fabioc-aloha

Safely consume an MCP server someone else wrote — evaluate it before installing, register it correctly, scope its credentials, and diagnose it when it misbehaves.

Implement an MCP server in TypeScript, Python, or C#/.NET, and register it with a host. Working stdio and HTTP samples verified against the published SDKs.

Decide whether to build an MCP server, which protocol primitives to expose, and how to design tools an agent can actually use. Covers transports, language choice, and the tools/resources/prompts split.

Secure an MCP server that is reachable over a network — host-name validation against DNS rebinding, CORS restraint, authentication, secret handling, and the confused-deputy problem.

Ship, version, and run an MCP server after it works — packaging and distribution, breaking-change discipline, deployment shapes, and debugging failures that only appear under a host.

Prove an MCP server works and that an agent can actually use it. Covers the Inspector, a ten-question evaluation set, and the difference between responding correctly and being usable.

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.

Clear documentation through visual excellence

End-to-end academic paper drafting for CHI, HBR, journals, and conferences with venue-specific templates, drafting workflows, and revision strategies.

Detect, create, and manage the AI-Memory fleet communication channel. Fires on bootstrap, session start (announcements), and feedback writes.

Generate on-brand Alex — ACT Edition SVG banners for documents (READMEs, plans, notes, release artifacts)

Patterns for fiction, narrative structure, character development, dialogue, and storytelling craft.

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

Convert Word documents (.docx) to clean Markdown with image extraction and pandoc cleanup

Greeting-triggered self-check — recognise greetings, check Edition version against the upstream tag, scan AI-Memory announcements, and report inside the greeting reply

Convert HTML documents to clean Markdown via pandoc

Create and maintain ASCII visual dashboards for project tracking with parallel lane progress bars

Store and manage voice samples for TTS cloning — portable, version-controlled audio references

Clear documentation through visual excellence

AI music generation via Replicate — 5 models for background tracks, lyrics, and sound design

Practitioner methodology for longitudinal case study research, evidence-based documentation, and publication-ready academic writing in AI-assisted development.

First impressions matter. Set projects up for success.

Cloud TTS via Replicate — 15 models, voice cloning, emotion control, and multi-language support

AI video generation via Replicate — 17 models, editing, and production workflows

Run the 7-step Artificial Critical Thinking pass — Materiality → Hypothesise → Alternatives → Disconfirmers → Audit priors → Severity → Commit-with-marker

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

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

Build knowledge bases that build software — research before code, teach before execute

Two-phase brain upgrade — mechanical install via shared core, then LLM-led semantic reconciliation

Clear documentation through visual excellence

End-to-end academic paper drafting for CHI, HBR, journals, and conferences with venue-specific templates, drafting workflows, and revision strategies.

Patterns for fiction, narrative structure, character development, dialogue, and storytelling craft.

Patterns for thesis writing, dissertations, research papers, literature reviews, scholarly work, and venue-specific publication drafting

Debug skill/hook/agent loading issues using VS Code's Agent Debug Panel

**Domain**: AI/ML Architecture

Generate consistent visual character references across multiple scenarios using Flux and nano-banana-pro on Replicate

Create professional ultra-wide cinematic banners for GitHub READMEs using Flux and Ideogram models with typography options

Help writers produce content that sounds genuinely human by avoiding telltale AI-generated text patterns

Domain knowledge for AI adoption measurement, psychometric instrument development, and appropriate reliance research

Estimate task duration from an AI-assisted development perspective rather than traditional human developer estimates

Focus blocks, distraction management, and flow state triggers for cognitively demanding work

Internal metacognitive skill for automatic capability discovery — self-triggers when uncertain about available skills

End-to-end academic paper drafting for CHI, HBR, journals, and conferences with venue-specific templates, drafting workflows, and revision strategies.

Patterns for thesis writing, dissertations, research papers, literature reviews, and scholarly work.

**Domain**: AI/ML Architecture

Domain knowledge for AI adoption measurement, psychometric instrument development, and appropriate reliance research

Practical application of AIRS psychometric assessment for AI readiness, reliance calibration, and adoption optimization

Estimate task duration from an AI-assisted development perspective rather than traditional human developer estimates

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…

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…

Read-only audit for AI-tell prose: scan text against the humanizer's pattern catalog plus the project's house AI-tell list, and return a density verdict with a Major/Minor findings table and minimal recasts. Never rewrites. Use for pre-publish checks when the…

Render charts and compact dashboards as pure ASCII in a monospace grid: bar, dot, sparkline, histogram, box plot, scatter, bubble, heatmap, funnel, waterfall, treemap, gauge, KPI card, and more. No rendering engine, no SVG, no browser, no MCP server. Use when…

