peterbamuhigire

Top-level router for the Chwezi Core Systems web-development and software-engineering skills engine. Use for AI systems, SaaS, architecture, APIs, databases, security, frontend engineering, mobile, DevOps, reliability, product engineering, SDLC documentation, catalog maintenance, delivery evidence packs, routing fixtures, and world-class engineering quality gates.

Use when specifying or implementing engine-neutral gameplay systems such as movement, combat, AI, quests, dialogue, inventory, progression, save/load, world state, spawning, cameras, or narrative state; engine skills own framework integration.

Use when building, restructuring, profiling, testing, or packaging a Unity mobile game in C# for Android or iOS; covers project architecture, scenes, prefabs, data, input, assets, saves, builds, and Unity-specific release evidence.

Use when discovering, designing, prioritizing, or auditing AI-powered products for measurable business value. Applies to AI opportunity mapping, ROI cases, product strategy, client workshops, and deciding whether an AI feature should be built.

Use when specifying one AI-powered feature end to end, including model choice, prompt and context contracts, output schema, fallbacks, human oversight, UX states, and evaluation.

Use when discovering and ranking AI use cases for a project or module and producing an opportunity register with impact, effort, cost, risk, and evidence gaps.

Use when designing or building an AI-enhanced web app with chat, RAG, MCP tools, streaming, provider abstraction, feature gates, token budgets, and output guardrails.

Use when building Python agents with the OpenAI Agents SDK, including runners, tools, handoffs, guardrails, tracing, memory, multi-agent topology, and deterministic orchestration.

Use when defining a game's player promise, product hypotheses, platform options, production model, vertical-slice evidence, commercial boundaries, or greenlight decision before detailed requirements.

Use when specifying testable game software requirements for player experience, gameplay state, platforms, multiplayer, saves, content, performance, accessibility, telemetry, security, builds, release, or live operations.

Use when designing game client, authoritative state, engine integration, content, saves, multiplayer backend, platform adapters, telemetry, security, build, and live-operations architecture from an approved game SRS.

Use when turning approved game requirements and architecture into implementable Unity, Godot, Unreal, Apple-native, multiplayer, content-pipeline, build, and telemetry work packages with code and asset contracts.

Use when planning game QA, playtesting, balance, deterministic simulation, save migration, multiplayer network conditions, device performance, accessibility, localisation, security, certification, and release-candidate evidence.

Use when documenting reproducible game builds, signing, artifact promotion, distribution, staged rollout, rollback, crash diagnosis, matchmaking operations, live events, remote config, economy controls, support, or incidents.

Use when assembling or reviewing game greenlight, milestone, release, rights, security, player-research, build, test, live-operations, and independent-replication evidence without inflating capability claims.

Use when specifying a game's 3D asset and Blender source-to-engine pipeline, including asset briefs, rigs, animation clips, UV/bakes, materials, LODs, collision, export/import, lineage, automation, runtime budgets, and acceptance evidence; use game-system-architecture for whole-system boundaries.

Top-level router for the Chwezi Core Systems web-development and software-engineering skills engine. Use for AI systems, SaaS, architecture, APIs, databases, security, frontend engineering, mobile, DevOps, reliability, product engineering, SDLC documentation, catalog maintenance, delivery evidence packs, routing fixtures, and world-class engineering quality gates.

iOS AI/ML standards for WWDC26 Apple intelligence work, including Foundation Models, Language Model providers, Dynamic Profiles, Core AI, Evaluations, Core ML, Vision, NaturalLanguage, Speech, SoundAnalysis, and privacy-first on-device inference.

iOS architecture orchestration for production apps, modular codebases, Swift patterns, App Intents, Foundation Models/Core AI provider boundaries, scale practices, and release-ready implementation boundaries.

iOS data persistence standards with SwiftData, Keychain, files, offline sync, Core Spotlight semantic indexing, App Entity data exposure, and AI cache/privacy boundaries.

iOS development standards for AI agent implementation. Swift-first, SwiftUI, MVVM + Clean Architecture, async/await, comprehensive security, testing, and performance patterns. Use when building or reviewing iOS applications, generating Swift...

StoreKit 2 in-app purchases, subscriptions, App Store Server API, group and organization subscription watch items, Unity StoreKit plugin routing, paywall UI, transaction verification, and App Store Connect configuration.

iOS platform capability orchestration for App Intents, Siri, Spotlight semantic indexing, widgets, biometrics, Bluetooth printing, push notifications, native PDF export, networking, media, and Apple framework entitlements.

iOS quality and release orchestration for Swift Testing 6.4, Device Hub, Xcode 27 agents, Xcode Cloud, AI Evaluations, Instruments, TestFlight, App Store review, stability, and release evidence.

Use when reviewing new or changed skills and bundled resources for unsafe installers, credential harvesting, hidden execution, or excessive permissions; use skill-writing for authoring structure.

