MyAiFreedomSystems
OrganizationTurn real customer praise into branded testimonial cards worth posting — via Canva or a standalone template.
Categories
Indexed Skills (21)
graphic-testimonials
Create branded testimonial card images from quotes and photos — via the user's Canva template (duplicate, edit text with Canva MCP transactions, export PNG) or the bundled standalone HTML template rendered with headless Chrome. Then recolor to the brand color, composite circular client photos, and wire cards into a web page. Use when the user asks to make, design, or update testimonial cards/graphics/images, or to add social-proof sections to a page. Input is harvested material (quote + name + role + face per client), e.g. from harvest-testimonials.
harvest-testimonials
Fetch testimonials that already exist and collect each client's words and photo. Sources: YouTube channel videos (titles, auto-caption transcripts, face frames via yt-dlp + ffmpeg), web pages (blog testimonial sections), and social/community platforms (Skool, Facebook, LinkedIn, Instagram, blog comments — via a browser-control or computer-use skill in the owner's own logged-in session). Use whenever the user asks to gather, collect, pull, or mine testimonials, reviews, or client quotes from their YouTube channel, website, blog, or social communities — before anything is designed. Output is raw material (quote + name + role + face image per client), and EVERY candidate passes a mandatory qualification gate (script pre-filter + scored rubric) before design. Pair with graphic-testimonials to turn the harvest into branded card images.
hooks-guide
Comprehensive guide to agent lifecycle hooks across platforms. Covers what hooks are, when they fire, safety rules, universal patterns (pre-dispatch validation, post-converge logging, compaction survival), platform-specific adapters for Hermes, Claude Code, Codex, Cursor, OpenCode, and others, and registration/installation instructions per platform. Use when designing governance enforcement, pre-flight checks, audit trails, or any hook-based automation.
provision-project
Provision a project folder for AI agent work with governance files, directory skeleton, session ledger, and platform-specific agent overlays. Produces a fully scaffolded workspace that agents on any platform (Hermes, Claude Code, Codex, Cursor, OpenCode, etc.) can use immediately. Use when creating a new project, initializing a workspace, or standing up a fresh agent-ready folder.
hooks-guide
Comprehensive guide to agent lifecycle hooks across platforms. Covers what hooks are, when they fire, safety rules, universal patterns (pre-dispatch validation, post-converge logging, compaction survival), platform-specific adapters for Hermes, Claude Code, Codex, Cursor, OpenCode, and others, and registration/installation instructions per platform. Use when designing governance enforcement, pre-flight checks, audit trails, or any hook-based automation.
provision-project
Provision a project folder for AI agent work with governance files, directory skeleton, session ledger, and platform-specific agent overlays. Produces a fully scaffolded workspace that agents on any platform (Hermes, Claude Code, Codex, Cursor, OpenCode, etc.) can use immediately. Use when creating a new project, initializing a workspace, or standing up a fresh agent-ready folder.
testimonial-display
Place testimonials on websites and sales pages for maximum trust and conversion. Use when placing testimonials on a page, building a wall of love, adding a testimonial slider or carousel, deciding where social proof goes on a sales page, designing a testimonial section layout, choosing between grid/masonry/slider/video embed/star-rating snippet patterns, interleaving testimonials through long-form copy, or auditing testimonial placement for accessibility, performance, and authenticity.
logo-theme-manager
Build and maintain a true theme system for websites. Use when replacing a logo, swapping a favicon, generating a favicon set, building a token-based theme.css with CSS variables, auditing brand consistency across a site, hunting down hard-coded hex colors in pages, tracking every copy of a logo across a project, or making sure a brand change reaches every page, template, and clone. Prevents the classic failure where logo files, colors, and favicons get missed when a brand changes.
moe-build-team
Multi-model expert team orchestration for high-quality build execution. Assembles a panel of AI voices with role-specific lenses, drives research and planning to convergence, and delivers through the user's proof surface. Distills a proven operational codebase into a distributable governance protocol.
provision-agent
Provision a new AI agent with identity overlays, scoped skills, tool constraints, handler profile, and memory structure. Creates SOUL.md, TOOLS.md, MEMORY.md, and USER.md files on top of the project scaffold. Extends provision-project with agent-specific identity. Use when creating a named agent, standing up an agent identity, or binding skills and tools to a new agent instance.
provision-team
Provision a new agent team with identity, composition, governance, and orchestration protocol. Creates TEAM_IDENTITY.md, TEAM_COMPOSITION.md, TEAM_GOVERNANCE.md, and registers the team in the governance nucleus. Use when assembling multiple agents into a coordinated team for a shared purpose — code review squads, build teams, research panels, or any multi-agent workflow.
