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 ooiyeefei/ccc --skill pitch-craftgit clone --depth 1 https://github.com/ooiyeefei/cccWrote 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/ooiyeefei/ccc/pitch-craft)<a href="https://agentmods.dev/skills/ooiyeefei/ccc/pitch-craft"><img src="https://agentmods.dev/badge/skills/ooiyeefei/ccc/pitch-craft/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/ooiyeefei/ccc/pitch-craft"><img src="https://agentmods.dev/badge/skills/ooiyeefei/ccc/pitch-craft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00157 | $0.01554 |
| Opus 5 | $0.00078 | $0.00777 |
| Sonnet 5 | $0.00031 | $0.00311 |
| Haiku 4.5 | $0.00016 | $0.00155 |
Grade A, and why
pitch-craft 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pitch Craft - Timed Spoken Scripts
A timed script is engineering plus theater. The clock is a hard constraint; the storytelling is why anyone remembers you. Every failure mode of a bad script traces to violating one of those two, so this skill enforces both: beats before words, and the craft rules in references/storytelling.md.
Steps
1. Beats before words
Get three things before drafting a single sentence:
- The beats: what is on screen (or on stage) at each moment, in order. For a demo voiceover these are the recording's milestones - use the sidecar's verified
t_videovalues, never planned holds (see demo-video's Gate 3); for a deck they are the slides; for a live pitch they are slides plus stage moments (team intro, demo break). - The clock: either fixed windows from an existing recording (
0:16 -> 0:43), or a total slot to budget (a 5-minute pitch). - What each beat proves: a beat with no claim behind it gets cut, not narrated.
If the beats don't exist yet, build the beat sheet first and get the user's sign-off. For a demo film that beat sheet is demo-video's storyboard - five columns, journey coverage, Gate 1 approval - not an ad-hoc list. Prose written before beats always runs long and anchors the story to sentences instead of evidence.
2. Budget the words
Read references/timing.md and compute a word ceiling per segment (words = seconds x words-per-second; voiceover ~2.4-2.6 wps, live stage ~2.0-2.2 wps). Write the budget line at the top of the script (e.g. 5:00 slot = ~2:30 spoken + 2:36 demo). If the numbers don't fit before writing, they won't fit after.
3. Draft with the craft rules
Read references/storytelling.md and apply it: hook before names, analogy per abstraction, a throughline that bookends and is re-emphasised where earned (paraphrased, not repeated verbatim), plain words, numbers that land twice. Recorded voiceover and live speech are different registers - never reuse one as the other (see the register section in storytelling.md).
What ships with it
5 files 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 · 81 lines · 157 tokens per session scan A 6d93d2cfc750
pitch-craft is a skill published in the GitHub repository ooiyeefei/ccc (487 stars, last pushed 1mo ago), licensed MIT. It adds 157 tokens to every session and 1,554 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…