Productivity
mdkit
Last updated 2026-11-18 · benchmark measured 2026-11-18 — deterministic & reproducible
Desktop app for organizing, syncing, and sharing AI-generated markdown files.
mdkit at a glance
mdkit is a desktop app for macOS and Windows that organizes, versions, and syncs the .md skill files generated by AI tools like ChatGPT, Claude, and Notion, for individuals and teams.
Good for
- Finance teams standardizing AI-generated reports like earnings summaries, risk summaries, and client briefs
- Organizations building a shared skill.md library so new hires and team members automatically get the latest updates
- Developers versioning AI coding skills for code review, debugging, and scaffolding, with the ability to roll back regressions
Pricing
Free to download and use, no account required; Enterprise plan with more storage, admin controls, and support available by contacting sales.
Questions people ask
What does mdkit do?
It stores, versions, and syncs the .md files (skill.md files) produced by AI tools such as ChatGPT, Claude, and Notion, and makes them accessible from the menu bar on macOS and Windows.
Who is mdkit for?
It's for anyone who uses AI tools and wants to organize, version, and share their skill.md files, including AI tool users, finance teams, developers, organizations, and new hires.
How much does mdkit cost?
mdkit is free to download and use with no account required, and an Enterprise plan with more storage and admin controls is available by contacting sales.
Can my team share skill.md files and get updates automatically?
Yes, teams can build a shared skill.md library, and when a skill is updated, everyone with access gets the latest version automatically.
Does mdkit support version control and rollback?
Yes, it includes version control for AI workflows so you can track changes and roll back a skill.md file if it regresses.
Written by Legit.Show from mdkit.ai on 2026-11-18. It does not change the score.
Are you the maker of mdkit? Claim this listing. It is free, takes a meta tag, a DNS record or GitHub admin rights, and never changes the score.
Launched something? Add your product, free.
To cite this score: legit.show/s/mdkit-ai/2026-11-18. That address never changes; this page moves with every re-measure.
Legit.Show scored mdkit 68/100 on 2026-11-18, measured across all 7 frames from its public surface. legit.show/s/mdkit-ai/2026-11-18
Is mdkit production-ready?
Legit.Show scores mdkit 68 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on mdkit (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Performance; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 100/100
- Accessibility — 95/100
- Security — 35/100How this compares across the catalogue: The Web Security Baseline
- Privacy — 25/100How this compares across the catalogue: The Privacy Gap
- Reliability — 92/100
- Standards — 92/100
- Discoverability — 35/100
What we measured
- Security headers present: X-Content-Type-Options.
- No Content-Security-Policy and no HSTS.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 28 ms to first byte.
- Returns a proper 404 for unknown routes.
- 0 of 0 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
Who it's for
AI tool users · Finance teams · Developers · Organizations · New hires
Pricing
Free (with Enterprise plan available)
Sources and updates
- Description
- Taken from mdkit.ai's own website on 2026-11-18.
- Benchmark
- Measured by Legit.Show from the live site, the way any visitor sees it — with no access to its code or accounts. Same method for every product, and no AI decides the score. Last checked 2026-11-18.
Put together from public information, without mdkit's involvement. If anything here is wrong, tell us and a person will check it.
Visit mdkit → · Alternatives to mdkit → · How this was measured →