Latest Agent Skills

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the Task tool for architecturally enforced context isolation. Supports Jest, Vitest, pytest, Go test, cargo test, PHPUnit, and RSpec.

SQL patterns for database querying and design

Run a single experiment iteration. Edit the target file, evaluate, keep or discard.

Provides patterns to build Retrieval-Augmented Generation (RAG) systems for AI applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

Prd

Modern PHP programming patterns

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.

Okr

Full autonomous engineering workflow

Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.

Fix failing or flaky Playwright tests. Use when user says "fix test", "flaky test", "test failing", "debug test", "test broken", "test passes sometimes", or "intermittent failure".

Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.

Modern C++ programming patterns and idioms

Document architectural decisions in standardized ADR format. This skill should be used when making significant technical decisions, choosing between approaches, establishing patterns, or when other skills (create-plan, implement-plan, brainstorm) identify decisions that need documentation. Triggers on "document decision", "create ADR", "architectural decision", or automatically when invoked by other skills during planning and implementation.

Go programming patterns and idioms

Refines ideas iteratively. Refine ideas through structured divergent and convergent thinking. Use "idea-refine" or "ideate" to trigger.

Structure and draft a Confidential Information Memorandum for a sell-side M&A process — the disclosed marketing document sent to buyers after they sign an NDA.

Translate text faithfully into a target language while preserving meaning, register, and intent.

Organize symptoms, history, and questions into a clear summary to bring to a clinician — no diagnosis.

Draft a clear, complete, ready-to-send offer letter with compensation, terms, and contingencies — flagging every unconfirmed figure.

Model a leveraged buyout end to end — sources and uses, tranche-level debt with amortization and cash sweep, levered free cash flow, and sponsor returns (IRR and MOIC) with returns attribution and credit-stat tracking.

Value a business by discounting unlevered free cash flow at WACC with mid-year convention, a dual-method terminal value, and a full enterprise-to-equity-to-per-share bridge plus WACC-versus-growth sensitivity.

Audit an existing financial model workbook for correctness (formula tracing, hardcode and error detection, sign and consistency checks, tie-outs, and sensitivity stress) before you rely on its outputs.

Trace a break between two records of the same position or cash — accounting vs custodian, fund vs prime broker, trade vs settlement — from the aggregate difference down to the offending transaction, and classify it for clearing.

Build a personalized study plan with spaced-repetition scheduling toward a deadline and goal.

Design or repair a CI/CD pipeline with well-ordered parallel stages, lockfile-keyed caching, quality gates, and build-once artifact promotion.

Run a structured churn-save play for an at-risk account to diagnose root cause and reverse the decision.

Turn a diff or plain description into a conventional-commit message - honest type and scope, a why-focused body, breaking changes flagged, nothing invented.

Adapt the commercial-legal playbook and its standard / fallback / walk-away positions to a company's risk tolerance, industry, and signing authority, and version the result.

Generate high-CTR titles and opening hooks for a piece of content and score them against clarity and curiosity.

Produce a 30/60/90-day cash-flow forecast from AR and AP with base/low/high confidence bands and shortfall alerts.

Rank the top-5 leads worth calling today with tailored, history-grounded talking points and proposed calendar blocks — no auto-send.

Merge many sources into one cited, deduplicated answer with per-claim confidence.

Run a structured, multi-source deep-research loop on a question until the answer stops changing.

Track open comment periods and draft a substantive, on-the-record comment that argues your position within the docket's rules and deadline.

Review QML code for correctness, performance, and idiom using qmllint and Qt6 best practices.

Review Qt6 C++ code for correctness, memory ownership, and idiomatic use of QObject, signals/slots, and implicit sharing.

Write a bug report a developer can reproduce and fix without asking a single follow-up question.

Maintain a RAID log tracking risks, assumptions, issues, and dependencies with owners and review cadence.

Write a PRD or feature spec that aligns design and engineering — problem with evidence, explicit non-goals, measurable success metrics, and testable acceptance criteria.

Monitor a live model for data quality, input and prediction drift, performance decay, and fire retraining triggers.

Deploy a trained model to serving with versioning, shadow or canary rollout, and a tested rollback path.

Audit a page or site across keywords, on-page, content gaps, and technical health, then return a prioritized impact/effort action list.

Turn a raw transcript or scribble into decisions, action items with owners and dates, and open questions - so nothing agreed in the room evaporates afterwards.

Remove an installed legal skill cleanly — check dependents, purge artifact and config, and preserve an audit record plus reinstall coordinates.

Run the Legal Builder Hub security-review gate on a candidate legal skill — inspect its manifest and body for unsafe behavior before any install is allowed.

Customize an installed legal skill's settings — jurisdiction defaults, tone, autonomy, and enforced conditions — without weakening its security posture.

Review and manage an IP portfolio across trademarks, patents, copyrights, and domains — docketing assets, deadlines, coverage gaps, and prune-vs-maintain decisions.

Tailor the IP-LEGAL sub-plugin to one organization by capturing its risk tolerance, jurisdictions, and default playbook positions.

Run a trademark clearance search before adopting a new brand name, mark, or logo and risk-rate it clear, caution, or high-risk with a proceed/modify/abandon recommendation.

Populate an investment-banking pitch template from source data — situation, market, valuation, buyer landscape, and process recommendation — to win or advise on a mandate.

Build and prioritize the acquirer universe for a sell-side M&A process — strategic and financial buyers scored on strategic fit, ability to pay, and likelihood to transact.

Create subtitles or captions with correct timing, line breaks, and reading-speed limits.

Adapt content for a specific locale — units, dates, currency, idioms, and cultural fit — beyond literal translation.

Build a bilingual terminology glossary and style guide that enforces consistency across a translation project.

Produce a ready-to-run onboarding plan — pre-boarding checklist, day-1 agenda, first-week plan, and 30/60/90 ramp milestones with owners.

Build a rolling 30/60/90-day cash forecast from AR/AP aging and fixed outflows, flag floor breaches, and model liquidity levers.

Tie out a fund NAV package end to end — assets, liabilities, capital, and per-share/per-unit price — proving the accounting equation, the price, and the day-over-day movement before the NAV is released.

Write or maintain technical documentation — READMEs, runbooks, API references, architecture docs — that a specific reader can act on without asking follow-ups.