jqai-ai-skills

Generate the dual-agent workspace contract, an AGENTS.md skill registry plus a CLAUDE.md pointer, so one set of skills serves both Claude Code (which auto-discovers them) and agents like Codex (which need required-reading instructions). Use when the user says "set up AGENTS.md", "make my skills work in Codex too", "dual agent setup", or "workspace contract".

Scaffold a complete client project folder from your own reusable structure template, with a filled-in brief file and feedback log. Never overwrites existing work. Use when the user says "new client", "set up a client folder", "onboard this client", or "create a project workspace for".

Run a structured discovery interview for a new client project and turn the answers into a completed brief plus a strategy starter document. Conversational, skips what is already known, and never fabricates unanswered questions. Use when the user says "run discovery", "brief for this client", "discovery questionnaire", or "help me figure out what this client needs".

Scan a folder of outreach or CRM markdown files for overdue follow-ups and draft the follow-up messages, oldest first. Report-first and drafts only, it never sends anything. Use when the user says "any follow-ups due", "check my outreach pipeline", "who did I forget to follow up with", or "follow-up status".

Generate a recurring status snapshot of a folder-based workspace (clients, pipeline files, recent activity, command health checks) ending in an Attention Needed section that surfaces what is stalled or overdue. Read-only except for the report file. Use when the user says "status report", "weekly report", "what's going on in this workspace", or "ops snapshot".

Write a client proposal or quote from your own service tiers, saved once in a pricing config. Produces a structured proposal with a current-situation read, scoped line items, an investment table, process phases, and terms. Drafts only, a human reviews before anything reaches a client. Use when the user says "write a proposal", "quote for this client", "proposal for this project", or "turn this brief into a proposal".

Record a cropped region of your Windows desktop to a clean MP4 video file. Drag a box over any part of the screen, record silently, and stop with one click. Uses FFmpeg with a drag-to-crop overlay, no editor or account needed. Use when the user says "screen record", "record my screen", "record a region", "capture a part of my desktop", "screen capture to video", or "make a screen recording".

Write a start-here handoff document at the end of a work session capturing state, decisions, next steps, and gotchas, so the next session (or the next person) resumes in minutes instead of re-deriving everything. Use when the user says "wrap up", "handoff", "end of session", "write a handoff note", or "where did we leave off" at the start of a new session.

Author a new Claude Code skill the right way, from choosing the storage tier (project, shared library, or user-global) to scaffolding the SKILL.md, linking it across workspaces, and registering it for agents that do not auto-load skills, like Codex. Use when the user says "create a skill", "turn this workflow into a skill", "make this repeatable", or "new skill for".

Refresh and verify a GitHub profile or public proof layer. Use when the user wants to update GitHub profile visuals, replace README assets while preserving paths, audit profile image references, validate live GitHub rendering, prepare LinkedIn/X proof copy, or document a profile-refresh proof trail.

Plan, document, and follow up on public proof campaigns across LinkedIn, X, GitHub, websites, and videos. Use when the user wants carousel or thread copy, alt text, post/video captions, public link tracking, reply banks, engagement review, or a campaign proof trail after publishing project work.

Lint copy against a brand voice guide. Scans files for em dashes, buzzword clusters, hedge language, vague superlatives, passive voice, exclamation marks, and AI-tell phrases, then reports every violation with a suggested rewrite. Report-only by default, applies fixes on request. Use when the user says "lint this copy", "check this against our voice", "does this sound like us", "voice check", or "clean the AI tells out of this".

Generate a branded, single-file HTML client intake questionnaire for any service business. Picks the right question set (brand identity, web design, automation project, or pre-call brief), styles it with the project's brand colours and fonts, and includes validation, progress, and a success state. Pairs with php-form-mailer to make it send email. Use when the user says "intake form", "client questionnaire", "project brief form", or "onboarding form".

Write a personalised cold outreach email from a company research block. Produces one tight email under 180 words built on a specific observation about the prospect, plus three alternative subject lines, a LinkedIn connection note, and a 7-day follow-up. Drafts only, never sends anything. Use when the user says "write a cold email", "outreach email for this lead", "draft outreach for this company", or "follow up email for this prospect".

Capture a raw idea as a dated, tagged markdown file in an ideas folder and keep an index up to date. Cleans filler words from the dump while preserving the substance, so capture stays fast and retrieval stays possible. Use when the user says "idea:", "capture this idea", "save this idea", or "add to my ideas".

Score a list of leads 0 to 100 against your own ideal-client rubric and rank them into hot, warm, and cold tiers. Takes a CSV or markdown list of leads, scores each with a reason and a suggested next action, and outputs a ranked file. Honest about missing data: leads it cannot judge get flagged for research, not guessed. Use when the user says "score these leads", "rank this lead list", "prioritise my prospects", or "which of these should I contact first".

