Turn supplied post exports into a social performance review with CSV column mapping, comparable date windows, linked channel charts and exact weighted rates. Export source and filtered metrics, then build native editable charts, PowerPoint and a 30-second film.
Domain result film + actual browser walkthrough · editable inputs
workbench.html + workbench.js + workbench.csssource-bundle.zip exported by browser; project.json + optional CSV/imagespresentation.html + presentation.pptx + editable native domain pagesfull domain CSV / JSON / SOP handoffactual MP4 + captions + chapter stills + input/render evidenceImport your post CSV, review the column mapping, compare equal windows and filter the linked charts. Watch the 30-second report film and real CSV-to-export browser walkthrough.
FIELDNOTES data is fictional practice material. Impressions are not unique reach, clicks do not prove revenue, and descriptive differences are not causal lift. No private analytics fetch, posting or paid image generation occurs.
Capabilities: Zero-dependency editor launch; CSV upload and explicit column mapping; equal-window validation; channel/metric chart filters; exact weighted engagement and CTR; missing/zero-denominator handling; source-linked experiment drafts.
Deliverables: Live local report, canonical CSV/source ZIP, filtered metrics export, native editable PowerPoint channel chart and deck, exact input/calculation files, 30-second result movie, captions and evidence manifest.
First run: python3 scripts/start.py. Local editor needs no pip install; rendering uses the included pinned requirements.
Review: Upload your CSV in Edit inputs, confirm the metric definitions and column mapping, then Apply. Select channel and chart metric in Result preview. Download filtered metrics or export the whole source bundle; your agent regenerates PowerPoint and video from those exact files.
FROM PACKAGE TO FIRST RESULT
Import your post CSV, review the column mapping, compare equal windows and filter the linked charts. Watch the 30-second report film and real CSV-to-export browser walkthrough.
These steps use a project folder. Open the project in your agent and run terminal commands from its root.
Package folder .agents/skills/social-performance-studio
Download and unzip the package into the folder above. Keep all its files together, with SKILL.md directly inside that folder.
Downloads require a verified account and purchase access. Choose a new folder if this Skill is already installed.
Read SKILL.md, review the generator and check its runtime requirements before running:
cd .agents/skills/social-performance-studio
python3 scripts/start.pyUpload your CSV in Edit inputs, confirm the metric definitions and column mapping, then Apply. Select channel and chart metric in Result preview. Download filtered metrics or export the whole source bundle; your agent regenerates PowerPoint and video from those exact files.
Python 3.10+ starts the editor without installing dependencies. MP4/PPTX generation uses pinned Pillow, python-pptx and local FFmpeg. Result films are renders; walkthroughs record actual local browser actions with practice input. No paid API, agent execution or publication call. Non-ASCII film copy needs a permitted font with its glyphs.
If delivery already exists, change the output to ./delivery-2. Existing files are never overwritten.
Use Social Performance Studio at .agents/skills/social-performance-studio. Read SKILL.md and review scripts/build-report.py. Run examples/project.json into a new output folder and show me all generated files. Keep fictional sample content clearly labeled.
Tried this workflow? Help others decide with an honest review.
The listed individual package price is USD 4.99. Premium downloads require a confirmed purchase or active membership. Your agent subscription, model access and external provider credits are separate.
This release lists Codex, Claude Code, Cursor as intended installation hosts. Check the package’s dependencies and permissions before running it. These labels do not certify that every workflow has been tested in every agent.
The documented 1.1.0 workflow lists: workbench.html + workbench.js + workbench.css; source-bundle.zip exported by browser; project.json + optional CSV/images; presentation.html + presentation.pptx + editable native domain pages; full domain CSV / JSON / SOP handoff; actual MP4 + captions + chapter stills + input/render evidence. Some files or exports are optional; follow the package’s setup and inspect the delivered result.
Python 3.10+ starts the editor without installing dependencies. MP4/PPTX generation uses pinned Pillow, python-pptx and local FFmpeg. Result films are renders; walkthroughs record actual local browser actions with practice input. No paid API, agent execution or publication call. Non-ASCII film copy needs a permitted font with its glyphs.
