ai-maker

Use this skill when the user wants to generate ideas, challenge a plan, or think through a problem from multiple angles. Triggers include: 'brainstorm', 'what are my options', 'red-team this', 'what could go wrong', 'devil's advocate', 'pre-mortem', 'give me ideas', 'challenge this', 'what am I missing', 'generate alternatives', 'stress-test this plan', or any request to explore possibilities or find weaknesses before committing. Do NOT use for user research synthesis — use ai-maker-user-research for that.

Use this skill when the user wants a visual output that renders as an HTML page — dashboards, status boards, trackers, comparison tables, timelines, or any rich visual deliverable. Triggers include: 'build a dashboard', 'create a canvas', 'make a status board', 'visual summary', 'render this as HTML', 'interactive report', 'one-pager layout', 'card grid', 'progress tracker', or any request where the output should be a rendered HTML artifact rather than plain text. Also use when the user asks for an output they can share or print as a visual document.

Use this skill when a manager needs to understand, review, or evaluate code without writing it themselves. Triggers include: 'explain this code', 'review this PR', 'what does this do', 'is this good code', 'evaluate this architecture', 'what are the risks', 'prepare questions for the engineering team', 'what's the technical debt here', or any request to understand or assess a technical codebase from a manager's perspective. Do NOT use for writing production code or debugging implementations — use technical Workbench skills for that.

Use this skill when the user needs to interpret metrics, understand what data means, build a data visualization, or define what to measure. Triggers include: 'what does this data mean', 'interpret these metrics', 'build a chart', 'create a dashboard', 'show me a trend', 'what should we measure', 'data summary', 'metrics report', 'anomaly in the data', or any request to make sense of numbers for a business decision. Do NOT use for building technical data pipelines or processing large datasets — use ai-workbench-data for that.

Use this skill when the user wants to create an HTML artifact, dashboard, one-pager, or visual report, or when they want feedback on a design's visual quality or brand compliance. Triggers include: 'build a dashboard', 'create an HTML page', 'design a one-pager', 'review this design', 'does this match the brand', 'make it look better', 'add a visual layout', 'canvas output', or any request to produce or review a polished visual deliverable. Do NOT use for technical UI development (React, WinUI 3) or accessibility audits of existing code — use the appropriate technical skill for those.

Use this skill for management communication, sprint operations, and team coordination. Triggers include: 'draft an email', 'write a status update', 'plan this sprint', 'write a meeting agenda', 'capture action items', 'help me communicate this', 'translate this for the team', 'stakeholder update', 'sprint planning', 'retrospective', 'escalation', or any request to run an effective team operation. Do NOT use for sending actual emails or scheduling meetings in M365 — use ai-maker-workiq for that.

Use this skill when the user needs to define testing strategy, set quality standards, evaluate test coverage, or review a QA plan. Triggers include: 'what should we test', 'is our test coverage good enough', 'define acceptance criteria', 'review this QA plan', 'what's the right testing approach', 'how much testing do we need', 'quality gate', or any request to reason about what quality means for a project. Do NOT use for writing actual test code — use ai-workbench-testing for that.

Use this skill when the user wants to research a topic, evaluate a vendor or product, build a competitive landscape, or make an evidence-backed decision. Triggers include: 'research this', 'competitive analysis', 'what does the data say', 'investigate', 'market landscape', 'evidence for', 'look into', 'compare options', 'due diligence', 'strategic analysis', or any request to synthesize multiple sources before making a decision. Also use when preparing a research brief, executive summary, or recommendation memo. Do NOT use for deep technical implementation research (API docs, GitHub repo analysis) — use ai-workbench-researcher for that.

Use this skill when the user needs to plan, conduct, or analyze user research. Triggers include: 'write an interview guide', 'synthesize these interviews', 'build a persona', 'what do users want', 'user pain points', 'jobs to be done', 'survey design', 'research findings', 'user needs', 'customer insights', or any request to understand users or customers through research methodology. Do NOT use for competitive market analysis — use ai-maker-research for that.

Use this skill to save, recall, or organize information in the vault — the personal knowledge base. Triggers include: 'save this', 'remember this', 'add to vault', 'log this decision', 'what did we decide about X', 'find in my vault', 'recall', 'document this', 'knowledge base', 'where did I put', 'organize my notes', or any request to persist or retrieve personal context across sessions. Also use when the user wants to capture a decision with its rationale for future reference.

Use this skill for Microsoft 365 integration — email, calendar, Teams, tasks, and M365 search. Triggers include: 'send an email', 'schedule a meeting', 'draft a Teams message', 'find that email', 'what's on my calendar', 'create a task', 'Outlook', 'Teams post', 'Microsoft 365', 'M365', 'check availability', or any request to take action in the Microsoft 365 ecosystem. Do NOT use for general communication drafting without M365 integration — use ai-maker-ops for that.

