fabioc-aloha/Alex_ACT_Scout

lint-clean-markdown

Write markdown that passes markdownlint on first attempt — encode the most common rules as muscle memory

markdown-mermaid

Create and maintain Mermaid or custom SVG diagrams as concise visual arguments tied to a document's Big Idea. Use when a diagram must clarify a process, decision, relationship, or state, or when document edits may have made one stale.

markdown-sanitization-chain

Render user-supplied markdown safely — marked.js → DOMPurify → Mermaid (order matters; skipping the sanitizer is XSS)

code-review

Systematic code review for correctness, security, and growth — not just style enforcement

critical-thinking

Challenge what you think is right — alternative hypotheses, missing data, evidence quality, bias detection, falsifiability, and adversarial review

mcp-builder

Build MCP servers for LLM tool integration in Python (FastMCP), Node/TypeScript (MCP SDK), or C#/.NET (Microsoft MCP SDK). Use when authoring a new MCP server, evaluating a candidate MCP for the Plugin Mall, or diagnosing an MCP issue raised by a heir.

plan

Use when the user wants a plan instead of execution, or before any non-trivial implementation (multi-file, architectural choice, > 15 min). Writes a concrete actionable markdown plan with bite-sized tasks (2-5 min each), exact file paths, complete code, and…

problem-framing-audit

Step-back protocol — restate, generalise, specialise, invert, ask why, pre-mortem, check stakeholders, and audit framings before solving

security-and-hardening

Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. OWASP-aware, language-agnostic principles with TypeScript examples — applies to any feature that accepts untrusted data, manages user…

status-reporting

Create stakeholder-friendly project status updates and progress reports. Use when writing a status update, progress report, weekly or milestone recap, release summary, or any stakeholder-facing account of where work stands.

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Four-phase root-cause-first method (investigate → pattern-analyze → hypothesize → implement) that beats guess-and-check thrashing.

chart-big-idea

Distill the central claim a chart should communicate before choosing the chart type, title, or encodings. Use when creating chart titles, figure captions, visual briefs, or deciding whether a chart earns its place.

chart-vocabulary

Choose appropriate chart types and Flint encodings from the analytical task, data shape, and reader goal. Use when selecting among bar, line, scatter, heatmap, histogram, KPI, waterfall, area, donut, and other Flint chart templates.

flint-chart

Author Flint charts in Scout from data, intent, and audience context. Use when creating, selecting, rendering, or refining charts with the Flint MCP tools; pairs with chart-big-idea, chart-vocabulary, and render-verify.

render-verify

Verify rendered visual artifacts before delivery. Use after rendering Flint charts, Mermaid diagrams, SVG figures, screenshots, or image assets to catch invisible output, broken links, unreadable labels, clipped marks, and misleading presentation.

adversarial-review

Structured skepticism for high-stakes decisions and reviews. Six methods — Red Team/Blue Team, Pre-Mortem, Steel Manning, Murphyjitsu, 10/10/10, Cross-Model External Critic. Use before publishing an ADR, plan, proposal, framework edit, or release; when "this…

alex-act-core

Alex ACT Core for Microsoft Scout. Use to orient yourself to the converted ACT skill set, Scout install layout, and where the original skills, instructions, prompts, and references live.

compile-brain

Create or improve a Markdown instruction, skill, prompt, or agent from an explicitly selected file or user-identified text. Use when a user asks to optimize an existing brain artifact or create one for consistent future execution.

component-evidence

Measure package components with transparent static importance from Brain Compiler and opt-in local usefulness outcomes. Use when recording whether an installed skill helped, or when combining those records with a Brain Compiler assessment.

doc-hygiene

Documentation hygiene — anti-drift rules, code-documentation placement, count elimination, and living document maintenance. Use when auditing docs or comments for drift, fixing hardcoded counts and dead links, documenting code for adopters, or deciding…

ethical-reasoning

Ethical reasoning framework for AI decisions — 5 moral foundations (care/harm, fairness, loyalty, authority, sanctity) with priority ordering, constitutional principles (human agency, transparency, beneficence, justice, privacy), 5-step ethical decision…

git-workflow

Apply consistent git practices for branch hygiene, safe commits, and recovery from common mishaps (lost commits, bad merges, accidental pushes), including GitHub CLI account routing. Use when authoring or reviewing a git workflow, recovering broken local…

meditation

End-of-session consolidation workflow that extracts reusable lessons, anti-patterns, gotchas, failure modes, and decisions into the shared Scout knowledge base.

risk-analysis

Probability × impact risk assessment for curation and planning decisions. Categorize risks (quality, coherence, scope creep, token budget, breaking change, staleness), score by likelihood × impact, and route by risk score to ship / gate / ADR. Use before…

scout-greeting-checkin

Run a read-only Alex ACT Scout session-start check when the user opens with hello, hi, or a greeting. Verify package setup, shared data, Flint, and available package releases, then offer explicit maintenance actions.

scout-knowledge-base

Preserve battle-tested session lessons, anti-patterns, failure modes, and reusable decisions in a shared file-based knowledge base for Scout instances.

scout-shared-data-setup

Prepare a user-selected synchronized folder for Alex ACT Scout component evidence and shared knowledge-base records. Use when meditation, component-evidence, or scout-knowledge-base needs its OneDrive-backed infrastructure configured.

spike

Use when the user wants to feel out an idea before committing to a real build — "spike this out", "try it", "is this even possible?", "compare A vs B". Throwaway experiments that decompose into 2-5 feasibility questions, build minimal observable prototypes,…

act-tenets

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…

alex-finch-personality

Keep Alex Finch's stable personality available in Scout: curious, principled, emotionally attentive, independent, concise, calibrated, and grounded in ACT.

anti-hallucination

Prevent fabricated facts, invented APIs, and citation confabulation at the point of generation. Use when generating factual claims, code examples, API references, library names, configuration values, error messages, or citations — anything where 'sounds…

big-idea

Distill the central claim before authoring any summary-shaped output: hero copy, commit-message subject, PR title, ADR title, slide title, executive summary, skill description, abstract. Length is format-dependent (1 sentence for titles, up to a short…

communication-craft

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…

humanizer

Use when the user wants to humanize, de-AI, de-slop, or un-ChatGPT a piece of text — strip AI-isms and add real voice. Scans for 29 documented AI-writing patterns (Wikipedia's "Signs of AI writing") and produces a draft → self-audit → final rewrite. Optional…

mutation-testing

Meta-test your test harness — apply small intentional defects to production code, expect the suite to catch each one. Surfaces silent coverage gaps that 100% line coverage hides.

test-driven-development

Use for any feature, bug fix, refactor, or behavior change — enforces RED-GREEN-REFACTOR. Write the failing test first, watch it fail, write minimal code to pass, refactor. Carve out only throwaway prototypes, generated code, configuration files. Adapted from…

flint-chart-mcp

Set up, diagnose, and register the optional Flint MCP runtime for Microsoft Scout. Use when Flint tools are missing, chart rendering fails, or the user wants to install or repair the visual add-on runtime.

print-svg-style-guide

Produce clean, print-safe SVG and chart styling guidance for documentation and reports. Use when visual artifacts need consistent typography, margins, contrast, export behavior, or compatibility with markdown, PDF, and print workflows.