Top Agent Skills

Enforces comment and documentation discipline when writing or editing code: concise file headers, native-format function docs, inline comments for non-obvious logic, and protection of existing comments.

Drafts a GitHub issue with YAML frontmatter and checkboxes, writing it to a local file for review.

Creates a self-contained interactive HTML explanation of code changes, including background, intuition, code walkthrough, and quiz sections, with diagrams and responsive styling.

Enforces a principal-engineer self-review checklist on every code block before output, covering correctness, performance, security, naming, and testability.

Design, simulate, and run quantum circuits on simulators and quantum hardware using Google's Cirq framework.

Orchestrates AI/ML workflows for building LLM applications, RAG systems, AI agents, and ML pipelines, covering design, integration, observability, and security.

Designs collaborative AI agent teams using the CrewAI framework, covering agent roles, task decomposition, crew orchestration, process types, memory systems, and event-driven flows.

Automates job search, auto-apply, resume generation, application tracking, salary intelligence, and recruiter outreach via the JobGPT MCP server.

Generates thorough project documentation by exploring the codebase, identifying the tech stack and deployment target, and writing a comprehensive README.md covering local development, architecture, and production deployment.

Synthesizes the current conversation into a PRD and publishes it to the project issue tracker with a triage label.

Governs AI coding agents with safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks to ensure safe, thorough, and honest work.

Generates a complete set of favicons from a source image and updates project HTML with the appropriate link tags.

Turns a raw idea into four linked planning files through a five-phase pipeline: clarifying questions, deep research, a PRD with non-goals and metrics, and a phased execution plan with kill criteria.

Generates text, images, video, speech, and music, and performs web searches via the MiniMax AI platform using the mmx terminal CLI.

Optimize content for AI Overviews, ChatGPT, Perplexity, and other AI search systems. Use when improving GEO, AI citations, llms.txt readiness, crawler accessibility, and passage-level citability.

Design user flows and screen structure using UX patterns like progressive disclosure, hub-and-spoke navigation, and information pyramids.

Write defensive, portable Bash scripts for automation, CI/CD, and system utilities, with strict error handling, safe argument parsing, and testing.

Formalizes narrative technical documents into structured mathematical problem specifications with variables, constraints, objectives, and uncertainty, citing evidence and flagging missing information.

Sets up the Manifest observability plugin for agents, including installing the plugin, configuring an API key and optional custom endpoint, and verifying the gateway logs.

Creates walkthrough videos from Stitch project screens using Remotion, with transitions, zoom effects, and text overlays.

Implements a code change on a feature branch, opens a single pull request to main, and runs a code review loop before handoff.

Coordinates multiple AI agents working on a shared task list using Claude Code's native team tools, with task decomposition, staged execution, and verification.

Write efficient C code with proper memory management, pointer handling, and POSIX compliance, including debugging and testing guidance.

Launches an RSVP speed reader to display text one word at a time with Spritz-style highlighting.

Design schemas, write TypeScript functions, and manage real-time data, auth, storage, scheduling, and deployment for Convex backends.

Create, list, and view GitHub issues interactively using the gh CLI, with guided prompts for titles, bodies, labels, and filters.

Build, optimize, and execute quantum circuits with Qiskit on local simulators or cloud hardware, and analyze results.

Transforms rough sketches or text descriptions into photorealistic, high-fidelity 3D product renders with customizable styles and materials.

Connects Claude to 1000+ apps via Composio to send emails, create issues, post messages, and update databases.

Build reliable background processing and durable, long-running workflows using Inngest without managing infrastructure.

Analyze and optimize content for visibility in AI Overviews, ChatGPT, Perplexity, and other AI search systems by evaluating citability, structure, authority, and technical accessibility.

Write defensive, portable Bash scripts for automation, CI/CD, and system utilities, with strict error handling, safe argument parsing, and testing via Bats and ShellCheck.

Guides Firebase development with best practices for security rules, data modeling, and avoiding common pitfalls.

Diagnoses why a page is or is not converting, scores conversion readiness, and provides prioritized, evidence-based recommendations.

Analyzes a single webpage's on-page SEO, content quality, technical meta tags, schema, images, and performance, producing a scorecard and prioritized recommendations.

