Skills directory · page 30

Operate across Google Drive, Docs, Sheets, and Slides as one workflow surface for plans, trackers, decks, and shared documents. Use when the user needs to find, summarize, edit, migrate, or clean up Google Workspace assets without dropping to raw tool calls.

Operate Google Drive, Docs, Sheets, and Slides as a single workflow interface for handling plans, trackers, presentations, and shared documents. Use when the user needs to find, summarize, edit, migrate, or clean up Google Workspace assets without using raw tool calls.

Use when a launched managed agent needs grading against a rubric and improving ('grade my agent', 'is it good enough'). Builds the outcome with outcome_builder.py, reads verdicts with verdict_reader.py and runs held-back evals from eval_scaffold.py.

Create and manage production-ready Grafana dashboards for comprehensive system observability.

Identify grammar, logical, and flow errors in text and suggest targeted fixes without rewriting the entire text. Use when proofreading content, checking writing quality, or reviewing a draft.

Use for any NIH funding question ('find grants for my research', 'which NIH institute'). Maps the idea to institutes, study sections and NOSIs via RePORTER, matches mechanisms with mechanism_matcher.py and writes a .docx strategy. NIH only.

Query the code graph database to understand component relationships, dependencies, and change impact. Use when the user asks to "find callers", "check dependencies", "what uses this", "show relationships", "find serializers", or when reading code and needing to understand what depends on a component before modifications.

GraphQL gives clients exactly the data they need - no more, no less. One endpoint, typed schema, introspection. But the flexibility that makes it powerful also makes it dangerous. Without proper controls, clients can craft queries that bring down your server. This skill covers schema design, resolvers, DataLoader for N+1 prevention, federation for microservices, and client integration with Apollo/urql. Key insight: GraphQL is a contract. The schema is the API documentation. Design it carefully.

Master modern GraphQL with federation, performance optimization, and enterprise security. Build scalable schemas, implement advanced caching, and design real-time systems.

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".

Interview the user relentlessly about a plan or design until every branch of the decision tree has an explicit recorded decision and no open questions remain. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Use when a plan should be stress-tested against the project's own docs (CONTEXT.md glossary, docs/adr decisions), or the user says 'grill with docs'. Scans ADRs with adr_scanner.py and updates the docs inline as terms and decisions settle.

Apply AI-generated visual edits to video using xAI / Grok — change object colors, add effects (smoke, fire, sparkles), restyle scenes, or alter what's in a clip ("make the sunglasses red", "add smoke from the gun", "make it sparkly"). Use whenever an edit can't be done deterministically with ffmpeg/overlays and needs generative reimagining of the footage. Covers trimming, chunking, audio mux, and seamless reassembly.

Ground a chat answer or written document in a numbered citation ledger: register every source at retrieval time, cite per sentence, render the Sources block mechanically, and verify the draft before delivering — optionally upgrading to verbatim evidence quotes and an `[unverified]` marker for claims no source can carry. Use when an answer rests on fetched information rather than knowledge. Not for academic BibTeX pipelines, incidental lookups mid-task, or creative writing.

Write growth log entries that extract reusable patterns from completed work — root cause, transferable rule, and a recognizable signal — instead of diary-style event narration, with a 4-8 sentence template and merge-duplicates discipline. Use when capturing what was learned after a complex task, debugging session, failure, or rollback, when reviewing progress over a period, or when a delivery gate asks what was learned.

Identify growth loops (flywheels) for sustainable traction. Evaluates 5 loop types: Viral, Usage, Collaboration, User-Generated, and Referral. Use when designing growth mechanisms, building product-led traction, or understanding how growth loops work.

High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

Identify the best GTM motions and tools across 7 motion types: Inbound, Outbound, Paid Digital, Community, Partners, ABM, and PLG. Use when selecting marketing channels, choosing between inbound and outbound strategy, or planning cross-channel campaigns.