Use when creating or normalising reusable proposal skills, trigger routes, contracts, references, or authoring automation; use skill-safety-audit instead for a read-only security review.

Use when routing, drafting, reviewing, or assembling a complete consulting proposal, EoI, bid, or tender response; use a numbered pipeline skill when only one known section is required.

Use when choosing whether an AI agent is included, sold as an add-on, or sold standalone; use the pricing skill for rate mechanics and the SLA skill for service commitments.

Use when selecting and adapting agent-specific contract exhibits for a proposal, MSA, or statement of work; use the addendum skill when drafting the full MSA/SLA overlay.

Use when defining intervention credits, abort rights, or refund mechanics for an agent engagement; use the SLA skill for broader credits and the outcome-pricing skill for success fees.

Use when drafting agent-specific MSA and SLA addendums covering action accountability, audit logs, kill switches, intervention, liability, and upstream-provider dependencies.

Use when procurement, legal, or finance challenges agent pricing, failed-task billing, audit rights, refunds, liability, indemnities, or price corridors; use the contract pack for final clauses.

Use when a game for children or learners needs age-appropriate comprehension, scaffolding, learning-feedback separation, privacy/safety, stopping cues, guardian/teacher needs, accessible play, or non-exploitative engagement. Use onboarding-and-first-run-design for ordinary apps.

Use when a game needs visual pillars, shape language, colour scripting, character/world readability, cultural motif governance, 2D/3D cohesion, VFX hierarchy, an asset bible, style scalability, performance-aware art, or engine handoff. Use illustration-style-and-systems for non-game illustration sets.

Use when tuning a game action through anticipation, response, impact, timing, animation, VFX, audio-visual coordination, camera, hit-stop, particles, haptics, reduced-motion, sensory alternatives, or intensity settings. Use micro-interactions-and-feedback for ordinary UI controls.

Use when designing game HUDs, menus, maps, inventory, dialogue, tutorials, pause/settings, save/load, failure/success, controller focus, touch, couch-distance, or diegetic interfaces. Use ordinary app UI skills for non-game task flows.

Use when a game needs its player fantasy and interaction loop routed into HUD, art direction, feedback, camera, input, accessibility, testing, and engine handoff. Use ordinary app UI skills for non-game software and the four game specialists for focused craft.

Use when designing or auditing an interactive UI for WCAG 2.2 AA, keyboard and focus behaviour, accessible names, screen readers, target size, reflow, authentication, or reduced motion. Use inclusive-and-assistive-design for needs beyond the compliance floor.

Use when auditing one existing UI, page, screen, flow, or document for design quality and producing evidence-backed, severity-rated findings. Use product-design-audit for multiple product surfaces and design-qa-and-pre-launch-review for a release verdict.

Use when facilitating a live or asynchronous design critique that needs a clear ask, safe feedback, a decider, and recorded outcomes. Unlike design-audit or heuristic evaluation, this runs the human review session rather than producing expert findings.

Use when authoring, validating, or debugging cloud-init user-data, Ubuntu autoinstall, or RHEL-family Kickstart for first-boot provisioning. Use linux-server-provisioning for interactive post-boot setup and linux-config-management for ongoing desired state.

Use when managing repeatable server state with Ansible, etckeeper, check mode, or drift remediation across Debian/Ubuntu and RHEL families. Use linux-server-provisioning for one-time bootstrap and linux-cloud-init for first boot.

Use when installing, upgrading, pinning, removing, or diagnosing packages and repositories with apt, dnf, snap, Flatpak, or automatic updates. Use linux-server-provisioning for a complete new-server sequence and linux-config-management for fleet-wide desired state.

Use when interactively provisioning a fresh Debian/Ubuntu or RHEL-family server after first boot, including identity, admin access, updates, firewall, services, and verification. Use linux-cloud-init for unattended first boot and linux-config-management for repeatable fleet state.

Use when creating, revoking, or auditing Linux users, groups, SSH keys, sudo/wheel access, PAM settings, SELinux user mappings, or file permissions. Use linux-secrets for credential material and linux-server-hardening for broader host policy.

Use when scanning for leaked credentials, encrypting configuration with age, sops, or GPG, rotating secrets, or checking credential-file handling. Use linux-access-control for user and permission administration and linux-server-hardening for wider host controls.

Use when operating BIND or Unbound as an authoritative or recursive DNS server, including zone authoring, validation, reloads, reverse zones, transfers, and SELinux contexts. Use linux-network-admin for client-side resolution or interface configuration.

Use when diagnosing or configuring Linux interfaces, addresses, routes, client DNS, reachability, VLANs, or time synchronisation with Netplan or NetworkManager. Use linux-dns-server for hosted DNS zones and linux-firewall-ssl for packet filtering.