routing-matrix
Configure a multi-model routing matrix for AI agent orchestration. Define role assignments, model pools, provider lanes, fallback chains, and dispatch policies. Ships as a user-fillable YAML template — pre-populated with role structure and governance policies; the user fills in model names, providers, and ban lists. Use when setting up agent team orchestration, defining which models serve which roles, or configuring automated model dispatch.
goal
IncredAgents /goal command — structured planning + launch infrastructure (Swarm Heartbeat, Telegram) + stateful execution + workspace governance. Fuses plan-for-goal (planning discipline) with persistent state management plus quad-logging, approval gates, completion audit, and Pacific Time.
graphics
Canonical graphics skill. One entry point for every visual asset the user generates — graphics, images, infographics, banners, slides, diagrams, logos, mockups, posters. Eight curated styles A through H with example-led picker, ASK-FIRST discipline, and the safe pipeline guarantees. Triggers on graphics, image, infographic, banner, slide, diagram, logo, mockup, poster, generate an image, render, design a, make a picture of, "remake this slide", visual asset.
wrapup
End-of-session fidelity-first wrapup. Captures what happened, reviews it, drafts a session summary, runs a review pass (self-review or Mixture-of-Experts (MOE) Kaizen), and archives to user-configured destinations. User-agnostic and distributable — destinations, formats, and paths are defined in config/wrapup.config.json, never hard-coded.
pre-flight-check
Mandatory pre-delivery quality gate for any artifact — websites, pages, images, documents, generated files. Use before delivering, shipping, deploying, or presenting any work as done, and whenever the user asks for a review, QA pass, or pre-launch check. Runs truth checks (no fabricated people, quotes, or numbers), copy review, versioning, link verification, geometry-based visual verification across the full breakpoint sweep (not just desktop and phone), a measurable review-team pass, and an honest delivery report. Prevents shipping unverified work.
package-public-skill
Prepare a private agent skill for public release on GitHub — evaluate standalone usefulness, scrub personal names/paths/machine details, generate README + CHANGELOG + LICENSE, build a themed landing page from the house site template, and package a .skill zip. Use when the user wants to publish, open-source, sell, give away, or "prep for GitHub" any skill, or when working inside the SkillManager_Public release pipeline.
takemycourseforme
Extract a paid online course from Skool or Circle into ADHD-friendly cliff notes (a TLDR + scannable study guide) plus a "know enough to build/implement it" handoff. Trigger on phrases like "extract this course", "cliff notes", "study this course", "TLDR the course", "summarize my course", "study guide", "course extraction", or when the user names Skool or Circle. Teaches the full pipeline: auth (never headless for Skool), course-tree mapping, resumable lesson capture (text + resource links to the downloadable ZIP/PDF files that are the real deliverables), video + transcript pull (yt-dlp/Whisper, Step 4), transcript cleanup, deep read, gap analysis, and the implementation handoff.
brief-me
Slash-invoked as `/brief-me`. The user's single trigger to receive a converged multi-model team advisory report on a decision or research topic the conversation already established. The agent assembles the brief from six required team voices (Researcher, Advisor, Kaizen 1, Kaizen 2, Linter, Builder), renders it into a single self-contained local HTML file from the shipped template, opens it on the user's screen, and the user clicks "Copy my answers" and pastes their picks back into chat. The assembling agent is never a voice in the brief.
kaizen
Establishes Kaizen as Claude's working discipline — continuous, small, process-oriented improvement applied to every artifact, every session, and every decision. Use alongside the Prime Directive and the Four Currencies framework. The Prime Directive chooses which action Claude takes next. Kaizen governs how Claude does that action so the underlying system ends up stronger than before the action was taken. Load this at the start of every session with anchor. Re-read when Claude notices itself defaulting to big-bang rewrites, perfectionism, one-shot deliverables, or polishing trivia instead of iterative, standards-based refinement.
pre-build-sop
Force real preparation before building anything. Activate whenever the request contains "build", "create", "make", "set up", "train", "implement", "develop", "scaffold", "add a feature", "integrate", or any word that means producing code, files, schemas, pipelines, or systems. This skill prevents the most destructive failure mode in this workspace — pattern-matched building without verified current knowledge or observed inputs. Pairs with qa-protocol (which enforces verification at the end); this skill enforces verification at the beginning. If both skills apply, run pre-build-sop first and qa-protocol last.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.