Generate a spec-compliant llms.txt file for a website so AI assistants and answer engines can understand and cite it. Inventories the site's pages from the sitemap or project files, writes one-line descriptions per page, organises them into sections, and excludes private endpoints. Use when the user says "llms.txt", "make my site readable to AI", "AI search optimization file", or "GEO file".

Create or append to today's daily note in an Obsidian vault from the terminal. Adds timestamped sections to the right dated file without overwriting anything, creating the note with a date heading if it does not exist yet. Use when the user says "daily note", "log this to today", "add to my daily note", or "note this down".

Wire any HTML form to a two-email PHP system. Generates a complete PHP handler that sends a structured notification email to the site owner and a branded HTML confirmation to the person who submitted, updates the form action and JS handler with a mailto fallback, then tests the live endpoint with curl. Works on any plain PHP host (cPanel, shared hosting) with no framework and no third-party form service.

Scan a folder tree for accumulated junk (dependency folders, build caches, stray backups, log files, OS litter, duplicate copies) and produce a sized, grouped cleanup report. Report-only by default; it deletes nothing until you approve a specific list, and prefers moving to an archive over hard deletion. Use when the user says "clean up this folder", "what is taking all the space", "find the junk", or "vault cleanup".

Prepare private work for safe public GitHub publishing. Use when the user asks to publish safely, turn private project work into a GitHub-safe artifact, sanitize a project, make a public case study, prepare material for GitHub, review a repo before pushing, or check whether files contain secrets, client data, raw prompts, logs, local paths, private source, or other sensitive material.

Curate public-source links, saved notes, newsletters, documentation updates, release notes, market signals, and research snippets into safe daily or weekly briefs with source tracking, public/private visibility labels, archive decisions, and human review. Use when the user asks to make a research brief, summarize saved links, build an AI news digest, organize reading notes, create a public-safe source roundup, prepare a weekly intelligence brief, or separate public-ready notes from private research without exposing credentials, raw prompts, logs, local paths, account data, client material, or private source lists.

Audit, rewrite, prioritize, and monitor Etsy or marketplace listings using public-safe product data. Use when the user asks to optimize an Etsy listing, improve product titles, tags, descriptions, keyword fit, marketplace SEO, listing batches, shop audits, eRank-style keyword review, competitor notes, or listing refresh workflows without exposing shop exports, private metrics, customer data, credentials, raw CSVs, or live shop configuration.

Design safe, human-reviewed prospecting, lead qualification, enrichment, scoring, outreach draft, and follow-up workflows. Use when the user asks to build an outreach pipeline, prospecting workflow, lead scoring system, sales ops dashboard, market research pipeline, cold email review queue, CRM handoff, or any AI-assisted outreach process that must avoid exposing credentials, private data, prospect lists, raw prompts, scraped exports, or unattended sending.

Write public-safe case studies from private projects, automations, agent workflows, internal tools, demos, or client-facing systems. Use when the user asks to turn project work into a case study, create client proof, write a sanitized GitHub case study, summarize an internal system publicly, document an automation without sharing source code, or explain a workflow while removing credentials, raw prompts, logs, databases, client data, local paths, and private implementation details.

Write release notes, GitHub release copy, website update blurbs, and short launch posts from changelogs, git diffs, README changes, shipped feature lists, or product/system updates. Use when the user asks to announce a release, summarize what changed, prepare public launch copy, write a changelog, turn implementation notes into marketing-safe copy, or create LinkedIn/GitHub/X posts for a new version.

Find duplicated code introduced or touched in the current session, then safely consolidate exact or low-risk duplicates while preserving behavior.

Generate a simple desktop-oriented self-playing HTML product demo. Use for legacy demo walkthroughs with an intro screen, dashboard mockup, sidebar captions, timeline controls, cursor animation, highlights, piano music, and ending screen. Prefer demo-animation-v2 when the user needs mobile support, fullscreen controls, touch gestures, or the packaged template engine.

Generate the recommended responsive self-playing HTML product demo. Creates a single-file index.html with intro screen, dashboard mockup, step-by-step animation, captions, timeline controls, piano music, cursor animation, highlights, ending screen, mobile controls, touch gestures, fullscreen API, landscape hint, and prefers-reduced-motion support.

Scan files for em dashes and replace them with natural alternatives. Removes one of the most common AI writing tells from any copy.

Audit AI skill files or skill folders for security risks before installing. Reads SKILL.md and related metadata, checks for dangerous patterns, and returns a safety verdict.

Generate browser console scripts to scrape paginated websites. Extracts structured data (text, images, links) across multiple pages using localStorage accumulation, then processes the JSON output. Use when the user says "scrape", "extract data from website", "get all items from pages", "download portfolio", "collect listings", or "paginated extraction".

Explain what this skill does, when it should be used, and the user phrases that should trigger it.