An open-source set of go-to-market skills for solo technical founders — positioning, first users, launch and pricing, sequenced into a roadmap your agent works with you.
AGENTS.md AuthoringSkill
Summary
Write and maintain concise AGENTS.md and CLAUDE.md files that document the conventions an agent actually needs.
Features
- Creates concise, reference-backed AGENTS.md and CLAUDE.md files
- Documents conventions agents actually need
- Keeps instruction files maintained rather than stale
Install This Skill
Add this skill to your favorite AI agent in a few steps.
Skill Content
Description
Project instruction files fail in two directions: too thin to be useful, or so long that the important rules are buried. This skill produces ones that work.
It covers what belongs in an AGENTS.md or CLAUDE.md — build and test commands, architectural constraints, conventions that are not obvious from the code, and the mistakes newcomers reliably make — and, just as importantly, what does not: restating what the code says, generic best practice, and anything an agent can determine by looking.
It also covers maintenance, since the main failure mode of these files is drifting out of date until they actively mislead. Every claim is expected to be backed by a reference in the repository rather than asserted. Published by Sentry.
Related Skills
Multi-source academic literature search as an agent skill — OpenAlex, Semantic Scholar, CrossRef, PubMed and arXiv at four depths, from a 5-minute scan to a PRISMA-S logged systematic review.
Claude Code skill that audits a site for visibility in AI answers — citability scoring, AI-crawler access, llms.txt, schema markup and brand-mention scanning — plus classic technical SEO.
A four-skill bundle that runs the academic pipeline end to end — deep research, paper writing, peer review and revision — as multi-agent workflows inside Claude Code.