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 mycelium-hq/ai-brain-starter --skill repurpose-talkgit clone --depth 1 https://github.com/mycelium-hq/ai-brain-starterWrote 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/mycelium-hq/ai-brain-starter/repurpose-talk)<a href="https://agentmods.dev/skills/mycelium-hq/ai-brain-starter/repurpose-talk"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/repurpose-talk/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/mycelium-hq/ai-brain-starter/repurpose-talk"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/repurpose-talk.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 | $0.00101 | $0.01155 |
| Opus 5 | $0.00051 | $0.00577 |
| Sonnet 5 | $0.00020 | $0.00231 |
| Haiku 4.5 | $0.00010 | $0.00115 |
Grade A, and why
repurpose-talk 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 10d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repurpose Talk
Turn a single speaking engagement into maximum content leverage. Run this after any talk, panel, fireside chat, or workshop.
Trigger
/repurpose-talk or when the user says "I just gave a talk", "the panel is done", "just finished speaking"
Input
Ask for (in this order, skip any they don't have):
- Recording - video/audio file path or link
- Transcript - if available (check meeting note tools, Google Docs, or manual notes)
- Slides - if used
- If none of the above: ask them to brain-dump the key points, best audience reactions, and any quotes they remember
Process
Phase 1: Extract (from whatever input is available)
Pull out:
- 3-5 key insights they shared (the things that made people nod or take notes)
- 1-2 stories they told (personal anecdotes are the highest-performing content)
- Best one-liners (quotable sentences, these become standalone posts)
- Audience questions that came up (each question is a content seed)
- The main thesis of the talk in one sentence
Phase 1.5: Score clip candidates against the virality framework
For each candidate moment (one-liner, story beat, question, insight), tag which virality category it hits. Cherry-picked from SamurAIGPT/Generative-Media-Skills ai-clipping SKILL.md (MIT) — 8 categories that explain WHY short-form clips travel:
- Hook moments — strong opening line that stops the scroll
- Emotional peaks — laughter, anger, vulnerability, awe
- Opinion bombs — spicy, contrarian, debate-bait takes
- Revelation moments — "wait, what?" reframes
- Conflict — disagreement, tension, callouts
- Quotable lines — tight, screenshot-worthy phrasing
- Story peaks — climax of a narrative arc
- Practical value — actionable insight a viewer will save
A clip that hits 2+ categories is a stronger pick than one that hits 1. A clip that hits 0 isn't worth packaging — drop it.
The taxonomy is FOR RANKING + EXPLAINING, not for inventing content. Every clip still has to come from the actual talk; never confabulate a "spicy take" the speaker didn't make.
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.
- 10d ago First seen · 103 lines · 101 tokens per session scan A 1c60703bc433
repurpose-talk is a skill published in the GitHub repository mycelium-hq/ai-brain-starter (36 stars, last pushed yesterday), licensed MIT. It adds 101 tokens to every session and 1,155 once invoked, about $0.0005 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
canvas
Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.
agent-tamagotchi
Terminal pet that lives in your statusline. 12 species, 5 stats (DEBUGGING, PATIENCE, CHAOS, WISDOM, SPEED). Reacts to your workflow - happy when tests pass, sad when builds fail, excited during swarm mode. Deterministic species from user ID.
flow
Personal task and agent-session manager. CLI binary is flow (assumed on PATH) and stores metadata in /.flow/flow.db (SQLite). Use this skill when the user asks about their work, tasks, or projects in any natural phrasing — including but not limited to: "what's left", "what's remaining", "what's pending", "what do I…
meme-generator
Generate captioned meme images for social replies and chat. Use when the user asks for a meme, wants to caption an image with top/bottom text, or needs a quick visual for a post. Produces a PNG from a template plus caption text.
daily-brief
Compose a morning briefing for the user by pulling today's calendar, open tasks, and relevant memory, then delivering a short prioritized summary over the primary chat channel. Use when the user asks for a daily brief, "what's on today", a standup, or sets up a scheduled morning digest.
tg-slot
Free a membership slot so a Telegram account can join or create a group. Accounts have a hard ceiling on channels plus supergroups, and at the ceiling both creating and joining fail with an error that misleadingly blames the target chat. Finds the least-valuable current memberships, proposes what to leave, and retries…