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 ViryaZheng/xmum-application-skills --skill xmum-research-advisorgit clone --depth 1 https://github.com/ViryaZheng/xmum-application-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/viryazheng/xmum-application-skills/xmum-research-advisor)<a href="https://agentmods.dev/skills/viryazheng/xmum-application-skills/xmum-research-advisor"><img src="https://agentmods.dev/badge/skills/viryazheng/xmum-application-skills/xmum-research-advisor/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/viryazheng/xmum-application-skills/xmum-research-advisor"><img src="https://agentmods.dev/badge/skills/viryazheng/xmum-application-skills/xmum-research-advisor.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 | $0.00042 | $0.01279 |
| Opus 5 | $0.00021 | $0.00639 |
| Sonnet 5 | $0.00008 | $0.00256 |
| Haiku 4.5 | $0.00004 | $0.00128 |
Grade A, and why
xmum-research-advisor 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 12d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
XMUM Research Advisor
Purpose
Use this skill for research-background planning and MPhil/PhD-style applications. It helps the applicant choose authentic, verifiable research work over paid packaging or inflated credentials.
Shared Application Workspace
Before substantial research-advising work, check the current workspace for application-profile.md and application-tracker.md. If present, read them first, reconcile them with the latest user message, and treat them as the current source of truth.
Use application-profile.md for stable research evidence, methods, supervisors, outputs, projects, and recommendation options. Use application-tracker.md for supervisor lists, target programs, proposal status, contact dates, replies, risks, and next actions. If a supervisor or research direction is added, update or propose updates to the tracker.
Paid Research Red Flags
Warn the applicant when a "research product" has these signs:
- Short camp or lecture series marketed as serious research.
- Famous professor branding with little real supervision.
- Guaranteed paper publication, especially with extra publication or page fees.
- Weak venue, unclear peer review, or a paper the applicant cannot explain technically.
- No real dataset, code, lab work, experiment, literature synthesis, or methodological contribution.
- Recommendation provided as a certificate or PDF rather than submitted through the official referee system.
- The supervisor cannot credibly verify the applicant's work through an institutional channel.
- The project is open to participants without relevant prerequisites and assigns no real technical task.
Core test: can the applicant truthfully explain the question, method, result, and personal contribution, and can a real supervisor verify it?
Preferred Research Paths
Recommend authentic routes first:
- Ask XMUM faculty for research assistantship, FYP extension, lab/project participation, or directed reading.
- Start earlier than application season, especially for MPhil, PhD, or US applications.
- Build continuity: course -> project -> FYP/research -> recommendation -> statement.
- If the applicant has access to a real university lab or research group, join only when actual tasks are available.
- Use summer schools only when they are official, credit-bearing, or genuinely skill-building.
- Prefer a small real project over a polished but hollow paid credential.
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.
- 12d ago First seen · 127 lines · 42 tokens per session scan A e75964b06a78
xmum-research-advisor is a skill published in the GitHub repository ViryaZheng/xmum-application-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 1,279 once invoked, about $0.0002 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.