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 serejaris/kimi-skills --skill keynote-composergit clone --depth 1 https://github.com/serejaris/kimi-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/serejaris/kimi-skills/keynote-composer)<a href="https://agentmods.dev/skills/serejaris/kimi-skills/keynote-composer"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/keynote-composer/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/serejaris/kimi-skills/keynote-composer"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/keynote-composer.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 | $0.00079 | $0.03342 |
| Opus 5 | $0.00039 | $0.01671 |
| Sonnet 5 | $0.00016 | $0.00668 |
| Haiku 4.5 | $0.00008 | $0.00334 |
Grade A, and why
keynote-composer 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 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.
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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keynote Composer
One-line brief → professional speech draft: Built on Aristotle's Rhetorical Triangle (Ethos · Pathos · Logos), generates speech drafts tailored to product launches, galas, TED-style talks, and more—with a built-in pause/tone/pace annotation system and automatic delivery time estimation.
Quick Start
Simply describe the occasion and topic, and the Agent follows the SOP to produce a fully annotated speech draft:
User: Write a CEO address for our annual gala—reviewing last year's achievements and looking ahead
Agent: [Outputs a speech draft with pause/tone annotations + estimated duration per the SOP]
Annotation System
Speech drafts use 【】 markers to cue the speaker on rhythm and emotion:
| Category | Example | Purpose |
|---|---|---|
| Pause | 【Pause 2s】 |
Seconds of silence—builds suspense or lets the audience absorb a point |
| Tone | 【Tone: passionate】 【Tone: composed】 【Tone: warm】 |
Shifts the emotional register |
| Pace | 【Pace: slower】 【Pace: faster】 【Pace: resume normal】 |
Adjusts speaking speed |
| Action | 【Scan the room】 【Face the left section】 【Walk to center stage】 |
Body language and stage movement cues |
| Emphasis | 【Emphasis】 |
Stress the next sentence or word |
| Interaction | 【Wait for applause】 【Raise hand to invite audience participation】 |
Audience engagement moments |
Duration Estimation Rules
- Chinese speech pace varies by occasion (see Phase 5 parameters): product launch 230 chars/min, gala 220, TED-style 240, ceremonial 200
- English speech pace: 130 words/min (TED-style approx. 140–160 words/min)
- Pause durations are summed separately
- Interaction segments (applause, Q&A) are estimated per annotation
- Final output format:
Estimated duration: XX min XX sec (body XX words + pauses XX sec + interaction XX sec)
SOP Workflow
Phase 1: Context & Requirements Clarification
Goal: Establish the occasion, audience, purpose, and constraints.
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.
- 9d ago First seen · 306 lines · 79 tokens per session scan A 1781ed206d13
keynote-composer is a skill published in the GitHub repository serejaris/kimi-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 3,342 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
offensive-wifi
Wireless / 802.11 attack methodology for red team engagements and wireless security assessments. Covers monitor-mode setup, WPA/WPA2-PSK handshake capture and PMKID attacks, WPA3 SAE downgrade and Dragonblood, WPA-Enterprise (EAP) attacks (MSCHAPv2 cracking, EAP-TLS cert theft, evil-twin RADIUS), Karma / Known Beacons…
syndic
Gère un parc de copropriétés en France avec vue portfolio consolidée. Couvre administration, comptabilité (décret 2005, plan comptable copro, 5 annexes), assemblées générales (convocation, PV, notification), appels de fonds, travaux, fournisseurs, recouvrement d'impayés et transition de syndic. Maîtrise les majorités…
offensive-bluetooth-classic
Bluetooth Classic (BR/EDR) attack methodology — device discovery, service enumeration via SDP, LMP/L2CAP layer attacks, legacy PIN cracking (BlueBorne / KNOB), Bluetooth file-transfer abuse (BlueSnarfing legacy), unauthenticated profile abuse (HSP, HFP, OPP), and modern relevance against older industrial / automotive…
design-md-validator
Validate DESIGN.md files against the official Google specification using the @google/design.md CLI linter. Works with local files. Use when the user wants to lint a DESIGN.md, check spec compliance, find broken token references, verify WCAG contrast ratios, diff two versions, export tokens to Tailwind or DTCG format…
agent-wiki
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.
agent-ready-oauth-protected-resource
Sub-skill de agent-ready-cloudflare: Implement OAuth Protected Resource Metadata.