Create a go-to-market strategy covering marketing channels, messaging, success metrics, and launch timeline. Use when planning a product launch, creating a GTM plan from scratch, or defining a launch strategy for a new market.

Baixa todos os encartes vigentes do Supermercado Guara (todas as paginas em alta resolucao). Use quando o usuario mencionar "baixar encartes Guara", "encartes Guara", "encartes Supermercado Guara", ou colar a URL supermercadoguara.com.br/folhetos.

Protocol for the ctx-guard context and usage guard, and how to configure it. Use whenever a message starting with "[ctx-guard]" arrives (a context or usage note, a prompt turn saying the user is away, a refused ready token, a blocked tool, a lifted brake, a subagent budget note), when asked to write a ctx-guard handoff or end a reply with the ready token (CTX-READY), and when the user asks to set up, explain or change ctx-guard, a context guard or usage guard, its roles, thresholds, triggers, handoff, auto clear or compact, subagent budgets, trust or the /ctx-guard command.

Query NHGRI-EBI GWAS Catalog for SNP-trait associations. Search variants by rs ID, disease/trait, gene, retrieve p-values and summary statistics, for genetic epidemiology and polygenic risk scores.

Full-pipeline toolkit for AI short dramas (MiniMax H3 + AutoDL cloud rendering / self-hosted ComfyUI server rendering): script audit and dialogue locking → break down visual/voice assets and write reference-image prompts → write storyboards and H3 prompts → compile self-check → AutoDL batch rendering → review footage and rework → voice unification/stitching/subtitles/loudness delivery. Used when starting a new drama, writing storyboards or prompts for an episode, breaking down assets, rendering, reviewing footage, or doing post-production. Source: 60-episode practice on "Crossing the Line" + RunningHub H3 comparison testing.

Собрать обвязку для передачи — папку `.claude`, готовую к копированию в чужой проект или на другую машину, плюс памятку получателю. Вызывать по «собери обвязку», «собери полку», «подготовь к передаче», «/handoff», с указанием пути, куда собрать.

Compact the current conversation into a handoff document for another agent to pick up, referencing existing artifacts (PRDs, plans, ADRs, issues, commits, diffs) by path or URL instead of duplicating them. Use whenever the user wants to hand off to a fresh agent, is ending a session mid-task, asks for a handoff doc or a summary of state, decisions and next steps for the next session, or starts a new session that picks up prior work.

Records, searches, filters and redacts HAR captures and turns them into scrapers. Use when the user has or needs a HAR capture. Not for non-capture JSON or HTML.

Use for a decision where every option hurts (layoff vs down round, killing a loved product). Runs 10/10/10 and regret minimization.

Audit, restructure, and design harnesses — scheduled operational scripts, drift checkers, watchdogs, gated data pipelines wrapped around a repo or agent system. Use when helper scripts have grown past one screen, checkers are multiplying, or a harness subsystem needs a home. Not for one-off scripts, and not for application code that no scheduled check or gate runs.

Preview, confirm, and execute a deterministic harnessed update when you want to upgrade harnessed itself. Report partial outcomes honestly and offer bounded agent repair only after a second confirmation.

Expert Haskell engineer specializing in advanced type systems, pure

Development patterns for clinical decision support systems (CDSS). Drug interaction checks, dose validation, clinical scores (NEWS2, qSOFA), alert severity classification, and integration into electronic medical record workflows.

Clinical Decision Support System (CDSS) development patterns. Drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), alert severity classification, and integration into EMR workflows. Use when building clinical decision support — drug interaction checks, dose validation, clinical scoring, or alert severity.

EMR/EHR development patterns for healthcare applications. Clinical safety, encounter workflows, prescription generation, clinical decision support integration, and accessibility-first UI for medical data entry. Use when building EMR or EHR features such as encounter workflows, prescription generation, or clinical data entry UI.

EMR/EHR development patterns in healthcare applications. Clinical safety, encounter workflows, prescription generation, clinical decision support integration, and accessibility-first user interfaces for medical data entry.

