fullREFIT

@fullrefit source repo

33 skills
0 followers
11 hours ago last updated

▌
Start Session · fullrefit bundle
Cross-surface session-start protocol (Claude Code, Codex, Cowork, Desktop, web). AUTO-DETECTS the right resume path — no flag to remember: on every run it first looks for a deep-save CONTINUATION-BRIEF for the project; if one exists it resumes from the brief ONLY (~1-3k tokens, skips claude --continue) so you never reload a bloated transcript; if none exists it warm-starts (claude --continue, else Open Brain + local files + archaeology) and presents a synthesized summary with Final Exchange. Optional overrides: --full forces the complete reload even when a brief exists; --fresh forces brief-only. Applies the Brain-First Rule for the session. MANDATORY TRIGGERS: start session, start-session, resume, resume session, pick up where we left off, continue session, where did we leave off, restart project, restart session, what was I working on, resume project, fresh start, warm restart, resume without bloat, load the brief, continuation brief resume, --fresh, --full.

0
installs
▌
Signal Scanner · fullrefit bundle
Internal build/activity content scanner for creators and builders. Mines your own builds, agent sessions, automations, runbooks, debugging work, docs, tools, deployments, and operating activity for proof-backed content and revenue opportunities, then routes them through your Revenue-Content Engine without making you the failure case. MANDATORY TRIGGERS: signal scanner, scan this build, scan my activity, mine this build, content from this build, content from my work, content opportunity, scan this session, scan this project, repurpose this build, what content is in this, build story, activity scan, proof scan, /signal-scanner, /scan.

0
installs
▌
Claude Md Forge · fullrefit bundle
Turn source material — a Claude or ChatGPT conversation, a YouTube or podcast transcript, a strategy doc, notes — into a topic-specific agent context file (CLAUDE.md for Claude Code, AGENTS.md for Codex CLI and Cursor, or AGENTS.md plus a thin CLAUDE.md shim for a shared repo), so every future session in that directory operates with the strategy, tactics, vocabulary, and rejected paths from that source. Distills rather than summarizes: keeps only what changes agent behavior, pushes depth to docs/, refuses to produce README-style documentation. MANDATORY TRIGGERS: CLAUDE.md, AGENTS.md, agents md, claude md, turn this transcript into a CLAUDE.md, make an AGENTS.md from this conversation, convert this chat into project context, capture this session's knowledge, topic CLAUDE.md, domain context file, persistent context from transcript, YouTube transcript to CLAUDE.md, seed a project with this knowledge, agent memory from this conversation, claude-md-forge.

0
installs
▌
Skill Architect · fullrefit bundle
Comprehensive skill creation, improvement, and packaging following the agentskills.io open standard. Produces deployment-ready .zip files for upload to Claude.ai, Claude Desktop, Claude Code, Cowork, or any agentskills.io-compatible platform. Use when building new skills from scratch, auditing or improving existing skills, authoring SKILL.md files, configuring frontmatter, structuring bundled resources, or packaging skills for distribution. Handles the full lifecycle: intent capture, resource planning, SKILL.md authoring, validation, packaging, and iteration. MANDATORY TRIGGERS: skill creation, SKILL.md, skill improvement, skill audit, frontmatter, skill packaging, agentskills.io, progressive disclosure, skill validation, skill architecture, bundled resources, create a skill, build a skill, package a skill, new skill, update skill, improve skill.

0
installs
▌
Skill Translate · fullrefit bundle
Port a skill from one AI coding or chat platform to another. First checks whether translation is needed at all: Claude Code, Codex CLI, Cursor, and other Agent Skills-standard tools take the same SKILL.md unchanged, so those are installs, not conversions — copy the folder and validate. Genuine translation applies only to platforms with proprietary formats: ChatGPT Custom GPTs plus Actions, Gemini Gems and GEMINI.md, Perplexity Spaces, Hermes Agent. Maps each component to the target's character limits, MCP support, and file format. MANDATORY TRIGGERS: skill translate, convert skill, port skill, install this skill everywhere, install skill in codex, install skill in cursor, sync my skills across tools, does this skill work in cursor, skill for chatgpt, skill for gemini, skill for perplexity, skill for hermes, translate to chatgpt, translate to gemini, cross-platform skill, make this work in chatgpt.

