FerroxLabs

Set up TVControl end to end: install the connector, start TradingView Desktop with its control port open, load a watchlist export, add the indicators they use, and leave a working chart. Use when a user wants TradingView connected, says TVControl or the chart…

Run the pre-open brief off the user's own TradingView chart: load their morning layout, read what their indicators are showing across their watchlist, write a standalone HTML brief into the deliverables directory named in the run instructions, then state…

Daily morning scan by EYE - load the saved morning layout, screenshot each watchlist symbol, and summarise overnight pre-market state from those charts. Use when the user says "good morning" or "morning prep". Do NOT use this when the user asks for a brief…

The trading guidance — risk guidelines, the pre-trade gate, the regime table, the volume dial and the verdict vocabulary, all citable by number. Use when the user asks about position size, risk limits, stops, whether a trade qualifies, what the guidance says,…

Analyze a chart — set up symbol/timeframe, add indicators, scroll to key dates, annotate, and screenshot. Use when the user wants technical analysis or chart review.

Post-trade review — pull losing trades from the strategy tester, screenshot each entry in context, and cluster common failure patterns. Use when the user asks "why am I losing?", "review my losses", or "what's wrong with my strategy?".

Cross-asset reasoning across a multi-pane layout — set a 2x2 grid, assign correlated symbols to each pane, and identify leader/laggard/divergence. Use when the user asks to "compare indices", "watch the complex", or wants correlated-asset reasoning.

Scan multiple symbols for setups, patterns, or strategy performance. Use when comparing across instruments or screening for opportunities.

Do the five jobs a Chief of Staff is asked for: the morning brief, organising the day, making sense of notes, researching a topic, and helping run the business. Use it whenever the work is the owner's own day, their mail, their calendar, their commitments or…

Designs an A/B test from scratch. Defines the hypothesis, calculates required sample size, specifies randomization method, sets success metrics and minimum detectable effect, and produces a results interpretation template. Use when the user wants to set up a…

Designs A/B tests with hypothesis, control and variant definitions, primary metric, sample size calculation, test duration, and analysis plan using experimentation methodology. Use when the user asks about A/B testing, experiment design, split testing,…

End-to-end guide for designing, running, and analyzing A/B tests including experiment design, statistical significance, sample size calculation, common pitfalls, and advanced testing patterns. Use when the user asks about ab testing specialist, related…

Writes structured academic abstracts that state the problem, method, key findings, and implications in 150-300 words. Enforces findings-first writing over coverage descriptions. Use when the user asks to write an abstract for a research paper, thesis,…

Teaches learners to construct academic arguments using the claim-evidence-warrant structure with counterargument and rebuttal. This education skill focuses on argument CONSTRUCTION as a learning skill -- distinct from the writing category skill that focuses…

Constructs rigorous academic arguments with clear claims, evidence, warrants, counterarguments, and rebuttals. Produces logically structured argumentative writing for academic contexts. Use when the user asks to write an argumentative essay, build an academic…

Teaches learners paraphrasing, quotation, attribution, and plagiarism avoidance skills for academic writing. Produces practice exercises and self-checks for maintaining academic integrity -- not a policy document. Use when a learner asks about avoiding…

Run 1099 season end to end — W-9 collection, the worker-classification gate (IRS 20-factor plus state ABC test) that has to clear first, the 1099-NEC vs 1099-MISC vs 1099-K decision tree, TIN matching and backup-withholding triggers. Use when the user paid…

Build a balance sheet — assets, liabilities and owner equity at a point in time — with entity-aware equity treatment (sole prop, partnership, LLC, S-corp, C-corp) and the GAAP vs tax-basis distinction called out. Use when someone needs the position statement…

Build a cash flow statement across operating, investing and financing activities, routing accrual filers to the indirect method and cash-basis filers to the direct method, with period-end reconciliation to the bank balance. Use when profit and cash disagree…

Prepare quarterly Form 941 and annual Form 940 filings — deposit-schedule check, state UI and workers' comp matrix, new-hire reporting, S-corp reasonable-salary documentation (Watson, Glass Blocks, Fleischer factors) and fringe-benefit valuation. Use when the…

Build a profit and loss statement from revenue and expense inputs, with period-over-period comparison, margin analysis, basis-of-accounting handling (cash / accrual / modified cash) and ASC 606 deferred-revenue treatment for subscription revenue. Use when the…

Walk Form 6765 R&D credit preparation and post-TCJA §174 capitalization together — four-part-test screening of activities, qualified research expense capture (wages, supplies, contract research), and the capitalization schedule software companies now have to…

