Nothing declared. Everything counted.

Turn Your Logs Into Skills.

Not someone else's skill pack.
Derived from how you actually work, receipts on every line. 

  ~ stratless tune

  Your tune — Claude Code pair

  Measured from this record: 8 rituals · 8 lessons · 9 rules
                             · 1 win · 8 arrivals

  The sitting asks your own Claude Code once — about $0.08
  of your plan. Proceed? [y/N] y

  2 skills proposed from the evidence

  THE PACK — every entry is a skill file
    ⚙ watch-ci-after-merge  (occurrences 283 · sessions 88)  new
      A completed merge is followed by an actual CI status
      check before the turn is called finished.
    ⚙ name-the-mechanism-plainly  (count 4 · sessions 4)  new
      Every direct meaning-question gets a concrete,
      jargon-free answer naming the actual mechanism.

  writes to ~/.claude/skills · nothing else touched
  every receipt is your own count · remove any time: stratless stop

  Install? [y/N]
InstallRead the source

MIT. No account, no API key, no cloud. Nothing leaves your machine.

Install

Try it free · Type into your terminal

npx stratless

v0.15.1 · MIT · changelog ↗

There's no trick

The conversation was always there.

No cloud. No training. No separate bill. Your assistant already keeps every chat on your disk, Claude Code in ~/.claude/projects and Codex in ~/.codex/sessions, and probably nobody reads them.
Stratless reads what you did, counts what recurs, and compiles the skills your history already earned.

On your machine, your chats are measured into evidence, and the sitting turns the evidence into skills. One runtime comes in at init. Nothing goes out.

Derived, not pre-matched. Minutes to build. how it works →

Reads Claude Code and Codex

Made for your AI. Meant for you.

The two assistants stratless reads today, and the only two it names. Skills install to both, each through its own native skill door, measured against the real thing.