0
installs
▌
Web App Builder · fullrefit bundle
Convert one or more markdown files into a single-file HTML web application using the default design system (Carbon Forge). Handles full content analysis (format selection, interface pattern selection), responsive rendering (collapsible sections, tabs, sidebar navigation, interactive checklists, code blocks with copy buttons, styled tables, callout boxes), and single-file HTML output (all CSS and JS inline, no build step, no frameworks). Outputs are browser-ready HTML files. MANDATORY TRIGGERS: web app from markdown, markdown to HTML, convert markdown, web app builder, web app, single-file app, HTML from docs, interactive docs, doc viewer, markdown viewer, documentation site, web app from docs, build me a web app.

0
installs
▌
Loop Goal Triage · fullrefit bundle
Triage any task, prompt, or project to the right execution method, then rewrite the prompt to run that way in Claude Code or Hermes. The space is five-way, not a binary: a plain prompt (most tasks), /goal or Hermes goal-mode (drive one task to a verifiable finish), timer polling (/loop or Hermes cron), dynamic workflow or delegation, or a durable Routine or Hermes cron/webhook job. Built to prevent the core failure: forcing generative or judgment-heavy work into a loop, where quality drifts as the model pattern-matches its own output. Splits deterministic sub-steps that can loop from generative cores that cannot. MANDATORY TRIGGERS: loop or goal, /goal vs /loop, should I loop this, loop-goal-triage, Hermes loop, Hermes goal, Hermes cron, how should I run this, autonomous run, batch this directory, point claude code at, convert to a loop, execution method, should I automate this, promote to a routine, run this unattended, can I run this in cowork, which surface, /goal vs routine, dynamic workflow vs goal.

0
installs
▌
Github Repo Setup · fullrefit bundle
Repository-agnostic setup agent that clones, inspects, installs, and smoke-tests any GitHub repository using the repo's own manifests rather than assumptions. Detects language stack (Node, Python, Rust, Go, Ruby, Deno, Bun, Docker) from lockfiles, aligns toolchains via version managers (nvm, pyenv, rustup, asdf, mise), installs with the correct package manager, handles .env setup, runs a minimum smoke test, and produces structured phase reports. Optimized for macOS arm64 with Homebrew, nvm, pyenv, and 1Password CLI; branches for Linux and Windows. Use when setting up a cloned repository, evaluating a new GitHub project, reproducing an environment, or onboarding a codebase. MANDATORY TRIGGERS: github repo setup, clone and install, repo setup, set up repository, install this repo, set up this project, onboard codebase, reproduce environment, new repo, fresh repo, get this repo running, set up dev environment, repo install, universal setup, github setup.

0
installs
▌
Gamma Optimization · fullrefit bundle
Transform raw content into Gamma.app-optimized presentations, documents, and webpages. Use when users need to create professional Gamma content from unstructured materials, optimize existing content for Gamma, or need guidance on Gamma settings and workflows. Handles tier-specific limitations (Free/Plus/Pro/Ultra), structure-first methodology, and SPLICE image prompting.

0
installs
▌
Vibe Coding Router · fullrefit bundle
Route vibe-coding work to the right agent skill/tool without loading a mega-prompt. Use when you are building, planning, debugging, QAing, shipping, or content-mining software with Claude Code, Codex, or another LLM; when a request mentions vibe coding, super-app, command center, skill routing, design-taste, superpowers, Agent-Native, Mastra, or choosing which installed skill/tool should drive the next phase. MANDATORY TRIGGERS: vibe coding, vibe-coding-router, super-app, command center, choose skills, route skills, phase router.

