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 mlopscommunity/Coding-Agents-Conference-skills --skill expert-persona-skillsgit clone --depth 1 https://github.com/mlopscommunity/Coding-Agents-Conference-skillsWrote 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/mlopscommunity/coding-agents-conference-skills/expert-persona-skills)<a href="https://agentmods.dev/skills/mlopscommunity/coding-agents-conference-skills/expert-persona-skills"><img src="https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/expert-persona-skills/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/mlopscommunity/coding-agents-conference-skills/expert-persona-skills"><img src="https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/expert-persona-skills.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 | $0.00056 | $0.02067 |
| Opus 5.5 | $0.00022 | $0.00827 |
| Sonnet 5.5 | $0.00011 | $0.00413 |
| Haiku 4.5 | $0.00006 | $0.00207 |
Grade A, and why
expert-persona-skills 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 2mo 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expert Persona Skills
Overview
A technique for writing short, focused skill files (often under 50 lines) that prime Claude to operate as a domain expert. The key insight: you are not teaching the LLM new knowledge. You are activating latent knowledge it already has. A small bag of context — the right terminology, constraints, mental models, and reference points — is enough to shift Claude from generic assistant into a credible domain practitioner.
Core principle: Short, focused priming beats long instruction sets. Even 40 lines can unlock deep expertise if those lines contain the right activation signals.
Dependency: None. These are plain Markdown skill files. Optionally pair with MCP servers for tool access in the target domain.
When to Use
- You need Claude to work in a non-coding domain (legal, marketing, finance, security, PM)
- You want consistent expert-level output across multiple conversations
- You are building a skill for a domain you are not personally expert in
- You want to package domain knowledge for a team so everyone gets the same quality
- You are creating a library of reusable personas for different project phases
When NOT to Use
- The task is a one-off question with no need for consistency across sessions
- You need legally binding advice (skills improve quality but do not replace licensed professionals)
- The domain requires access to proprietary data that cannot be described in a skill file
Common Mistakes
| Mistake | Why it's wrong |
|---|---|
| Writing a 500-line skill that tries to teach the LLM everything | You are activating, not teaching. Claude already knows trademark law — it just needs the right framing to apply it. Long files dilute the signal. |
| Omitting concrete constraints and defaults | "Be a good PM" activates nothing. "Default to RICE scoring, timebox discovery to 1 week, require a one-pager before any spec" activates a specific PM style. |
| Copying a textbook instead of curating activation signals | A paragraph of terminology, a list of common pitfalls, and a decision framework will outperform ten pages of reference material. |
| Skipping reference examples from real projects | Well-executed open source projects are the best design references for unfamiliar domains. Point Claude at one instead of writing your own spec from scratch. |
| Making the skill only about instructions, ignoring tools | Skills are bags of context plus MCP servers. A trademark skill paired with a USPTO search tool is dramatically more useful than either alone. |
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.
- 2mo ago First seen · 181 lines · 56 tokens per session scan A fa9fb2c0d84d
expert-persona-skills is a skill published in the GitHub repository mlopscommunity/Coding-Agents-Conference-skills (39 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 2,067 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
expert-persona-skills compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| expert-persona-skillsmlopscommunity/Coding-Agents-Conference-skills | Skill | 39 | 7mo ago | Apache-2.0 | A | 56 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 5d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 316k | 8d ago | MIT | A | 21 | Claude Code |