← Back to Skills Marketplace
zack-dev-cm

TinyTroupe Feed Research Lab

by Zakhar Pashkin · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
87
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install tinytroupe-feed-research-lab
Description
Run bounded synthetic audience research for draft posts and X-style feed experiments inspired by TinyTroupe and public xai-org/x-algorithm architecture. Use...
README (SKILL.md)

TinyTroupe Feed Research Lab

Use this skill to compare draft posts with synthetic audience personas and produce a research report. Treat outputs as qualitative pretesting and hypothesis generation, not live X ranking predictions.

Core Workflow

  1. Collect 2-10 draft posts or content angles.
  2. Clarify the target audience if available.
  3. Run scripts/tinytroupe_feed_research_lab.py in deterministic mode.
  4. Read feed_research_report.md, feed_research.json, and persona_reactions.csv.
  5. Present the best draft, why it won, key objections, rewrite suggestions, and the boundary statement.
  6. If the user asks for TinyTroupe proper, use the generated persona specs and experiment plan as the input to a separate TinyTroupe notebook or script.

Quick Start

SKILL_DIR="${CODEX_HOME:-$HOME/.codex}/skills/tinytroupe-feed-research-lab"
python3 "$SKILL_DIR/scripts/tinytroupe_feed_research_lab.py" \
  --audience "AI builders and creator-operators interested in X algorithm research" \
  --draft "I audited this viral X algorithm claim against public source. Verdict: misleading." \
  --draft "Replies are king. Here is what the public repo actually proves." \
  --output-dir /tmp/tinytroupe-feed-research

Use files:

python3 "$SKILL_DIR/scripts/tinytroupe_feed_research_lab.py" \
  --drafts-file /tmp/drafts.json \
  --personas-file /tmp/personas.json \
  --output-dir /tmp/tinytroupe-feed-research

The script writes:

  • feed_research_report.md: human-readable comparison and rewrite guidance.
  • feed_research.json: machine-readable drafts, personas, reactions, and warnings.
  • persona_reactions.csv: row-level persona reactions.
  • share_card.md: short public-safe summary.
  • share_card.svg: visual summary card.
  • tinytroupe_experiment_plan.md: optional bridge plan for a real TinyTroupe run.

Input Formats

--drafts-file accepts:

  • JSON list of strings.
  • JSON list of objects with id and text.
  • Plain text blocks separated by ---.

--personas-file accepts JSON objects with:

  • name
  • segment
  • interests
  • dislikes
  • reply_bias
  • skepticism
  • link_sensitivity
  • safety_strictness

Missing persona fields fall back to conservative defaults.

Boundaries

Read references/research-boundaries.md before presenting results that mention algorithms, feed ranking, virality, reach, shadowbans, or account status.

Never say:

  • "this predicts reach,"
  • "this clones the X For You feed,"
  • "this proves a shadowban,"
  • "this optimizes for the live algorithm,"
  • "this is what real users will do."

Prefer:

  • "synthetic audience reaction,"
  • "draft pretest,"
  • "conversation-quality signal,"
  • "X-style feed research sandbox,"
  • "hypothesis to validate with real posting or user research."

TinyTroupe Bridge

The MVP script does not require TinyTroupe. It produces tinytroupe_experiment_plan.md so a later agent can create a TinyTroupe notebook with:

  • the same personas,
  • the same draft set,
  • a structured reaction schema,
  • a validation note that simulation outputs are research signals.

Companion Skills

Use x-algo-claim-auditor when the task is checking whether a viral algorithm claim is true. Use open-feed-recsys-lab when the task is verifying the public source repo, Phoenix artifact readiness, or architecture map.

Usage Guidance
This looks safe to install for local draft-research use. Before running it, review the command, provide only drafts you are comfortable storing locally, and choose a private output directory for the generated reports.
Capability Analysis
Type: OpenClaw Skill Name: tinytroupe-feed-research-lab Version: 1.0.0 The skill bundle provides a deterministic simulation tool for analyzing social media draft posts against synthetic personas. The Python script (scripts/tinytroupe_feed_research_lab.py) performs local data processing using standard libraries without network access, shell execution, or sensitive file reads. The instructions in SKILL.md and documentation in research-boundaries.md include explicit safety guidelines to prevent the AI agent from making misleading claims about reach or algorithm prediction.
Capability Tags
crypto
Capability Assessment
Purpose & Capability
The stated purpose is synthetic audience pretesting for draft posts, and the visible artifacts align with that purpose through persona scoring, bounded claims, and explicit warnings not to present results as live X reach or ranking predictions.
Instruction Scope
The instructions are scoped to collecting drafts, running the bundled script, reading generated reports, and presenting bounded qualitative findings. No prompt override, hidden goal change, or forced unsafe tool use is evident.
Install Mechanism
There is no package install step or external dependency installation, but use does require running the bundled local Python script. This is expected for the skill's purpose.
Credentials
The script reads user-selected draft/persona files and writes reports to a user-specified output directory. This is proportionate, but generated files may contain draft content and should be stored carefully.
Persistence & Privilege
No credentials, privileged access, network calls, or background persistence are declared. The only persistence shown is local report output such as JSON, CSV, Markdown, and SVG files.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install tinytroupe-feed-research-lab
  3. After installation, invoke the skill by name or use /tinytroupe-feed-research-lab
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: compare draft posts with deterministic synthetic audience personas and bounded feed-research reports.
Metadata
Slug tinytroupe-feed-research-lab
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is TinyTroupe Feed Research Lab?

Run bounded synthetic audience research for draft posts and X-style feed experiments inspired by TinyTroupe and public xai-org/x-algorithm architecture. Use... It is an AI Agent Skill for Claude Code / OpenClaw, with 87 downloads so far.

How do I install TinyTroupe Feed Research Lab?

Run "/install tinytroupe-feed-research-lab" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is TinyTroupe Feed Research Lab free?

Yes, TinyTroupe Feed Research Lab is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does TinyTroupe Feed Research Lab support?

TinyTroupe Feed Research Lab is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created TinyTroupe Feed Research Lab?

It is built and maintained by Zakhar Pashkin (@zack-dev-cm); the current version is v1.0.0.

💬 Comments