Skills for your AI
Analyzes insurance claims customer feedback into sentiment, categories, trends, dashboards, reports, segments, anomalies, surveys, responses, and predictions. Use when a claims manager asks to analyze, categorize, summarize, visualize, segment, flag, survey, r
Analyzes insurance claims, transactions, policies, provider, voice, and image data to detect fraud, validate claims, score risk, and produce alerts and reports. Use when asked to find fraud patterns, cross-reference claims against external records, flag high-r
Analyzes insurance claims data, monitors trends, reviews claims, supports investigations, and builds fraud training and reporting materials. Use when claims managers need suspicious pattern detection, red-flag claim review, investigation reports, policy gap an
Turns insurance claims data into structured datasets, performance reports, forecasts, risk and fraud findings, sentiment analyses, benchmarks, dashboards, and cost analyses. Use when a claims manager needs claim data gathered and organized, KPIs or trends anal
Streamlines insurance claims processing from intake to payment, covering data extraction, document classification, fraud flagging, claimant communication, trend analysis, workflow optimization, adjudication, routing and payment. Use when a claims manager needs
Turns insurance claims data into cleaned datasets, trend analyses, visualizations, fraud flags, cost-driver rankings, forecasts, and reports. Use when the user provides claims data and asks for trend analysis, forecasting, fraud detection, cost drivers, model
Helps secondary teachers with attendance, seating charts, behavior plans, rules, transitions, conflict resolution, group work, differentiation, and parent communication. Use when a teacher needs classroom management tasks drafted, planned, or organized.
Migrates codebases from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5 by updating model strings, removing the context-1m beta header, and adding the effort parameter. Use when the user asks to migrate, upgrade, or switch models to Opus 4.5.
Installs, configures, tests, and runs clidash, a read-only web dashboard that builds tabs and tables from any CLI's JSON output. Use when the user wants to set up clidash, tailor its config, verify it works, run it as a service, or troubleshoot its endpoints.
Provides accountants with client financial advisory analysis and planning support across statements, budgeting, tax, investments, retirement, risk, cash flow, debt, valuation, succession, estate, and education. Use when an accountant needs analysis, strategies
Generates a prioritized client health report with weighted health scores, RAG status, trend direction and actionable recommendations from CRM, support, usage, billing and communication data. Use when asked for a client health report, client risk review, churn-
Loads, analyzes, and simulates genome-scale metabolic models with COBRApy using FBA, FVA, knockouts, flux sampling, production envelopes, gapfilling, and model building. Use when the user wants to run constraint-based metabolic modeling on an SBML, JSON, or YA
Reviews AI-generated code diffs against ten guardrail rules covering conventions, minimal change, invented APIs, verification, weakened tests, swallowed errors, scope, unread deletions and secrets. Use when a diff or AI-written change needs review, when a clai
Generates, validates, optimizes, embeds, and organizes code snippets for web developers, including templates, integration guidance, analytics frameworks, and repository blueprints. Use when a developer asks for a snippet in a specific language, needs embeddabl
Answers questions about a codebase by reading its knowledge graph, checking freshness, and tracing nodes, edges and layers. Use when the user asks how code is structured, what a function or file does, how components relate, or which architectural layer somethi
Installs, authenticates, configures, defaults, or removes the Codex agent provider for NanoClaw groups. Use when the operator asks to install Codex, fix Codex auth errors, switch a group to Codex, default new groups to Codex, or remove Codex.
Use when building a quarterly bookings forecast, ARR projection, pipeline forecast, NRR projection, or commit/best-case/pipe-only board number — especially when the CRO needs to walk the board through funnel math + cohort ARR + per-stage conversion assumptions
Use when reviewing, approving, or designing commercial motion — pricing models, deal review, discount approval, partnership economics, channel mix, commercial policy, RFP/RFI response, bookings forecast. Triggers on "review this deal", "should we discount", "p
Stages, splits, and commits git changes with Conventional Commit messages, including patch staging and post-commit verification. Use when the user asks to commit or stage changes, split a working tree into logical commits, write a commit message, or verify a c
Analyzes corporate communication metrics across media, social, web, internal channels, and stakeholder feedback, producing reports with sentiment, reach, engagement, and recommendations. Use when the user asks for media coverage, social engagement, website tra
Conduct comprehensive company research and due diligence. Analyze business model, competitive landscape, management, and market position.
Automates financial reporting from data extraction and cleaning through report generation, scheduling, validation, archiving, forecasting, reconciliation, and audit compliance. Use when the user needs financial data pulled and cleaned, reports generated or dis
Automates compliance reporting by extracting, validating, analyzing, and reporting compliance data and managing documents, alerts, audits, and communications. Use when gathering compliance data from multiple sources, generating reports from templates, reconcil
Isolates macOS connectivity failures into local, DNS, path, or service fault domains using bounded read-only probes. Use when a user reports a connectivity problem, a site or app is unreachable, DNS or VPN resolution is suspected, or a process-specific network