Library of internal controls embedded in finance / accounting workflows. Segregation of duties, maker-checker, approval thresholds, supplier and payroll master-data controls, petty cash and cash drawer controls, inventory master-data controls, tax / rate table controls, audit-log review, exception monitoring, fraud / error indicators. Use whenever designing or reviewing access control, approval, audit trail, fraud detection, or internal-control attestation in a finance / accounting context.

Use when designing, reviewing, or testing fixed-asset registers, capitalization policy, componentization, depreciation, useful-life review, disposals, revaluation caveats, impairment indicators, tax depreciation caveats, and asset-register to GL tie-outs.

Use when scanning a software system, codebase, implementation plan, proposal, policy memo, business plan, blog post, SRS, or finance/accounting product specification against the Chwezi accounting and finance doctrine. Produces a deep gap analysis, risk-ranked findings, and detailed alignment instructions tied to the doctrine skills and source-register rules.

Use when designing, reviewing, or testing the canonical posting service, journal-entry schema, event-to-journal mapping, ledger invariants, reversals, idempotency, period locks, control-account tie-outs, and drilldown from source evidence to financial reports.

Governed dimensions (cost centre, project, grant, donor restriction, department, branch, product line, customer, supplier, activity, currency, book) and the budget / variance / allocation / contribution-margin / donor-grant reporting they support. Use when designing or implementing management reporting, KPI dashboards, budget vs actual, project profitability, grant utilisation, contribution-margin analysis, or allocation rules. Applies in software, SRS, SDS, test plan, proposal, and business-plan contexts.

Financial-instrument classification, measurement, and impairment under IFRS 9 (full IFRS) and Sections 11 and 12 (IFRS for SMEs). Trade receivables, payables, bank balances, loans, deposits, debt and equity instruments, derivatives, expected credit loss (ECL), hedge accounting. Use when financial instruments are material. Tier-3 scope — Section 11 basic-instruments handling is built first; full IFRS 9 ECL deferred until a client materially requires it.

Practical IFRS for SMEs equivalents to full IFRS standards. The default reporting framework for typical Chwezi clients (SMEs, schools, clinics, NGOs, retail, agribusiness, hospitality, family business). Cross-references each IFRS standard to its IFRS for SMEs section and notes the build implications. Use whenever generating finance content for SME clients, or when deciding whether full IFRS or IFRS for SMEs applies.

Lease accounting under IFRS 16 (full IFRS) and Section 20 (IFRS for SMEs). Lessee single on-balance-sheet model under IFRS 16; lessee operating-vs-finance classification under Section 20. Short-term and low-value exemptions. Lessor classification. Sale-and-leaseback. Use when leases or rental arrangements are in scope. Tier-3 scope — full lessee build deferred until a client materially requires it; Section 20 short-term operating-lease handling and IFRS 16 exemption-test reference are built first.

Ensures every website element — layout, messaging, navigation, imagery, CTAs — reflects the client's brand identity and speaks clearly to their ideal customer. Use before and during page building to validate that the site feels intentional, cohesive, and trustworthy.

Select optimal color palettes for websites using brand colors and color theory. Use when users need to define their website's color scheme, generate complementary palettes, ensure accessibility compliance, or refine existing colors for better visual impact and industry alignment.

Builds multi-language Astro site, verifies output for all language versions, generates deployment scripts and Nginx configuration with root redirect and language-aware routing. Supports English, French, Kiswahili. Use after all pages are built, as the final step.

Analyses up to 5 reference websites provided by the client, visits each one, and generates a structured design guide (docs/design-reference.md) that captures the patterns, features, and qualities the client admires. Use when the client provides URLs of websites they like. Run before design-system.

Establishes the visual foundation for a website — fonts, colors, spacing, animations, and aesthetic direction. Use before building any pages. Reads docs/style-brief.md for brand direction.

Language and tone standard for all written content. Enforces authentic East African English as used in Uganda, Kenya, and Tanzania — formal, clear, respectful, British-influenced, and professionally courteous. Apply to every piece of text generated for the website.

Secure email sending from static websites using PHP + PHPMailer on Apache/WAMP. Self-hosted contact form handler with 4-layer spam prevention (honeypot, timing, content scan, rate limiting), stateless CSRF, beautiful branded HTML emails, and bilingual support. No external services required.

Internationalization infrastructure for multi-language websites. Defines 3 supported languages (English, French, Kiswahili) with path-based routing, hreflang tags, and language-specific sitemaps. Orchestrates content organization and SEO across all language versions.

Generate Triple-Layer AGENTS.md documentation by scanning a project for its tech stack, data directory, and planning directory. Use when the user asks to standardize project documentation, generate agent files, or create AGENTS.md guides.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Update project documentation files (README.md, PROJECT_BRIEF.md, TECH_STACK.md, ARCHITECTURE.md, docs/API.md, docs/DATABASE.md, CLAUDE.md) when significant changes occur. Use for feature additions, architecture changes, dependency updates, API/database modifications. Ensures consistency across all docs.