0
installs
▌
Plan Execute Router · fullrefit bundle
Executes the plan/execute model routing pattern to cut AI-workflow cost by 50–75% on feature builds, refactors, and migrations. Claude plans the task at frontier capability and produces a detailed spec, then routes execution to a cheaper model — via Codex CLI subprocess if available, a Claude Code subagent scoped to a smaller model, or manual copy-paste instructions when neither path exists. Optionally invokes a frontier review pass on the executor's output. Includes fit-check to detect when a task does NOT fit the pattern and cost estimation for the specific split chosen. MANDATORY TRIGGERS: model routing, plan-execute, plan then execute, route to cheaper model, delegate execution, split planning from execution, cheaper executor, cost split, plan-execute-router, model split, use Codex for execution, use Sonnet for execution, spec-then-code, spec then code, save on this build, cost-optimize this task.

0
installs
▌
Project Doc Refresh · fullrefit bundle
Audit, research, and refresh Claude Project custom instructions and project documents so they reflect current Claude platform capabilities (Skills 2.0, MCP, subagents, caching, model routing) and current domain facts. Use when the user wants to update a CLAUDE.md, custom instructions, project documents, system prompts, or any long-lived context document that may have gone stale. Three-phase workflow — audit first, research only flagged items, produce a tracked-changes diff the user approves before finalizing. Never rewrites voice, behavioral rules, or institutional knowledge. MANDATORY TRIGGERS: refresh custom instructions, update project documents, audit CLAUDE.md, update system prompt, refresh project context, is my prompt stale, update my Claude project, modernize instructions, refresh skill docs, project doc audit, instructions audit, context refresh.

0
installs
▌
Claude Release Guide · fullrefit bundle
Convert shallow source material about a new Claude product or feature release (YouTube transcripts, blog posts, docs, announcements, pasted text) into a verified, teaching-grade implementation guide with prerequisites, exact steps, decision frameworks, edge cases, and cited sources. Specialized sibling to transcript-deep-dive: adds primary-source verification against claude.com and support docs, cross-references multi-source input for contradictions, outputs guides for teaching (Skool, LinkedIn, lead magnets, workshops) Use for Claude Design, Claude Code, Claude Cowork, Skills, MCP, Opus/Sonnet/Haiku model drops, pricing changes, platform features. MANDATORY TRIGGERS: claude release guide, new claude feature, claude release, claude announcement, claude product guide, teach a claude feature, claude how-to, new opus model, new sonnet model, new haiku model, claude design guide, claude code release, claude cowork release, release breakdown, feature deep dive.

0
installs
▌
Project Orchestrator · fullrefit bundle
Multi-platform AI project orchestrator that decomposes projects into routed task plans across Claude Cowork, Claude Code, Cursor, Warp.dev, n8n, and other AI tools. Use when the user provides project details (website build, brand identity, HR campaign, product launch, etc.) and needs an execution plan distributed across multiple AI platforms. Triggers on phrases like "orchestrate this project", "plan this across tools", "break this down", "create a task plan", "route this project", or any multi-phase project that would benefit from cross-platform execution. Also triggers when user provides a project brief, PRD, or scope document and wants it turned into actionable task files.

0
installs
▌
Public Release Audit · fullrefit bundle
Audit a private skill, prompt, framework, protocol, or project for safe public release, determine whether it is original and portable, choose the right package shape, generalize private dependencies, and produce a verified publication checklist. Use before publishing agent skills, prompts, protocols, frameworks, templates, or project artifacts to a public repository. MANDATORY TRIGGERS: public release, open source, publish, package for GitHub, make public, audit for publication, sanitize skill, generalize prompt, private to public.

0
installs
▌
Trafilatura Research · fullrefit bundle
Use Trafilatura for fast extraction of clean article text, metadata, and Markdown from web pages. Best for research corpora, article cleanup, and preparing sources for summaries or retrieval.

