← ClaudeAtlas

characterlisted

Train how a model talks from a constitution (a model spec) and prove the trait moved without costing anything else. Use when asked to give an agent a character, persona or voice that survives without a system prompt, to turn a model spec or list of principles into training data, to build DPO pairs or SFT rows for style, or to measure a trait before and after training. The judge is checked against the spec's own labeled replies before any pass rate is read; every trait is a Behavior on the platform, plus a control for what must not regress.
whilehq/whileai-sdk · ★ 3 · AI & Automation · score 77
Install: claude install-skill whilehq/whileai-sdk
# Character from a constitution A constitution is a list of principles with labeled examples. This skill turns it into graded rows, checks the judge, builds the training rows, and measures each trait before and after on frozen held-out prompts. The pipeline is the one Maiya et al. 2025 open-sourced: traits, prompts that exercise each trait, several replies per prompt, a judge that reads the principle, then preference pairs and SFT rows. Worked example with the OpenAI Model Spec: `recipes/03-select/character/`. `check.py` runs all of it offline. Names it defines that the blocks below use: `CONSTITUTION` (three traits, four situations each, one GOOD and two BAD replies per situation), `build_tasks` (one task per wording of each situation, split train/held-out by situation hash), `sample_rows` (a scripted student that replays the spec's replies at a fixed rate; `after=True` plays a student that landed the training), `K` replies per prompt, `TASKS_BY_ID`, `grade` (`wai.run_judge` with a lookup judge that reads `privileged.principle`, then the markers `trait`, `on_task`, `no_filler`), `spec_rows` (the spec's own replies with `gold_reward` and `gold_kind="human"`), `behavior_score` (points, 95% half-width, n from `wai.marker_summary`), `noise_floor` (re-run std in points from `wai.eval_variance`), `fake` (a recording transport that answers like the platform). Live, the student is a model sampled under the deployment prompt only (`You are Sol, an assistant.`, no constitution) and