Patient-safety evaluation tools for healthcare application deployments. Automated test suites cover CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance. Blocks deployment on safety failures.

Patient safety evaluation harness for healthcare application deployments. Automated test suites for CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance. Blocks deployments on safety failures. Use when a healthcare deployment must be gated on patient-safety tests for CDSS accuracy, PHI exposure, and workflow integrity.

Find open US healthcare jobs (nursing, CNA, allied health, therapy, imaging, pharmacy, physicians and more) and the hourly pay employers post, using CareJobs.Now's free MCP server or its public JSON endpoints. Use when someone asks for healthcare or nursing jobs in a US place, what a healthcare job pays, or which hospitals are hiring.

Protected Health Information (PHI) and PII compliance patterns for healthcare applications: data classification, row-level access control, tamper-proof audit trails, schema tagging, and common leak vectors such as logs, URLs, and browser storage. Use when code touches patient or clinician data, when implementing HIPAA or GDPR access controls, or when auditing a healthcare system for data exposure.

Compliance patterns for protected health information (PHI) and personally identifiable information (PII) in healthcare applications. Covers data classification, access control, audit trails, encryption, and common leakage paths.

Build Solana applications with Helius infrastructure. Covers transaction sending (Sender), asset/NFT queries (DAS API), real-time streaming (WebSockets, Laserstream), event pipelines (webhooks), priority fees, wallet analysis, and agent onboarding.

Build Solana trading applications combining DFlow trading APIs with Helius infrastructure. Covers spot swaps (imperative and declarative), prediction markets, real-time market streaming, Proof KYC, the DFlow Agent CLI for autonomous trading, transaction submission via Sender, fee optimization, shred-level streaming via LaserStream, and wallet intelligence.

Build Solana DeFi applications combining Jupiter APIs with Helius infrastructure. Covers token swaps (Swap API V2), lending/borrowing (Lend protocol), limit orders (Trigger), DCA (Recurring), token/price data, transaction submission via Sender, fee optimization, real-time streaming, and wallet intelligence.

Build Solana trading and intelligence applications combining OKX DEX aggregation with Helius infrastructure. Integration-only layer — describes when and how to compose OKX tools with Helius tools for swaps, token discovery, smart money signals, meme token analysis, and portfolio intelligence.

Build frontend Solana applications with Phantom Connect SDK and Helius infrastructure. Covers React, React Native, and browser SDK integration, transaction signing via Helius Sender, API key proxying, token gating, NFT minting, crypto payments, real-time updates, and secure frontend architecture.

Use for any Helm chart to create, review or harden (values.yaml, templates, subcharts, RBAC, pod security), before editing it. Analyzes the chart with chart_analyzer.py and validates values with values_validator.py.

Comprehensive guidance for creating, organizing, and managing Helm charts for packaging and deploying Kubernetes applications.

Trace how Hermes assembles its system prompt from instruction files: which file loads from which directory, which project file wins when several exist, and which tier each rule lands in. Use when auditing or editing SOUL/AGENTS/MEMORY/USER files, deciding where a durable rule belongs, debugging an instruction file that did or did not take effect, or reasoning about subagent context and prompt cache stability. Not for editing the runtime source, and not for other harnesses' context files.

Convert local Hermes operator workflows into sanitized ECC skills and release-pack artifacts. Use when preparing a Hermes workflow for public ECC reuse without leaking private workspace state, credentials, or local-only paths.

Converts local Hermes operator workflows into sanitized ECC skills and release-package artifacts. Use when preparing Hermes workflows for public ECC reuse without leaking private workspace state, credentials, or local-only paths.

Configure Hermes model providers, transports and routing: provider entries, default-route switching, reasoning effort, delegation pins, per-profile copies, and proving a route with live signals. Use when a model 404s or rejects an endpoint, a profile ignores its key, config drifts between root and profiles, vision or image generation errors, or a relay's effort/cost looks wrong. Not for another harness's own model configuration.