal CT and asks 'Is AVS necessary if I suspect bilateral disease?'

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI’s video API using the bundled CLI (`scripts/sora.py`), including requests like “generate AI video,” “Sora,” “video remix,” “download video/thumbnail/spritesheet,” and batch video generation; requires `OPENAI_API_KEY` and Sora API access.

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.

Comprehensive guide for Manim Community - Python framework for creating mathematical animations and educational videos with programmatic control

Quantum mechanics simulations and analysis using QuTiP (Quantum Toolbox in Python). Use when working with quantum systems including: (1) quantum states (kets, bras, density matrices), (2) quantum operators and gates, (3) time evolution and dynamics (Schrödinger, master equations, Monte Carlo), (4) open quantum systems with dissipation, (5) quantum measurements and entanglement, (6) visualization (Bloch sphere, Wigner functions), (7) steady states and correlation functions, or (8) advanced methods (Floquet theory, HEOM, stochastic solvers). Handles both closed and open quantum systems across various domains including quantum optics, quantum computing, and condensed matter physics.

Send WhatsApp messages to other people or search/sync WhatsApp history via the wacli CLI (not for normal user chats).

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents.

This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.

Notion API for creating and managing pages, databases, and blocks.

Comprehensive quantum computing toolkit for building, optimizing, and executing quantum circuits. Use when working with quantum algorithms, simulations, or quantum hardware including (1) Building quantum circuits with gates and measurements, (2) Running quantum algorithms (VQE, QAOA, Grover), (3) Transpiling/optimizing circuits for hardware, (4) Executing on IBM Quantum or other providers, (5) Quantum chemistry and materials science, (6) Quantum machine learning, (7) Visualizing circuits and results, or (8) Any quantum computing development task.

Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experimental validation including binding assays, expression testing, thermostability measurements, enzyme activity assays, or protein sequence optimization. Also use for submitting experiments via API, tracking experiment status, downloading results, optimizing protein sequences for better expression using computational tools (NetSolP, SoluProt, SolubleMPNN, ESM), or managing protein design workflows with wet-lab validation.

Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.

Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.

Mass spectrometry analysis. Process mzML/MGF/MSP, spectral similarity (cosine, modified cosine), metadata harmonization, compound ID, for metabolomics and MS data processing.

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

Control Eight Sleep pods (status, temperature, alarms, schedules).

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

Builds, edits, and analyzes workflows and skills. Use when the user requests to "build a workflow", "modify a workflow", "quality check workflow", or "analyze skill".

Build, audit, debug, and migrate websites for durable organic discovery and reliable use by search engines, LLMs, and browser agents. Use for SEO audits or implementation; new sites, routes, templates, CMSs, catalogs, or content programs; crawling, rendering, indexing, robots, canonicals, redirects, sitemaps, hreflang, structured data, metadata, links, faceted navigation, JavaScript SEO, Core Web Vitals, or migrations; keyword, intent, architecture, content, local, media, or authority work; traffic, ranking, CTR, or indexation losses; AEO, GEO, AI Overviews, AI Mode, ChatGPT search, crawler controls, agent-readable pages, Markdown representations, `Accept: text/markdown` content negotiation, `llms.txt`, WebMCP, or agent interaction design. Trigger whenever code or architecture can materially affect public discoverability or machine usability, even if the user does not say SEO. Do not use for paid-search management alone.

Trigger: chrome-devtools, browser automation, headless browser, web scraping, inspect element, chrome debugger, inspect page, network request, console logs. Scope: Interact with and automate headless Chrome via Chrome DevTools Protocol (CDP) for testing, debugging, and scraping. Boundary: Do not use for macOS native desktop GUI automation (use peekaboo instead).

Use when task matches design-system-rules design guidance for IA, usability, responsiveness, systems, motion, and visual QA.

Use when the user wants to negotiate a price, rate, compensation, contract, purchase, hotel, service, vendor deal, discount, upgrade, fee, renewal, refund, or other commercial terms; asks what to say to improve leverage or get a better deal; provides an offer/counteroffer and wants a response; or wants to maximize coupons, direct-booking value, bundles, competing configurations, or all-in economics. Do not trigger for ordinary writing, simple price lookup/comparison, arithmetic, generic persuasion, or conflict mediation without a concrete negotiated outcome.

Trigger: PostHog event, Segment schema, event properties, user funnel track, track taxonomy. Scope: Product behavioral telemetry, user funnel event models. Boundary: Excludes system performance exceptions.

Trigger: REST API, GraphQL schemas, HTTP methods, RFC 7807, endpoint structure, API contracts. Scope: API schema design, error models, request/response structures. Boundary: Excludes client-side visual layouts.

Trigger: clean architecture, hexagonal architecture, domain model, state machine, boundary decoupling. Scope: Software modular design, dependency boundaries, architectural layering. Boundary: Excludes frontend aesthetic styling.

Trigger: writing style, copy editing, simple copy, prose check, text clarity. Scope: Writing clear, direct, and concise English copy. Boundary: Excludes code formatting or marketing value propositions.

Trigger: marketing copy, landing text, CTA labels, value proposition, copywriting copy, conversion copy. Scope: Persuasive copy generation, conversion-focused taglines. Boundary: Excludes technical specifications or backend engineering.

Write or review UX copy — microcopy, error messages, empty states, CTAs. Trigger with "write copy for", "what should this button say?", "review this error message", or when naming a CTA, wording a confirmation dialog, filling an empty state, or writing onboarding text.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Create distinctive, production-grade frontend interfaces with high design quality. Use only when invoked by the `design` wrapper skill, OR when working outside a known site (no `~/Sites/<name>/` repo). Otherwise prefer `design`. Generates creative, polished code that avoids generic AI aesthetics.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Provides three modes — code review, adversarial challenge, and consult — for obtaining a second opinion on code.

Fast headless browser for QA testing and site dogfooding. (gstack)