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…

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…

Read a chart someone else made — image, screenshot, HTML, or dashboard — and extract insights, patterns, anomalies, and misleading framing. The reverse of authoring. Use when handed a chart to analyze, when checking whether a chart's visuals support its…

Catalog of chart types organized by seven communication goals (comparison, change over time, proportion, distribution, relationship, flow, deviation), with a selection algorithm, an evaluation loop for AI-suggested charts, and density limits for dashboards.…

Defense-in-depth, PII protection, secrets scanning, and secure packaging for distributed software

Systematic testing for confidence without over-testing — the right test at the right level

Generate consistent visual character references across multiple scenarios using Flux and nano-banana-pro on Replicate

Create professional ultra-wide cinematic banners for GitHub READMEs using Flux and Ideogram models with typography options

Generate professional presentations using the Gamma API with expert storytelling consulting based on Duarte methodology.

Intelligent project persona identification using priority chain detection with LLM and heuristic fallback

Reusable patterns for VS Code extension development.

Domain knowledge for AI adoption measurement, psychometric instrument development, and appropriate reliance research

Use when the user wants to humanize, de-AI, de-slop, or un-ChatGPT a piece of text — review AI-associated patterns and add real voice — or wants a copywriter pass that reviews existing copy for a named audience (e.g., non-native English readers) using an…

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.

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.

Activates, verifies, repairs, or removes this plugin's user-scope runtime instructions from canonical installed sources. Use after installing or updating Alex ACT ONE, when ACT behavior or Alex Finch identity is inactive, or when bootstrap receipt hashes…

Assess active Markdown brain files in a local AI agent project or plugin source without changing it. Use before modifying a brain or reviewing declared instructions, skills, prompts, agents, bundled Markdown resources, and research documentation.

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…

Previews and applies this plugin's repository scaffold, portable workspace QoL settings, and project Copilot settings while preserving project-owned files. Use for new repositories, missing AGENTS/HANDOFF/episodic files, or project .vscode setup.

Review session outcomes, recommend reusable skills or automation, and reconcile project guidance, handoff, tasks, and change history.

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

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.

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

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

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

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.

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…

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

Author markdown and Mermaid diagrams that render correctly in VS Code, GitHub, and other Mermaid 10+ consumers — covers diagram-tool selection, mandatory init template, parser pitfalls, and visual design rules. Use when writing technical docs with embedded…

Create agents that pass agent-review's six gates by construction — role capture, distinct-from-skill check, tool allowlist minimization, draft against gates, dogfood self-review. Use when authoring a new agent, refactoring an existing one, or promoting a Mall…

Audits a candidate agent (.agent.md) against five gates (spec compliance, content quality, scope fit, safety, currency & coherence) plus Gate 6 (tool allowlist minimality). Use when reviewing a new agent draft before commit, evaluating a Mall agent or store…

Detect, resolve, and manage the Alex_ACT_Memory shared memory bus. Fires on bootstrap, session start (announcements), and feedback writes.

Generate on-brand Alex — ACT Edition SVG banners for documents (READMEs, plans, notes, release artifacts)

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…

Perform a local brain audit for ACT Edition (and Supervisor) using deterministic QA plus targeted file review, then produce severity-ranked fixes. Pairs with extension-audit on the sibling surface side; the Marketplace surface routes there, not here.

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

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

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 — or wants a copywriter pass that reviews existing copy for a named audience (e.g., non-native English readers) using an…

Activates, verifies, repairs, or removes Core's 17 user-scope runtime instructions from canonical installed sources. Use after installing or updating Core, when Core identity or ACT behavior is inactive, or when Core receipt hashes drift.

Previews and applies Core's repository scaffold, portable workspace QoL settings, and project Copilot settings while preserving project-owned files. Use for new repositories, missing AGENTS/HANDOFF/episodic files, or project .vscode setup.

Author Mermaid diagrams that render correctly in GitHub, VS Code, and Mermaid 10+ consumers. Applies a config-driven init directive + linkStyle + semantic classDef vocabulary from `.github/config/brand-palette.json` (default: 6-role semantic palette +…

Preview, apply, or validate the curated read-in-place bridge from the global Copilot plugin store into Scout. Use after a Copilot plugin update, when Scout cannot resolve a bridged skill, or before adding a skill to the Scout allowlist.

Consolidate session learning into permanent architecture — extract patterns into skills, instructions, prompts, native memory, or repository handoffs

Applies cross-session context recovery, uncommitted-work detection, and focus routing after the resident instruction decides proactive behavior is appropriate. Use when continuity, worktree state, or active goals may change the response.