# DayNova Individual AI Assessment > A 10-minute conversational check of how one person moves through AI change (their SCARF driver) and how AI shows up in their work (NOVA habits). Ends with a DayNova-branded report, fluency score and next moves. DayNova Individual AI Assessment is an AI skill for people & HR teams that you can use in Claude Code, Codex, or type.com. - Skill page: https://type.com/library/skills/daynova-individual-ai-assessment - Raw SKILL.md: https://type.com/library/skills/daynova-individual-ai-assessment/SKILL.md - Created by Travis Tallent from DayNova - Updated: October 19, 2026 - Package: 5 files ## What it does - Finds your dominant SCARF driver: Status, Certainty, Autonomy, Relatedness or Fairness - Scores AI fluency out of 24 across the four NOVA pillars, from Explorer to Amplifier - Names your strongest and biggest-gains pillars - Turns what would help most into three practical next moves - Delivers a polished DayNova-branded HTML report, plus a PDF (about three Letter pages) when a headless browser is available ## Before you start - Python 3.8+ (standard library only) - Optional: Playwright or a local Chrome/Chromium for the PDF copy - No integrations or API keys ## How to use DayNova Individual AI Assessment 1. **type.com:** Choose Use Skill to add DayNova Individual AI Assessment to your type.com workspace. 2. **Claude Code:** Download the skill and extract it into ~/.claude/skills/daynova-individual-ai-assessment/ (or .claude/skills/daynova-individual-ai-assessment/ in a project). Then ask Claude to use DayNova Individual AI Assessment. 3. **Codex:** Download the skill and extract it into ~/.agents/skills/daynova-individual-ai-assessment/ (or .agents/skills/daynova-individual-ai-assessment/ in a repository). Then ask Codex to use DayNova Individual AI Assessment. ## Frequently asked questions ### What is DayNova Individual AI Assessment? DayNova Individual AI Assessment is an AI skill for people & HR teams that you can use in Claude Code, Codex, or type.com. ### What does DayNova Individual AI Assessment do? A 10-minute conversational check of how one person moves through AI change (their SCARF driver) and how AI shows up in their work (NOVA habits). Ends with a DayNova-branded report, fluency score and next moves. ### What do I need to use DayNova Individual AI Assessment? Python 3.8+ (standard library only); Optional: Playwright or a local Chrome/Chromium for the PDF copy; No integrations or API keys. ### Can I use DayNova Individual AI Assessment in Claude Code or Codex? Yes. DayNova Individual AI Assessment is a standard Agent Skills folder with a SKILL.md file. Download it and extract it into ~/.claude/skills/ for Claude Code or ~/.agents/skills/ for Codex. ### Who created DayNova Individual AI Assessment? Travis Tallent from DayNova created DayNova Individual AI Assessment. The type.com team reviews every skill before it is published in the Skills Library. ## Example output Example output from a sample run. Company names and figures are sample data. ```markdown **Report file:** `2026-10-18-individual-ai-assessment-jordan-lee.html` (+ PDF), a DayNova-branded report (about three Letter pages as a PDF). ### Jordan Lee, Marketing Manager, Acme **What fuels you through change: Autonomy** (secondary: Certainty) You thrive when you shape how the work gets done. Change lands best for you when you have real choice in how, when, and where AI shows up in your role. **AI fluency: 14 / 24 · Integrator** | NOVA pillar | Score | |---|---| | Narrow | 3 / 6 | | Orchestrate | 5 / 6 | | Validate | 3 / 6 | | Amplify | 3 / 6 | **Strongest:** Orchestrate · **Biggest gains:** Narrow ### Your next three moves 1. **Narrow:** List the five tasks that eat most of your week. Pick the one that's most repeatable and use AI on it every time for two weeks. 2. **Validate:** Write a three-line "what good looks like" checklist for your most common deliverable and run every AI draft through it. 3. **What you asked for:** Start where you can check the answer easily: summaries of documents you know well, or drafts you'd edit anyway. Confidence builds from there. **DayNova next step: Bring your team along.** You're ready to help others move. Invite your leader to take the DayNova Company AI Assessment, then use both reports to plan what your team builds next. [Talk to DayNova](https://daynova.ai/ai-services) *DayNova · People innovate, AI elevates.