Use this skill to create, debug, or improve GitHub Actions workflows and CI/CD pipelines. Triggers include: 'write a GitHub Actions workflow', 'CI/CD', 'fix this workflow', 'add a build step', 'deployment pipeline', 'GitHub Actions', '.github/workflows', 'release process', 'staging environment', 'automated deploy', 'workflow is failing', or any request to automate builds, tests, or deployments via GitHub. Do NOT use for PowerShell automation outside pipelines — use ai-workbench-powershell for that.

Use this skill to build data pipelines, instrument applications, process structured data files, or automate report generation. Triggers include: 'build a pipeline', 'ETL', 'process this CSV', 'parse this JSON', 'instrument this app', 'emit metrics', 'data transformation', 'automate this report', 'query this data', 'data processing script', or any request to construct the technical systems that collect, transform, or serve data. Do NOT use for interpreting what metrics mean for a manager audience — use ai-maker-data for that.

Use this skill to diagnose errors, analyze logs, resolve dependency conflicts, or find performance bottlenecks. Triggers include: 'why is this failing', 'debug this', 'error trace', 'read these logs', 'what's wrong', 'root cause', 'dependency conflict', 'version mismatch', 'slow build', 'performance problem', 'fix this error', or any request to trace a problem from symptom back to cause. Do NOT use for CI/CD pipeline failures specifically — use ai-workbench-cicd for those.

Use this skill to evaluate and review an existing HTML, UI, or visual artifact for quality, accessibility, or brand compliance. Triggers include: 'review this design', 'audit this HTML', 'check accessibility', 'WCAG compliance', 'contrast ratio', 'brand check', 'layout bugs', 'design quality', 'is this accessible', 'score this UI', or any request to evaluate something that already exists. Do NOT use to create new designs — use ai-maker-design or ai-maker-canvas for creation.

Use this skill for GitHub repository operations, branch management, pull requests, GitHub Pages, and git workflows. Triggers include: 'create a repo', 'set up GitHub Pages', 'manage branches', 'PR workflow', 'branch protection', 'merge strategy', 'gh CLI', 'rebase', 'cherry-pick', 'git conflict', 'publish to GitHub', 'release tag', 'repo settings', or any request to work with GitHub as a platform. Do NOT use for GitHub Actions pipeline authoring — use ai-workbench-cicd for that.

Use this skill to write, debug, or explain PowerShell scripts and Windows automation. Triggers include: 'write a PowerShell script', 'automate this with PS', 'debug this script', 'why is this failing', 'WMI query', 'Windows admin', 'registry', 'manage services', 'idempotent script', 'PowerShell module', 'ps1', or any request for Windows system administration via scripting. Do NOT use for GitHub Actions CI/CD pipelines — use ai-workbench-cicd for that.

Use this skill whenever the user wants to create, improve, or debug an AI skill, system prompt, agent persona, or copilot-instructions.md. Triggers include: 'write a skill', 'create a SKILL.md', 'improve this prompt', 'why is the AI doing X', 'design a system prompt', 'write an eval', 'test this skill', 'make the AI behave like', 'skill authoring', 'prompt engineering', or any request to build or extend AI behavior. Also use when defining what a skill should and should not do (scope fencing) or creating test cases to verify skill behavior.

Use this skill for deep technical research — digging into how a library, API, or framework actually behaves, analyzing GitHub repos, comparing implementation approaches, or tracing undocumented behavior through source code and issues. Triggers include: 'how does X actually work', 'dig into this repo', 'compare these approaches', 'find the root cause in the docs', 'what do the GitHub issues say', 'research the implementation', 'trace this behavior', or any request requiring multi-source technical evidence gathering. Do NOT use for business or strategic research — use ai-maker-research for that.

Use this skill to audit code for secrets, set up pre-commit hooks, or harden a GitHub Actions workflow or deployment config. Triggers include: 'scan for secrets', 'credential audit', 'API key leaked', 'pre-commit hook', 'secrets in git history', 'security review', 'harden this workflow', 'dependency vulnerabilities', 'npm audit', 'security checklist', or any request to find and fix security problems in code, configs, or pipelines. Does NOT cover runtime security, network security, or penetration testing.

Use this skill to write test code — unit tests, end-to-end tests, or PowerShell tests. Triggers include: 'write tests for this', 'add unit tests', 'Vitest', 'Playwright', 'Pester', 'test this function', 'increase coverage', 'E2E test', 'test suite', 'fix this failing test', 'mock this dependency', or any request to produce actual test files. Do NOT use for testing strategy and coverage planning (what to test, not how) — use ai-maker-quality for that.

Use this skill to extract text or data from images, scanned documents, or PDFs using OCR. Triggers include: 'extract text from this image', 'OCR', 'read this scan', 'PDF extraction', 'parse this form', 'digitize this document', 'extract fields from', 'process these scanned pages', 'vision', 'what does this image say', or any request to get structured data out of an image or document. Do NOT use for data transformation after extraction — use ai-workbench-data for that.