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 toolbox-playground/super-claudio --skill tech-career-mentorshipgit clone --depth 1 https://github.com/toolbox-playground/super-claudioWrote 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/toolbox-playground/super-claudio/tech-career-mentorship)<a href="https://agentmods.dev/skills/toolbox-playground/super-claudio/tech-career-mentorship"><img src="https://agentmods.dev/badge/skills/toolbox-playground/super-claudio/tech-career-mentorship/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/toolbox-playground/super-claudio/tech-career-mentorship"><img src="https://agentmods.dev/badge/skills/toolbox-playground/super-claudio/tech-career-mentorship.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 | $0.00130 | $0.01892 |
| Opus 5.5 | $0.00052 | $0.00757 |
| Sonnet 5.5 | $0.00026 | $0.00378 |
| Haiku 4.5 | $0.00013 | $0.00189 |
Grade A, and why
super-claudio:tech-career-mentorship 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 21d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Career Mentorship
Build a useful mentoring document from the evidence the mentor provides. The primary deliverable is one concise PDF, normally two pages and never more than three. Keep it suitable for sharing with the mentee and for the next mentor to continue.
Read references/pdf-structure.md before creating or updating the report.
Inputs and stages
Accept any combination of a résumé or CV (PDF, DOCX, or text), LinkedIn URL/export, session notes or transcript, a previous mentoring PDF/source, a Google Doc, and details the mentee has shared about goals and constraints. Use connected Drive access for a Google Doc when available; otherwise ask for an accessible export or pasted content. If a LinkedIn page requires sign-in or blocks access, ask for a profile export or the relevant sections as text rather than guessing. Inputs may arrive across several sessions. If one important detail is missing, proceed with the supported diagnosis and mark that detail as an open question instead of blocking the report.
Write the report in the user's language; default to concise Brazilian Portuguese when the user writes in Portuguese.
Choose the stage from the available material:
- Initial diagnosis: no prior mentoring report. Summarize the current profile from the CV/LinkedIn and any supplied notes. Offer conditional preliminary development areas for Cloud, DevOps, SRE, and practical AI use only where relevant to the person's experience. If the desired direction is unknown, say so and avoid presenting an individualized roadmap as settled advice.
- Mentoring update: a prior report or new session notes are supplied. Preserve the prior report's useful facts, incorporate new evidence, revise assumptions when needed, and refine priorities and the learning roadmap. Add career and soft-skill guidance only from the mentee's statements or mentor's observations; otherwise leave prompts for the next conversation.
- Final or handoff update: if the user indicates the mentoring cycle is ending or handing off, consolidate decisions, actions, owners, and review dates, while keeping unresolved questions visible.
What ships with it
1 file 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.
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.
- 21d ago First seen · 82 lines · 130 tokens per session scan A b970c24a267b
super-claudio:tech-career-mentorship is a skill published in the GitHub repository toolbox-playground/super-claudio (5 stars, last pushed today), licensed MIT. It adds 130 tokens to every session and 1,892 once invoked, about $0.0005 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 2026-10-06.
Other skills, from other repositories
book-to-skill
Book-to-skill takes technical books, documentation, or other long-form sources and converts them into a skill made of a core definition plus per-chapter files, a glossary, and cheatsheets, so an agent can load only the relevant section instead of the whole document. It supports PDF, EPUB, DOCX, HTML, and several other…
summarize
Summarize or extract text and transcripts from URLs, podcasts, YouTube videos, and local files. Use when the user asks to summarize a link, article, or document, transcribe a YouTube video, or wants to know what a URL or video is about.
wowerpoint
Turn one document into a kawaii NotebookLM slide deck. Use for "wowerpoint this", "make a deck about ", "turn this report into slides", or any request to render a single document as shareable narrative slides.
pptx-import
A method for adding an uploaded PowerPoint presentation to an existing classroom as extra pages while keeping the slides' original layout. PowerPoint is Microsoft's presentation file format.
pdf-analysis
A PDF analysis method for reading both normal PDFs with selectable text and scanned PDFs made from page images.
potpie-resource-pdf
Use when the user asks to ingest a PDF (report, contract, paper, manual, slide export) into Potpie so agents can search and cite it. Teaches the extraction-script flow: resolve the document's identity, split on the PDF's own structure into sections and 4k-char chunks, import with potpie resource import, write…