Borrowing it
Nothing to install: this file belongs to spxrtiat111/2sense. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/spxrtiat111/2sense/main/.claude/skills/ad-learnings/SKILL.mdgit clone --depth 1 https://github.com/spxrtiat111/2senseWrote 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/spxrtiat111/2sense/ad-learnings)<a href="https://agentmods.dev/skills/spxrtiat111/2sense/ad-learnings"><img src="https://agentmods.dev/badge/skills/spxrtiat111/2sense/ad-learnings/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/spxrtiat111/2sense/ad-learnings"><img src="https://agentmods.dev/badge/skills/spxrtiat111/2sense/ad-learnings.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 | $0.00112 | $0.01040 |
| Opus 5 | $0.00056 | $0.00520 |
| Sonnet 5 | $0.00022 | $0.00208 |
| Haiku 4.5 | $0.00011 | $0.00104 |
Grade A, and why
ad-learnings 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ad-learnings
Eyes + ears come from the 2Sense MCP server (works in Claude Code AND the Desktop
app). You, the orchestrator, do the thinking.
Step 1 — Perceive (eyes + ears)
Call the MCP tool mcp__2Sense__analyze_ad with source = the path or URL the
user gave (optionally language: "fr"/"en" to force transcription language).
It returns one text block (timestamp legend + transcript) followed by the contact-sheet images — each grid cell is a frame with its timestamp burned in top-left. Look at the images (eyes) and read the transcript (ears).
- If the
2SenseMCP isn't connected, tell the user to reconnect MCP / restart, or run the CLI fallback yourself from the repo root:bin/ee prep "<src>". - CLI-only optimization for batch/long jobs: instead of the MCP images landing in your
context, run
ee prepthen spawn the ad-eyes sub-agent (subagent_type: "ad-eyes") on the sheets dir + manifest; it returns a compact JSON timeline. Use this when analyzing many videos at once.
Step 2 — Load brand context before judging
Perception is raw; good advice needs the brand's frame:
- Which brand? If unclear, ask. Load canon with the
novexlaborhautessenceskills, orqmd query "..."/ theobsidianMCP. Don't invent positioning, audience, or offer — look it up. - Pull audience, core values, awareness stages, UMP/UMS, and existing creative frameworks (pain points, concepts, format shows) relevant to this ad.
Step 3 — Teardown
Ground every claim in a timestamp (from the burned-in frame times + transcript segments):
- Hook (0–3s) — what's shown/said, the device, does it earn the next 3s? Quote it.
- Retention & pacing — cut rhythm, energy, dead spots.
- Message & awareness stage — claim/desire channeled; fit to the audience's awareness level for this brand.
- Clarity — legible without sound? (captions burned in? on-screen text?)
- Brand & product — first appearance vs. attention peak.
- CTA — present? clear? well-timed?
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 · 75 lines · 112 tokens per session scan A 1b4ba47b8edb
ad-learnings is a skill published in the GitHub repository spxrtiat111/2sense (0 stars, last pushed 2mo ago), licensed MIT. It adds 112 tokens to every session and 1,040 once invoked, about $0.0006 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 2026-09-01.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.