← all publishers

experientiallabs

@experientiallabs source repo

Report this profile Claim this profile

• 9 skills
• 0 followers
• 6 hours ago last updated

1. ▌
   Test Build · experientiallabs

   Run the live Experiential build-to-serve path as an unattended automation. Fits the pinned terminal-tasks trace export through the CLI, calibrates the judge non-interactively, fits a router, verifies exact replay, and serves the frozen policy on loopback. Use when asked to test the build path, verify cloud setup, or attach this skill to an automation.
   0
   installs
2. ▌
   Test Gateway · experientiallabs

   End-to-end happy-path test of the Experiential local gateway, covering interactive first-run setup via the exp run TUI, the served OpenAI-compatible routes, usage accounting, restart persistence, and integration with an external OpenAI-compatible client such as opencode. Use when asked to test, validate, or demo the local gateway.
   0
   installs
3. ▌
   Improve Judge · experientiallabs

   Improve a canonical common-owned judge from reviewed rollout evidence, human labels, and leakage-safe calibration without bypassing the frozen router workflow.
   0
   installs
4. ▌
   Ready For Merge · experientiallabs

   Mandatory pre-merge gate for every PR. Runs /code-review --fix at an effort level scaled to the PR's breadth, resolves every review comment (Cursor, Greptile, humans), and verifies the diff complies with AGENTS.md. Use whenever the user says a PR is ready to merge, asks to merge, or invokes /ready-for-merge.
   0
   installs
5. ▌
   Pr Feedback · experientiallabs

   Address reviewer feedback on GitHub pull requests by making targeted fixes or explaining disagreements. Use when responding to PR comments.
   0
   installs
6. ▌
   Setup Local · experientiallabs

   Set up the full CLaaS stack (vLLM + API + OpenClaw/Telegram) locally. Uses Docker if available, falls back to native setup otherwise.
   0
   installs
7. ▌
   Setup Modal · experientiallabs

   Deploy the CLaaS Modal serverless distillation API. Use when deploying the SDPO distillation service to production.
   0
   installs
8. ▌
   Setup Tinker · experientiallabs

   Deploy the CLaaS Tinker stack (API + OpenClaw/Telegram) via Docker Compose. No GPU required.
   0
   installs
9. ▌
   Clear Tinker Storage · experientiallabs

   Delete all checkpoints from your Thinking Machine Tinker prod account to reduce storage charges. Requires TINKER_API_KEY.
   0
   installs