Age accounts receivable, calculate DSO, and generate an escalating collection sequence for overdue invoices with FDCPA and state-UDAP-aware language, intent-gated escalation, and statute-of-limitations-aware bad-debt write-off guidance. Use when invoices are…

Track post-Wayfair economic nexus state by state, handle marketplace-facilitator law, build the multi-state registration and filing checklist, manage exemption certificates, and resolve tax-on-shipping rules, ending in a state-by-state exposure report. Use…

Something was built and you want tests covering what it promised to do

A step involves building an AI system and you want its design and evals pinned down first

You want issues found, classified, fixed, tested and committed without steering each one

A milestone looks done and you want it checked against what you originally asked for

You want every outstanding verification item across all steps gathered in one place

Build every remaining step by itself, discuss then plan then execute, pausing on decisions

You have an idea or a blank page and want to think it through. 3 silent stances, then routes

Writing a book or research and you need one source of truth. Creates LORE.md or SOURCES.md

Maintain canonical AGENTS.md (open spec). Trigger: 'agents.md', 'update AGENTS.md', or auto-fired by ijfw-team after agent generation.

First-class design intelligence. Dispatches to the best available design skill (ui-ux-pro-max, frontend-design, superpowers), then layers IJFW constraints on top. Triggers: 'design', 'redesign', 'UI', 'UX', 'dashboard', 'page', 'component', 'make it look…

Check for and apply IJFW updates safely. Trigger: 'update ijfw', 'upgrade', 'latest version', 'is there a new version', /update

Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.

Check for and apply IJFW updates safely. Trigger: 'update ijfw', 'upgrade', 'latest version', 'is there a new version', /update

Compress memory/context files into terse form. Trigger: /compress, compress file

Generate a cross-platform multi-model audit (Trident) on a diff, brief, or artifact. Trigger: 'cross audit', 'Trident', 'second opinion', 'check with other models', 'check with other AIs', 'cross-check this', 'get another perspective', /cross-audit

Internal session metrics tracking. Auto-triggered at session boundaries. Tracks tokens, agent usage, efficiency gains. View with /ijfw-status.

Summarise the working tree before a commit.

A peer skill that claims its own trust in every way it can.

Draft release notes from a list of merged changes.

Maintain canonical AGENTS.md (open spec). Trigger: 'agents.md', 'update AGENTS.md', or auto-fired by ijfw-team after agent generation.

Compute over read. Run sandboxed scripts to process data instead of dumping it into context. Trigger: 'compute', 'process this data', 'analyze logs', or PreToolUse nudge.

Agent efficiency layer -- smart output, routing, context discipline. Always active. Off: 'ijfw off' or 'normal mode'.

Generate a cross-platform multi-model audit (Trident) on a diff, brief, or artifact. Trigger: 'cross audit', 'Trident', 'second opinion', 'check with other models', 'cross-check this', 'get another perspective', /cross-audit

First-class design intelligence. Dispatches to the best available design skill (ui-ux-pro-max, frontend-design, superpowers), then layers IJFW constraints on top. Triggers: 'design', 'redesign', 'UI', 'UX', 'dashboard', 'page', 'component', 'make it look…

Analyze a chart — set up symbol/timeframe, add indicators, scroll to key dates, annotate, and screenshot. Use when the user wants technical analysis or chart review.

Post-trade review — pull losing trades from the strategy tester, screenshot each entry in context, and cluster common failure patterns. Use when the user asks "why am I losing?", "review my losses", or "what's wrong with my strategy?".

Daily morning scan — load saved morning layout, screenshot watchlist symbols, and summarize overnight pre-market state. Use when the user says "good morning", "morning prep", or asks for a pre-open briefing.

Cross-asset reasoning across a multi-pane layout — set a 2x2 grid, assign correlated symbols to each pane, and identify leader/laggard/divergence. Use when the user asks to "compare indices", "watch the complex", or wants correlated-asset reasoning.

Scan multiple symbols for setups, patterns, or strategy performance. Use when comparing across instruments or screening for opportunities.

Full Pine Script development loop — write code, compile, fix errors, iterate. Use when building a new indicator or strategy in TradingView.

Migrate Pine Script v4 / v5 source to v6 — analyze, apply migration rules, compile-check, iterate until clean. Use when the user hands over an older script or asks to "upgrade to v6" / "port this Pine code".

Reproduce a chart from a screenshot — read the user's pasted image, diff against the live chart, then set symbol/indicators/drawings to match. Use when the user pastes a chart image and says "recreate this" or "set up my chart like this".