AI Agent Workflow Collection

The 10 canonical tenets of Artificial Critical Thinking (ACT) with rationale for each — I Hypothesis Primacy, II Disconfirmation Over Confirmation, III Multiple Working Hypotheses, IV System-Prompt Skepticism, V Calibration Over Confidence, VI Materiality Gating, VII Frame Before Solve, VIII Adversarial Self-Probe, IX Visible Markers, X The Discipline Applies to Itself. Use when a decision cites "a tenet", when running act-pass, when authoring a critical thinking rule, or when looking up the ACT canon.

Add a new project to the planning suite. Creates a project-specific configuration directory and walks through project settings.

Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats.

Recognize and prevent confabulation — when you don't know, say so.

Calibrated human-AI collaboration with creative latitude — trust calibrated to reliability, creativity preserved with validation.

Analyze documentation gaps, create Architecture Decision Records (ADRs), and build knowledge indexes. Use after feature completion, during knowledge sharing, or when onboarding documentation needs ...

Generate assisted PRs to correct Security Group ownership for first-party apps flagged by S360 tenant-isolation policy…

Atlassian Template and Files Creator/Modifier expert for creating, modifying, and managing Jira and Confluence templates, blueprints, custom layouts, reusable components, and standardized content structures. Use when building org-wide templates, custom blueprints, page layouts, and automated content generation.

Well-Architected Framework principles and Azure best…

Time Saved: 1-2 hours debugging identity and…

Time Saved: 30 minutes - 1 hour…

Execute read-only KQL queries against Kusto / Azure Data Explorer clusters via the Kusto MCP server. Read-only -- does not create, alter, or drop objects.

Execute read-only DAX queries against Power BI semantic models via the Power BI MCP server -- metadata discovery with INFO.VIEW functions and data retrieval with EVALUATE.

Bootstrap repository-scoped VS Code workspace files for a plugin-native Alex ACT workspace. Use when a new repository lacks Markdown Preview CSS, the current workspace needs the explicit /alex-act-manager bootstrap-workspace repair path, or a repo needs deterministic .vscode/settings.json and .gitignore setup without touching user settings.

Build professional, themed PowerPoint decks from Markdown via LLM-generated pptxgenjs JavaScript. Uses modular per-slide architecture for all decks. Supports data-driven decks with deck.yaml — fetc...

Convert a Marp Markdown file to HTML, PDF, or PowerPoint using marp-cli. Use when asked to "build slides", "export presentation", "convert to PDF", "generate PPTX", "marp build", or "export deck". ...

Hardcoded paths in build scripts break when directory structure…

Distill the one-sentence Big Idea, story arc, audience, and style stance for a chart BEFORE picking a chart type. Starts by questioning intent — whether the artifact should exist at all, and whether the stated purpose is the real one. Reads the surrounding docs / prose / ticket for an existing Big Idea first, then helps the user articulate one via a 3-question elicitation ladder if none is found. Asks whether the user wants a TRADITIONAL (safe) or INNOVATIVE (higher-impact, higher-risk) treatment. Use before invoking the flint-chart skill or the /render-chart prompt whenever the user's ask is 'chart this', 'visualize', 'make a chart', 'show the data', or when framing is unclear.

Reference catalog of chart types organized by seven communication goals (comparison, change-over-time, proportion, distribution, relationship, flow, deviation), plus a CSAR evaluation loop for AI-generated chart choices, override decision table, 5-visual rule for dashboard density, living gallery pointers (FT Visual Vocabulary, Data-to-Viz, Data Viz Catalog, Vega-Lite examples, Storytelling with Data), and a 6-step selection algorithm. Use when picking a chart type, evaluating an AI-suggested chart, reviewing chart choices for story-intent alignment, sanity-checking a dashboard's density, or explaining chart taxonomy to a heir.

Detect coherence violations between AlexACTEdition (brain) and AlexSkillMall (marketplace) — broken references, tag mismatches, deprecated install…

Communication patterns for feedback, cross-audience content, and eliciting needs. SBI feedback model (Situation → Behavior → Impact), stakes-calibrated review voice, So-What/What/Now-What audience lead for PRs and status reports, and the three-layer Need/Solution/Feature elicitation ladder. Use when giving feedback in a review, writing for a mixed audience (decision-makers + peers + newcomers + skeptics), clarifying an ambiguous ask before committing to a solution, or coaching someone else's communication.

Mixing structure and content makes both hard to…

When extracting hardcoded data to JSON, field values silently…

Previews and configures repository-level defaults for optional Alex ACT plugins while keeping Manager and Core enabled. Use when greeting setup finds no workspace capability profile, when a project needs different plugins than the user default, or when auditing workspace plugin scope.