Agent skill

train-convo-steering

Voice-first runtime steering + nightly deep analysis to learn per-user conversation steering priors.

majiayu000534★ · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill train-convo-steering --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 3 KB
Bundled scripts: none
Path: skills/ai-llm/train-convo-steering/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

--- name: train-convo-steering description: Voice-first runtime steering + nightly deep analysis to learn per-user conversation priors. triggers: - train convo steering - runtime steering step - train steering nightly provides: - train-convo-steering composes: [, task-monitor] --- # train-convo-steering (Skill v2) Voice-first **runtime steering** + nightly **deep analysis** to learn per-user conversation steering priors. This skill is designed for: - **Live voice**: per-turn inference must be fast and bounded (preset selection, not multi-candidate judging). - **Nightly deep learning**: optional DeepSeek V3 (TEE) judge calls to improve labels and update per-user priors. ## Concepts ### Collaboration State A compact state bucket per turn (`tempo`, `trust`, `alignment`, `affect`, `control`) mapped to `{low, mid, high}`. ### Steering Presets Configuration of response knobs (length, questions, initiative, certainty, grounding) and voice prosody. - `fast_proceed` - `clarify_once` - `trust_repair` - `deep_dive` - `exec_summary_plus_steps` - `socratic` ### Priors Per-user policy map `state key -> best preset` learned from reinforcement signals (user feedback, latency, DeepSeek judge). ## C

What's inside
Steps it walks through
  1. Concepts
  2. Collaboration State
  3. Steering Presets
  4. Priors
  5. Commands
  6. Runtime (voice-first)
  7. Nightly
  8. Memory Integration (memoryintegration.py)
  9. Pre-hook: recalluserpriors(userid, k=10)
  10. Post-hook: learnconversationprior(userid, priortype, value, confidence, context)
  11. Post-hook: learnnightlysummary(userid, globalbestpreset, trainingrows, ...)
  12. Bridge Keywords
  13. Configuration
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the train-convo-steering skill do?

Voice-first runtime steering + nightly deep analysis to learn per-user conversation steering priors.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill train-convo-steering --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going