0
installs
▌
Tiktok Carousel Forge · fullrefit bundle
Produce TikTok vertical carousel image sets (1080×1920 PNG, 9:16) from an existing LinkedIn carousel package. Reads LIC-linkedin-carousel/slides/ HTML files, reflows each slide to the vertical canvas using documented reflow rules, renders via Playwright Chromium, verifies every PNG is exactly 1080×1920 and non-blank, writes a tt-caption_{slug}_{MMDDYY}.md file, and stages everything into TT-tiktok-carousel/. Works standalone for re-renders after carousel revisions. Brand tokens (wordmark, tagline, colors) are set in config.example.md. MANDATORY TRIGGERS: tiktok carousel, TT carousel, tiktok post, tiktok images, produce tiktok, build tiktok, tt-carousel, tiktok-carousel-forge, TikTok PNGs, re-render tiktok, tiktok content, vertical carousel, 9:16 carousel.

0
installs
▌
Proof Shortio Airtable · fullrefit bundle
This skill creates Proof documents from Markdown or draft content, creates or reuses Short.io links for them, and records the result in Airtable. Use it when you want a seamless Proof link workflow, when a Proof document URL needs a shortlink, when creating tracked Proof docs, when troubleshooting Proof to Short.io to Airtable syncs, when configuring the automation, or when checking activation status. MANDATORY TRIGGERS: Proof shortlink, create Proof link, tracked Proof link, proof-shortio, proof-shortio-airtable, proof-shortlink-Airtable, proof-shortlink-airtable, Proof.ai Links, Short.io, Airtable shortlink, proof share URL.

0
installs
▌
Skill Install Protocol · fullrefit bundle
Install, distribute, and verify an existing agent skill from one canonical source across the client environments that are already present. Use when fanning out a skill, installing a skill from a repository, rebuilding client copies, checking ZIP parity, or verifying a skill installation. MANDATORY TRIGGERS: install skill, distribute skill, fan out skill, copy skill, skill parity, skill ZIP, install protocol, client skills.

0
installs
▌
Linkedin Carousel Forge · fullrefit bundle
Produce LinkedIn carousel PDFs and infographic PDFs using a configurable design system. Handles the full pipeline: content strategy (pain point mapping, narrative arc, slide sequencing), slide design (typographic posters, data comparisons, before/after layouts, CTA slides), HTML rendering, and PDF export. Outputs are upload-ready for LinkedIn's document carousel format. Also creates standalone infographic PDFs for single-image posts. Self-contained with complete brand system included — configure brand tokens in config.example.md. MANDATORY TRIGGERS: LinkedIn carousel, carousel post, carousel PDF, LinkedIn slides, infographic, infographic PDF, social graphic, LinkedIn graphic, carousel design, LinkedIn PDF, slide deck, branded slides, social media graphic, branded carousel.

0
installs
▌
Instagram Carousel Forge · fullrefit bundle
Produce Instagram carousel image sets (1080×1080 PNG) from an existing LinkedIn carousel package or content brief. Copies and renames slide PNGs from LIC-linkedin-carousel/slides/, verifies each image is exactly 1080×1080 and non-blank, writes an ig-caption_{slug}_{MMDDYY}.md caption file, and stages everything into IG-instagram-carousel/. Works standalone for re-renders after carousel revisions, MANDATORY TRIGGERS: instagram carousel, IG carousel, instagram post, instagram images, produce instagram, build instagram, ig-carousel, instagram-carousel-forge, IG PNGs, re-render instagram, instagram content, instagram slides.

0
installs
▌
Youtube Screen Share Forge · fullrefit bundle
Produce branded full-screen presentation slides for YouTube screen sharing in Ecamm Live. Takes a video script's framework section or concept spec and produces a single self-contained HTML file (1920x1080, 16:9) with keyboard-navigable slides. Templates: framework overview, concept reveal, before/after comparison, process flow, data/stat, diagnostic checklist, system architecture, chapter title, summary. Browser capture in Ecamm Live — no additional tools required. MANDATORY TRIGGERS: YouTube screen share, screen share slides, Ecamm slides, framework slides, YouTube slides, presentation slides, screen share forge, video presentation, /youtube-screen-share-forge, /screen-share-forge, /yt-slides, build the slides, make the slides, screen share deck.

