Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Pika-Labs/Pika-Pluginsnpx agentmods add skills/pika-labs/pika-plugins/persona-builderWrote 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/pika-labs/pika-plugins/persona-builder)<a href="https://agentmods.dev/skills/pika-labs/pika-plugins/persona-builder"><img src="https://agentmods.dev/badge/skills/pika-labs/pika-plugins/persona-builder/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/pika-labs/pika-plugins/persona-builder"><img src="https://agentmods.dev/badge/skills/pika-labs/pika-plugins/persona-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 60 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
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 | $0.00246 | $0.21226 |
| Opus 5 | $0.00123 | $0.10613 |
| Sonnet 5 | $0.00049 | $0.04245 |
| Haiku 4.5 | $0.00025 | $0.02123 |
Grade A, and why
persona-builder scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Presigned URLs expire in 300s.** A sequential `curl PUT` chain of 10+ files where each takes 8–12s can exceed the window for the last few URLs. **Always run PUTs in parallel** using `(curl ... &)` subshells + `wait`. How it starts
The opening of the file, as written. The whole thing — 681 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Influencer Identity
Tools below are Pika MCP tools, named bare — call each under whatever prefix your session exposes for the Pika MCP.
Take a person — their socials, their camera roll, the way they talk, who they want to be online — and run them through a glow-up with real talk. The output is a persona.md + portable folder kit + a roadmap to close the gap between where they are now and the persona they want to project.
Sister skill to build-a-brand: same uncompromising standards on voice, aesthetic, and specificity — but the brand is a human, not a product. The output is consumed by other Pika skills (ugc-ads, podcast, founder-product-video, app-sizzle, app-store-screens) so the influencer can produce on-brand content anywhere.
Cost transparency gate
Before any paid MCP call, call identity_balance({verbose: true}) once. Surface the current balance, recent burn rate, and remaining runway, then gate the run with this exact message:
Estimated cost: about 600-1,200 credits (~$6-$12) for scrape/transcription if needed, GPT-image-2 mood-board and voice-page atmosphere tiles, MCP HTML image renders, JPG conversion, final html_to_pdf render, and post-render analyze_media PDF QA. This exceeds $5, so Reply
proceedto continue orcancelto stop.
Do not call any paid MCP tool until the user replies proceed. If the user replies cancel, stop without generating. This is the only yes/no gate; after proceed, run the workflow until the next explicit user approval gate for identity/mood-board/PDF content.
Tone of the conversation
This is not a packaging exercise. The user came here to look more marketable. That means: be honest, be strategic, be specific. The skill should feel like a friend who books brand deals telling them what to actually fix — not a horoscope and not a Canva mood board factory.
- Lead with what the inputs prove, not what the user wished they'd hear. If their photos are crappy, say so and tell them how to fix it.
- Initiate the strategic conversation, don't wait to be asked. The user doesn't always know what's lucrative or what content mix gets paid — bring receipts.
- Name the gap explicitly: "to look like @[reference], you'd need to add X / drop Y / shoot in Z light." Don't soft-pedal.
- No empty validation. If the user's bio is generic, the answer isn't "love it!", it's a rewrite.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/aesthetic-prompts.md 8.8 KB
- references/persona-md-template.md 14 KB
- references/templates/mood-board-no-header.template.html 1.2 KB
- references/templates/mood-board.template.html 3.0 KB
- references/templates/pdf-about.template.html 1.3 KB
- references/templates/pdf-content-categories.template.html 2.1 KB
- references/templates/pdf-cover.template.html 841 B
- references/templates/pdf-do-dont.template.html 663 B
- references/templates/pdf-hooks-dm.template.html 878 B
- references/templates/pdf-moodboard.template.html 448 B
- references/templates/pdf-next-steps.template.html 2.3 KB
- references/templates/pdf-shared-head.template.html 11 KB
- references/templates/pdf-voice-mode.template.html 1.7 KB
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 · 681 lines · 246 tokens per session scan A 4e25654c445e
persona-builder is a skill published in the GitHub repository Pika-Labs/Pika-Plugins (40 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 246 tokens to every session and 21,226 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…