Observed by Atlas — nobody has proved they control this domain. Is it yours?
AgenticKit
OBSERVEDAI agents, skills and commands that write real feature code into your repo
- FRESHNESS
- 0.97
- DECAYS BETWEEN READS
- READINGS
- —
- VERIFIED / MEASURED
- VOUCHES
- 0
- SIGNED STATEMENTS
- THREADS
- 0
- FIELD NOTES
- CLICKS · 28D
- 1
- BOT-FILTERED
- FIRST SEEN
- AUG 19
- IN THE FLOW
AgenticKit installs a set of AI agents, skills, and slash commands into a repository's .cursor/ and .claude/ folders, enabling automated workflows like /ship to generate schema, API endpoints, tests, and docs directly as files. It covers both engineering tasks (feature pipelines, APIs, database migrations, security audits, deployments) and marketing tasks (positioning, landing page copy, email sequences, launch strategies). It is designed for use with Cursor and Claude Code by SaaS development teams.
Nothing measured yet. A reading is a measurement with its evidence attached — uptime checked, pricing re-read against what the page claims. Raise a checkable claim in a field note below and Atlas will measure it.
22 engineering agents · 23 slash commands (/ship, /build-api, …) · 30 skills + CURSOR.md auto-sync · ENGINEERING-ORG.md role map
Full engineering & marketing kit · Install engineering, marketing, or both · All org maps + kit updates · License key by email
12 marketing agents · 12 slash commands (/launch, /positioning, …) · 20 skills + docs/marketing/ auto-save · MARKETING-ORG.md role map
Every crawl is diffed. Material changes are listed.
Nobody has vouched for AgenticKit yet.
A vouch says you use it. Your handle, how long, and an optional note.
I use this — vouchHave a question about AgenticKit? Ask the people using it.
No field notes yet. A field note is about use: what broke, what it replaced, what the docs don't say. Anything in one that makes a checkable claim gets measured by Atlas, which replies with the reading.
Outbound clicks are counted for the builder.
Claim it