0
installs
▌
Interactive Checklist Skill · fullrefit bundle
Build interactive checklist, task tracker, and action item web apps as self-contained HTML files. Outputs single-file HTML with inline CSS and JS, deployable to Vercel via drag-and-drop. Features include multi-open accordions, per-item notes with HAS NOTES badges, structured markdown export for LLM consumption, checkbox state management with progress tracking, tabbed navigation by execution context, copy-to-clipboard on all code blocks, MANDATORY TRIGGERS: checklist, task tracker, action items, task list, to-do list, runbook tracker, step tracker, interactive checklist, checklist web app, task tracker app.

0
installs
▌
Presentation Deck Builder V2 · fullrefit bundle
Builds branded, keyboard-navigable presentation websites from structured report JSON. Provides four built-in brand profiles, a custom-brand workflow, an isolated renderer, content-budget validation, tests, and production build steps. Use for presentation websites, operator briefings, research decks, decision decks, branded reports, or converting source material into a navigable deck. MANDATORY TRIGGERS: presentation deck, slide deck, presenter website, report deck, branded deck, custom brand, Carbon Forge, TabSquirrel.

0
installs
▌
1pw Env · fullrefit bundle
Manage credentials across all projects using the 1Password environment variable system. Handles op run zero-disk secret injection, syncing credentials from 1Password vault to shell environment, adding new credentials, service account setup for AI agents, SSH agent integration, SDK usage, rate limit awareness, and troubleshooting auth failures. Covers: 1Password vault → op run → subprocess (preferred) and vault → op CLI → ~/.env.1p.tpl → ~/.env.mcp → shell (fallback). MANDATORY TRIGGERS: 1password, credentials, env vars, environment variables, API key missing, auth failure, credential sync, op CLI, secrets management, .env.mcp, credential setup, new credential, Touch ID timeout, vault, shell plugins, biometric auth, service account, SDK, op run, SSH agent, rate limit, Connect Server, Environments, agentic autofill, OP_SERVICE_ACCOUNT_TOKEN, op run wrapper.

0
installs
▌
Clearpath · fullrefit bundle
File and folder naming and organization system (ClearPath v3.0). Renames and reorganizes files to one legible convention: lowercase-hyphens for words, UPPERCASE format/platform prefixes (LF, SF, LIC, LI...) on subfolders and files, underscore as a segment separator that joins co-equal topics and precedes the date, MMDDYY dates (month-first, never ISO or YYMMDD), topic-based folders, 4-level soft depth, never an empty folder. Reorganizes WITHIN a topic's own home, never into a global type-based master folder. Workflow: scan, show a BEFORE/AFTER tree, get approval, execute with copy-first safety and before/after tree snapshots archived to _archive/. Use when creating, renaming, organizing, or auditing files and folders. MANDATORY TRIGGERS: clearpath, organize files, rename files, naming convention, file naming, folder structure, audit directory, naming compliance, file organization, clean up folder, restructure folder, tidy directory.

0
installs
▌
Deep Save · fullrefit bundle
Extract and save a long conversation to a knowledge MCP (e.g., Open Brain or equivalent) with signal/noise triage and permanence classification, AND write a durable cross-surface CONTINUATION-BRIEF for token-cheap fresh-context resume. Classifies every extractable item into three permanence tiers (permanent for decisions/rules/person notes, long-lived at 120-180 days, short-lived at 30-90 days), deduplicates, batch-writes with permanent/stale_after flags, links thoughts, then writes a 1-3k-token brief (local file + knowledge MCP) so a cleared/fresh window — on any surface incl. Cowork/Desktop — can resume the exact thread without reloading the full transcript. Works on any Claude surface with a compatible knowledge MCP. MANDATORY TRIGGERS: deep save, save this conversation, save chat to brain, extract and save, long save, full save, save everything important, save session to open brain, capture conversation, brain dump, continuation brief, warm restart prep, save before clear, prep for fresh context.