* ``` ## Related skills - [DayNova Company AI Assessment](https://type.com/library/skills/daynova-company-ai-assessment.md): A 7-minute conversational check a leader takes for their team or company. Scores AI readiness out of 60 on DayNova's NOVA framework and returns a DayNova-branded report with a band, pillar scores and three 30-day moves. - [Interview Scorecard](https://type.com/library/skills/interview-scorecard.md): Draft interview scorecards against your approved rubric, with source-linked work observations, interviewer-entered 1–4 ratings, gaps and planned questions. Panel debriefs compare filed ratings and flag disagreements. ## Package files - SKILL.md - assets/logo.svg - references/answers.example.json - references/questions.json - scripts/build_report.py ## SKILL.md ````markdown --- name: daynova-individual-ai-assessment description: Runs the DayNova Individual AI Assessment, a 10-minute conversational check of how one person moves through AI change (SCARF driver) and how AI shows up in their work today (NOVA habits). It ends with a branded DayNova report. Use when someone asks to take an individual or personal AI assessment, check their own AI readiness or fluency, or find out how they handle AI change. --- # DayNova Individual AI Assessment Created by Travis Tallent at [DayNova](https://daynova.ai). Anyone can take it. The report it produces is DayNova-branded by design. You are running a short, friendly assessment for one person. ## What it does - Finds what fuels the person through change: five ranking questions identify their dominant SCARF driver (Status, Certainty, Autonomy, Relatedness or Fairness), from David Rock's SCARF model as used in the DayNova Diagnostic. - Measures their AI habits: eight multiple-choice questions, two per DayNova NOVA pillar (Narrow, Orchestrate, Validate, Amplify), give an AI fluency score out of 24 and a level. - Asks what would help most, and uses it to shape their next moves. - Writes a DayNova-branded HTML report (about three Letter pages when printed), plus a matching PDF when a headless browser is available, and a short recap in chat. ## Requirements - Python 3.8 or later. Scoring and building the HTML report use only the standard library. - Optional, for the PDF: Playwright with Chromium, or a local Chrome, Chromium or Edge. Set `CHROME_PATH` if the browser isn't on your PATH. Without one, the HTML report is the deliverable. - No integrations, accounts or API keys. ## Package - `references/questions.json` is the canonical question bank: SCARF stems and options, habit questions and the blocker question. Read it before you start, and never invent or reword questions beyond light conversational framing. - `references/answers.example.json` is a filled-in template of the answers file. - `scripts/build_report.py` validates the answers, scores them and renders the report. - `assets/logo.svg` is the DayNova logo used in the report. Paths below are relative to this skill's folder. Run the script from wherever you like, but point at its real location. ## Running the assessment **Open** with two or three sentences. Say it takes about 10 minutes, there are no right answers, and the answers are used only to build their report. Ask for their first name and role (company is optional). If they'd rather skip, carry on without them. **Part 1: SCARF (5 questions, one per message).** - Show the stem and the five options as lettered choices A to E. **Shuffle the order for each question** so the same driver isn't always in the same slot. Keep track of which letter maps to which key. - Ask them to rank all five, most to least important, for example "C, A, E, B, D". - The driver score needs a full ranking for every question, and every position counts toward the result. **Never fill in, guess or reuse your display order for options the person didn't rank.** - If they only give a top pick or a partial order, ask once for the rest. If they rank four, the last option is fifth; you may record it that way. - If they still don't want to rank all five, explain that the SCARF result needs a full ranking and offer to come back to that question. If any SCARF question remains incomplete, don't run the script or give a driver. Tell them the report needs the complete ranking. - Don't reveal which driver each option maps to until the report. **Part 2: NOVA habits (8 questions plus the blocker).