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 agentmods add commands/noamseg/interview-coach-skill/presentgit clone --depth 1 https://github.com/noamseg/interview-coach-skillWrote 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/commands/noamseg/interview-coach-skill/present)<a href="https://agentmods.dev/commands/noamseg/interview-coach-skill/present"><img src="https://agentmods.dev/badge/commands/noamseg/interview-coach-skill/present.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.05138 |
| Opus 5 | $0.00000 | $0.02569 |
| Sonnet 5 | $0.00000 | $0.01028 |
| Haiku 4.5 | $0.00000 | $0.00514 |
Grade A, and why
present 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 4d 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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
present — Presentation Round Coaching
How Presentation Rounds Actually Work (Reference Knowledge)
Format Prevalence: Presentation rounds appear across seniority levels and functions:
- Senior+ engineering: system design presentations, architecture reviews, tech deep dives
- Product management: product sense, business case, strategy presentations
- Design: portfolio reviews, design critiques
- Data science: analysis presentations, methodology reviews
- Executive roles: strategic vision, 90-day plans, board-style presentations
- Consulting: case presentations
- Pre-sales/solutions engineering: technical demos, solution presentations
What Evaluators Actually Assess (from interview design literature and hiring manager perspectives):
- Communication clarity — Can they explain complex ideas simply? Do they calibrate to the audience?
- Structured thinking — Does the presentation have a logical arc? Can you follow the reasoning?
- Audience calibration — Did they pitch at the right level? A technical deep dive for executives fails. An executive summary for engineers fails.
- Time management — Did they stay within bounds? Going over time is the #1 presentation-round failure mode.
- Depth vs. breadth judgment — Do they know when to go deep and when to stay high-level?
- Q&A handling — Can they think on their feet? Do they admit what they don't know? Do they redirect constructively?
- Confidence and poise — Not arrogance, but comfort with the material and the format. Matt Abrahams (Stanford, via Lenny's Podcast) distinguishes between "performance confidence" (acting confident) and "process confidence" (trusting your preparation). Candidates who try to perform confidence often appear rehearsed. Candidates who trust their process appear natural. The warmup routine should build process confidence — comfort with the structure, flow, and key transitions — not a polished performance.
Narrative Arc Frameworks:
- Situation-Complication-Resolution (SCR) — Most versatile. Present the context, introduce the tension, deliver the resolution. Works for most technical and business presentations.
- Problem-Approach-Results-Learnings (PARL) — Best for technical/analytical presentations. Shows methodology and rigor. Common in data science and engineering deep dives.
- Context-Challenge-Options-Recommendation (CCOR) — Best for business case and strategy presentations. Shows decision-making process. Common in PM and executive rounds.
- Hook-Build-Deliver-Land (HBDL) — Best for executive audiences. Start with the punchline, build the evidence, close with the ask. Executives decide in the first 30 seconds whether to pay attention.
- What Is / What Could Be / New Bliss (Duarte) — Nancy Duarte's framework (CEO of Duarte Inc., 250,000+ presentations crafted, via Lenny's Podcast): Alternate between current reality ("What Is") and future possibility ("What Could Be") to build tension and longing, then end on the transformed future state ("New Bliss"). Found in MLK's "I Have a Dream," Steve Jobs's iPhone launch, and hundreds of great talks. Works at any scale from a 2-minute pitch to a 60-minute keynote. The key principle: the audience is the hero, not you — as Duarte puts it: "Your audience gets to make a choice if they accept or reject your idea. So, the balance of power is with them and not you." Position yourself as the mentor who brings tools and resolve, not the hero proving how great you are.
- Strategic Narrative (Raskin) — Andy Raskin's 5-part framework (strategic narrative consultant, "The Greatest Sales Deck I've Ever Seen" with 2M+ views, via Lenny's Podcast): (1) Name the shift — what's changed in the world (Old Game → New Game), (2) Name the stakes — who wins and who loses, (3) Name the object of the new game — the rallying cry, (4) Show the obstacles — what makes this hard, (5) Show how you overcome obstacles — your "magic gifts." This replaces the "arrogant doctor" anti-pattern (problem → my solution → why mine is better). For presentation rounds: don't do a feature walkthrough of your case study. Structure it as: here's the shift, here's who's winning, here's the goal, here's what's hard, here's how I/we overcame it. As Raskin puts it: "We didn't change the product — it was basically the same business, just how we talked about it."
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.
- 4d ago First seen · 358 lines · 0 tokens per session scan A c54a186480b5
present is a command published in the GitHub repository noamseg/interview-coach-skill (2,074 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,138 tokens. 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.
Other commands, from other repositories
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
cheatsheet
Generate a one-page exam cheatsheet from course-index and errors/log.md. Outputs to cheatsheet/final.md. Optionally convert to PDF.
learn-story-flow
Learn story-flow concepts with interactive guidance for junior developers.
no-vibe
Enter no-vibe mode in OpenCode (tutor mode, no direct project file writes).
teach-me-testing
Teach testing progressively through structured sessions. Use when user says ""lets learn testing"" or ""I want to study test practices"".
setup-bigquery.es
Command "setup-bigquery.es" from minicoohei/ai-agent-camp, covering configuración de autenticación bigquery / gcp, step 0: verificar el progreso de configuración, lo que hará en esta sesión, verificación de preparación and step 1: instalación de gcloud cli.