Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add felipecabargas/gambit --skill build-user-personagit clone --depth 1 https://github.com/felipecabargas/gambitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/felipecabargas/gambit/build-user-persona)<a href="https://agentmods.dev/skills/felipecabargas/gambit/build-user-persona"><img src="https://agentmods.dev/badge/skills/felipecabargas/gambit/build-user-persona/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/felipecabargas/gambit/build-user-persona"><img src="https://agentmods.dev/badge/skills/felipecabargas/gambit/build-user-persona.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00105 | $0.03326 |
| Opus 5 | $0.00053 | $0.01663 |
| Sonnet 5 | $0.00021 | $0.00665 |
| Haiku 4.5 | $0.00011 | $0.00333 |
Grade A, and why
build-user-persona scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Persona Builder
When to Use
Use this skill whenever you need to crystallise who you are building for. It adds the most value when:
- Before writing a feature request — ground the problem statement in a concrete user so the FR doesn't describe a product for a hypothetical person
- Before authoring a product strategy — establish the user segments the strategy is designed to serve before debating priorities
- When onboarding new team members — give engineers, designers, and stakeholders a shared mental model of users that is traceable to real data, not opinions
- When aligning design and engineering on who they're building for — prevent scope creep caused by different people imagining different users
- After running
synthesize-user-research— when a synthesis doc is ready, use this skill to add the persona layer that makes themes and pain points actionable - Before a design review — ensure design decisions can be evaluated against a named persona, not "users in general"
Input Format
The skill accepts research data in any of the following formats. You can paste content directly into the chat, provide a file path, or combine both.
Research synthesis document (output of synthesize-user-research):
# Research Synthesis: Onboarding 2026-Q1
Sources: 8 participants / 200 surveys / 42 tickets
Themes:
1. Manual export workaround — Validated (6/8 sources)
2. Permissions confusion — Validated (5/8 sources)
...
Raw interview notes:
Participant 2 — ops manager, 300-person logistics firm
"I'm in the product every day but only for about 15 minutes. I need to see the
status of our three main workflows at a glance — I don't have time to dig in."
[Observation: primary use case is status monitoring, not configuration]
Survey data with open-text responses:
Role: Head of Operations (42% of respondents)
Primary job: Monitor workflow health across teams
Top frustration: "Too many clicks to see what I actually care about"
Top need: "A summary view I can check in under a minute"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 301 lines · 105 tokens per session scan A cae172cd2563
build-user-persona is a skill published in the GitHub repository felipecabargas/gambit (2 stars, last pushed 3mo ago), licensed MIT. It adds 105 tokens to every session and 3,326 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
seo-page
Single-page SEO audit: deep content quality evaluation using Google's E-E-A-T framework, Helpful Content guidelines, on-page SEO factors, search intent alignment, technical signals, and readability analysis. Fetches GSC performance data for that specific page, crawls the live HTML, evaluates metadata, schema markup…
gemini
Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge. Three modes: review (pass/fail gate for Google Ads campaigns, SEO metadata, or code), challenge (adversarial stress-test that tries to break your changes), and consult (open Q&A with Gemini…
google-ads
Manage Google Ads — performance, keywords, bids, budgets, negatives, campaigns, ads, search terms, QS, location targeting, bulk operations, experiments, asset management, portfolio bidding, offline conversions. Use for any mention of Google Ads, CPA, ROAS, ad spend, or campaign settings.
geo-optimizer
Generative Engine Optimization (GEO) — make content rank in AI search answers from ChatGPT, Claude, Perplexity, Gemini, and Google AI Overviews. Audits existing content, rewrites for AI citation, and produces per-engine strategy. Use when asked to "optimize for AI search", "rank in ChatGPT", "GEO audit", "improve AI…
schema-markup-generator
Generate JSON-LD structured data markup for rich results in Google Search. Supports FAQ, HowTo, Article, Product, LocalBusiness, and multi-type schemas. Validates against Google requirements and provides implementation guidance. Use when asked to "add schema markup", "generate structured data", "JSON-LD", "rich…
google-ads-landing
Score and diagnose Google Ads landing pages. Use when asked to audit a landing page, check landing page quality, diagnose high-CTR but low-conversion-rate ad groups, improve Quality Score's Landing Page Experience component, or compare an ad group's messaging against its landing page. Trigger on "landing page audit"…