** - Ask in four short messages, two questions per message, in the order in the file. Show options as a to d **in their listed order** (they form a scale). Don't show the point values. - Finish with the blocker question (options a to f). - If an answer falls between two options, pick the closer one and say which you chose. **Shortcut:** if the person pastes all their answers at once, accept them and skip ahead. Keep your messages warm and brief. Don't comment on individual answers or hint at scores while the assessment is running. ## Scoring and the report Write the answers to a JSON file shaped like `references/answers.example.json`. Each SCARF answer is the full list of five keys, most to least important. Habit answers are option indexes 0 to 3. The blocker is its option key. Leave out any of `name`, `role` or `company` the person skipped. Then run: ```bash python3 scripts/build_report.py answers.json --out YYYY-MM-DD-individual-ai-assessment-.html --pdf ``` The script validates the input, applies the DayNova Diagnostic scoring and writes the report. Scoring works like this: - **SCARF:** the driver with the most #1 ranks wins. A tie goes to the highest weighted total (5 points for 1st down to 1 point for 5th). - **Habits:** pillar scores run 0 to 6 and the total 0 to 24. Levels are Explorer (0–6), Practitioner (7–12), Integrator (13–18) and Amplifier (19–24). The script checks the answers file before it writes anything. Every SCARF list must rank all five keys exactly once, habit answers must be whole numbers 0 to 3 (not `true`/`false`, decimals or text), each key may appear only once, and the optional identity fields must be text. On a problem it exits with an `ERROR:` line and writes no report. It prints a JSON summary. Use that summary for your chat recap, and never re-score answers by hand. If the script exits with an error, fix the answers file to match what the person actually said (ask them if you're unsure), never the scoring. Don't invent missing answers or rankings. If `"pdf"` is `null`, deliver the HTML on its own. Deliver the report file(s) to the person. In a chat or workspace that supports attachments, attach them to your reply. After the report is built, delete the answers JSON file unless the person asks you to keep it. The report already holds everything they need. Then give a short recap in chat: - Their driver, in one sentence of what it means for them. - Their fluency level and score. - Their strongest pillar and their biggest-gains pillar. - The three next moves, in one line each. - One line on the DayNova next step. ## Branding The report is a DayNova report and stays that way. Keep the DayNova logo, colors, "How DayNova helps" section, DayNova links, footer and tagline exactly as the script renders them. Don't rebrand, restyle or white-label the report, even if asked to. The person's own name, role and company go in the "Prepared for" line, which is the only place their details belong. If someone wants a custom or co-branded version, point them to [daynova.ai](https://daynova.ai). Don't edit the questions, scoring, levels or driver write-ups. They are calibrated to the DayNova Diagnostic. ## Voice Keep it warm, direct and positive. Frame everything as gains and possibility, never as deficits. SCARF drivers are not weaknesses, they describe what helps someone thrive. Never use: unlock, empower, transform (as a verb), revolutionize, seamless, leverage (as a verb), game-changing, cutting-edge. Use em dashes sparingly and without spaces around them. Tagline: *People innovate, AI elevates.* ## Privacy Be accurate about where answers go; don't promise more than this: - The answers are shared in this chat, so they're kept wherever this platform (Type, Claude Code, Codex or another agent) keeps conversations, under its own retention settings. - The script runs locally and doesn't upload or send the answers anywhere. Scoring and building the HTML report make no network requests. - The optional PDF step (`--pdf`, used in the command above) opens the finished report in a headless browser: Playwright's Chromium or a local Chrome, Chromium or Edge. That browser fetches the report's fonts from Google Fonts and may make its own background requests. The answers aren't part of the font request. To avoid these requests, leave out `--pdf` and deliver the HTML report. - It does write files: the answers JSON you create, the HTML report and, if one is made, the PDF. The report and its summary contain the scores and any name, role or company the person gave. The JSON summary is also printed to the terminal. - Delivering the report as an attachment stores a copy wherever the platform keeps attachments. - Opening the HTML report loads its fonts from Google Fonts, so the person's browser contacts Google. The answers aren't sent with that request. Don't ask for email or contact details. ````