Deploys web apps with backend APIs, database, and file storage to a public URL via the AppDeploy HTTP API.

Redirects to the canonical PR writing workflow when the legacy skill name is used.

Reviews local branch changes for bugs, security vulnerabilities, and code quality issues, producing a prioritized report with severity ratings and concrete fixes.

Quantize LLMs to 8/4/3/2/1-bit precision without calibration data, using multiple backends and HuggingFace/vLLM integration.

Creates, edits, and analyzes PowerPoint presentations by converting to markdown, unpacking raw XML, and applying design principles for new slides.

Query the Cancer Dependency Map (DepMap) for CRISPR gene dependency scores, drug sensitivity data, and gene effect profiles to identify cancer-specific vulnerabilities, synthetic lethal interactions, and validate oncology drug targets.

Validates the Emotional Attitude Score (EAS) metric by measuring its consistency with human judgment on word-level sentiment polarity, using the AmbGIMT dataset and pairwise score comparisons.

Computes the Receiver Operating Characteristic (ROC) metric using torchmetrics, supporting binary, multiclass, and multilabel tasks.

Create, analyze, and visualize complex networks and graphs in Python, covering graph construction, algorithms, generators, I/O, and visualization.

Computes the HARE Score, an entity- and relation-centric metric for evaluating machine-generated histopathology reports against ground truth, using GatorTronS+SapBERT embeddings and relation F1.

Evaluates computational throughput and real-time efficiency of embedded CPU and GPU platforms by measuring peak FLOPS via a matrix rotation kernel and assessing inference latency and power consumption on a robotic vision pipeline.

Computes the SQuAD metric using torchmetrics, given predictions and ground truth. Use when evaluating question-answering outputs with exact match and F1 scores.

Create publication-quality static, animated, and interactive plots with fine-grained control over every element, from basic charts to multi-panel figures, with export to PNG, PDF, and SVG.

Scores generated text for morphosyntactic well-formedness by measuring how closely it adheres to language-specific dependency rules extracted from treebanks.

Evaluates text-to-image generation models by decomposing assessment into five specialized skills (object presence, count, spatial relations, scale, and text rendering) and open-ended prompts, producing interpretable binary scores with visual and textual explanations.

Evaluates the faithfulness of abstractive summaries by verifying if factual claims (masked as cloze questions) in the reference summary can be correctly answered using only the generated summary, compared against a gold-standard answer derived from the source context.

Evaluates how well internal model representations (hidden states) predict token-level information importance in summarization tasks, using NDCG@10 and Spearman's rank correlation.

Evaluates speaker verification models by computing true positive rate at fixed false positive rate thresholds, probing embedding space separation of same-speaker versus different-speaker pairs.

Benchmarks LLM agents fine-tuned with the Agent Data Protocol across software engineering, web browsing, OS/database tool use, and reasoning tasks, reporting unit test pass rates and task success rates.

Benchmarks automatic speech translation and recognition on English-French and English-Romanian datasets, reporting BLEU and WER on tokenized outputs.

Evaluates speech language models on beyond-semantic speech attributes such as dialect comprehension, multi-turn context memory, emotion perception, age-aware response generation, and non-verbal cue handling, reporting accuracy and judge-based scores.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Lints native Knowledge Vault markdown against the capture-llm-wiki schema, checking frontmatter, wikilinks, and citation hygiene, and writes a report.

Firm-fixed-price cost buildup mirroring 1102 IGCE FFP wrap-rate math (BLS OEWS + GSA CALC+ + GSA Per Diem). USE WHEN the user asks to "build an FFP IGCE", "wrap rate buildup", "FFP cost estimate", "layer fringe overhead G&A fee", "how should we price this FFP task order", or "IGCE parity for our bid". Pulls labor categories from pursuit vault or defaults, stacks fringe/overhead/G&A/fee, exports JSON + XLSX to Studio. DO NOT USE FOR T&M/LH pricing (`igce-builder-lh-tm`), cost-reimbursement (`igce-builder-cr`), OT milestones (`ot-prototype-strategist`), or obligation intel (`competitive-intel`).

Profiles a competitor's vehicles, teaming posture, and recent award patterns, producing a markdown note for vault capture.