Founder Consumer

Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else. Prerequisites: Python 3.8 or newer, to run the bundled panel.py tool (standard library only, nothing to pip install), and an agent environment that can launch sub-agents: a full panel is 100 sub-agent calls by default (20 with --quick), which uses your own agent usage. No API key, no account, no paid service charged by the skill itself. Install "Founder Consumer" for me. It is a consumer panel: it builds a target customer profile and one pitch, deals reproducible buyer cards with the bundled Python tool panel.py, runs one sub-agent per buyer (100 by default, 20 in quick mode), and tallies who buys, who passes and why into founder/panel/results.md, with price answers for founder-pricing. Repository: https://github.com/Jakeschincariol/founder-skill (the skill is the whole skills/founder-consumer/ folder at the pinned commit: SKILL.md, customer.example.json, panel.py, pitch.example.md) Pinned version: install the code at commit fd9385b0cfe1b96bebce3898fbd506d73eff5a9d exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone https://github.com/Jakeschincariol/founder-skill into a temporary folder, check out commit fd9385b0cfe1b96bebce3898fbd506d73eff5a9d, and copy the skills/founder-consumer/ folder from that checkout. Then compare every file in the folder with the fingerprints recorded for this listing on 2026-10-18: [FINGERPRINTS] - SKILL.md: SHA-256 2f13355139a47ba1079dd7b4a16f719a4dbbf684813bb8193e33bdf85b75e1d0 - customer.example.json: SHA-256 b99cd47234629536d5ca12cc0be2c2b2df8094d1a706930e0f8ebf501bcf5963 - panel.py: SHA-256 fb765256dbf892c48e8622634dd45a37d12422cab510ee88351c43935e167eca - pitch.example.md: SHA-256 5f3d4c3723843485c257abc27d3daba2f6bb4562379f5a0f5134daa1121739fc If a file does not match, it changed since the listing was prepared: do not install it yet, tell me what you found and let me decide. 2. Read SKILL.md in full (and every other file in the folder) and tell me in plain words: what the skill does when used, which services it connects to, whether it reads or sends any personal information or keys, and anything that seems unusual. Stop on any red flag and tell me before going further. Confirm these points from the files: - The skill folder holds four files: SKILL.md, panel.py, customer.example.json (an example customer profile) and pitch.example.md (an example pitch). panel.py uses the standard library only (argparse, json, os, random, sys), reads and writes local files under founder/panel/, and makes no network calls, reads no credentials and no environment variables beyond file paths, and installs nothing. - When used, the panel runs as sub-agents inside your own agent environment (one per simulated buyer, in waves of 10). The moderator never answers for a buyer, and a buyer that fails twice is left out and counted. The skill itself contacts no external service and uploads nothing: the cost is your own agent usage for those sub-agent calls, which the file tells the agent to announce before a 100-buyer run. - What the panel produces is simulated research, stated in the file: buy rates are an upper bound because language models lean agreeable, and panel quotes must never be presented as customer testimonials. - Outputs stay in your project under founder/ (customer.json, pitch.md, panel/ cards, briefs, answers and results). Nothing is sent anywhere during installation itself; the only download is the skill folder from GitHub at the pinned commit. 3. When I say "yes, install", install it as a skill: copy the whole folder into the agent's skills directory, in a folder named "founder-consumer", keeping every file (SKILL.md, customer.example.json, panel.py, pitch.example.md). 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (for example: install Python 3.8 or newer if it is missing (the bundled tool needs it at use time; installing the skill itself needs nothing else), sign in or create an account (none is needed), provide any API key (none is needed); using the skill is a separate step that only starts when I ask for it). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.