0
installs
▌
Prep Project · fullrefit bundle
Analyze a project folder and produce executor-ready specification packages. Auto-routes deliverables to Cowork (content, research, docs, analysis) or the Claude Code task-orchestrator (bash, MCP tools, deployment, Git), and produces both packages when a project spans surfaces. Outputs a single COWORK-BATCH.md (Cowork) or a 5-file spec — README.md, 00-PROJECT-INDEX.md, CLAUDE-TASKS.md, SPECS.md, DEPENDENCIES.md (orchestrator). Every task is self-contained with an absolute output path and verifiable acceptance criteria. Use when decomposing a project into autonomous-execution-ready tasks. MANDATORY TRIGGERS: prep project, prepare project, prep for cowork, prep for orchestrator, prep for execution, project spec, execution spec, batch execution prep, task decomposition, cowork batch, orchestrator spec.

0
installs
▌
Script Forge · fullrefit bundle
Evaluate source material (transcripts, articles, competitor videos, news) against your content strategy, voice system, and target audience fit. Three possible verdicts: REJECT (with reasons), CONDITIONAL (with requirements), or APPROVE AND PRODUCE (delivers a full teleprompter-ready script formatted for spoken on-camera delivery). Handles both long-form (8-12 min YouTube) and short-form (45-90 sec Shorts/Reels). Enforces your brand's voice/tone operating system (TOV OS) across stance, editorial guardrails, teleprompter delivery, and hooks/flow/retention. Also enforces RESTART-DISCIPLINE. Will refuse to produce scripts from source material that fails the evaluation gate. MANDATORY TRIGGERS: script forge, /script-forge, make a script from this, can I use this, evaluate this content, turn this into a video, script from transcript, script from article, would this work for my audience, reframe this, competitor reframe, write a script, teleprompter script, teleprompter formatting, /sf.

0
installs
▌
Gpt 5 6 Relay · fullrefit bundle
Route one task through model-specific GPT-5.6 child threads with explicit thinking efforts and checkable handoffs.

0
installs
▌
Logo Designer · fullrefit bundle
Professional logo and visual identity design system that translates brand strategy into optimized AI image generation prompts for external tools. Creates comprehensive visual identity concepts using methodologies from 11 elite design studios. Generates tool-specific prompts for Midjourney, DALL-E, Ideogram, Flux, Freepik, and Google Nano Banana Pro. Use when you need logo prompts to run in external AI tools rather than direct in-session generation. MANDATORY TRIGGERS: logo prompts, AI logo prompts, logo concepts, visual identity prompts, Midjourney logo, DALL-E logo, Ideogram logo, Flux logo, logo prompt suite, logo prompt engineering, logo ideas, prompt for logo, logo prompt.

0
installs
▌
Skill Creator · fullrefit bundle
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) update or modify an existing skill, (8) validate a skill, (9) learn about skill structure, (10) understand how skills work, or (11) get guidance on skill design patterns. Trigger on phrases like "create a skill", "new skill", "make a skill", "skill for X", "how do I create a skill", or "help me build a skill".

0
installs
▌
Sop Generator · fullrefit bundle
Generate structured Standard Operating Procedures (SOPs) from process recordings, transcripts, voice memos, or freeform descriptions. Includes decision trees, error handling, time estimates, tools required, and success criteria. Use when the user wants to document a business process, turn a Loom/Zoom recording transcript into a formal SOP, or create onboarding documentation for team processes. MANDATORY TRIGGERS: SOP, standard operating procedure, document this process, create an SOP, process documentation, write up this process, procedure guide, turn this transcript into an SOP.

0
installs

33 published skills