Claude Skills by Jonhvmp

Phase 1 of Leopold. A structured debate that captures the mission and your decision-making, then writes the brief (MISSION, CHARTER, GUARDRAILS, PLAN) that the autonomous run executes.

Diagnose the Leopold install on every harness present (Claude Code, Codex): checks skills, hooks and their wiring, gstack, the driver toolchain, and whether an update is available.

Control plane for the global prompt enhancer: status, on/off, preview a prompt against the gate, and the learn loop that mines your enhancement ledger into proposed prompt-profile rules. Never edits PROMPT-PROFILE.md itself — you review and apply.

The self-improving charter. Mines past Leopold decisions, session corrections, and git history for recurring judgment calls, skeptic-verifies each candidate, and proposes charter amendments. Never edits CHARTER.md itself — you review and apply.

Synthetic-customer testing, conducted. Builds evidence-grounded persona contracts, walks a persona (or the whole cast) through a declared product flow — perceiving, reacting in character, journaling every turn — and ends with a structured report of bugs, confusion, accessibility problems and friction. Survives context-window rolls; works on Claude Code and Codex CLI.

Phase 2 of Leopold. Enters autonomous mode and conducts the coding agent (Claude Code or Codex CLI) through the plan, deciding from the charter instead of asking, with git locked. The Stop hook keeps it going until the plan is done or a stop condition fires.

Show the state of the current Leopold run: active or not, progress through the plan, decisions logged, and the most recent events.

Take the seat back. Cleanly ends the autonomous run at the next turn boundary and writes a final summary. Nothing is interrupted mid-turn.

Triage a backlog (GitHub issues, bug reports, any queue) as a dynamic workflow: quarantined classifiers over untrusted content, dedupe against what's tracked, severity-ranked report, fix plans for quick wins. Pair with /loop to run it continuously.

Phase 0 of Leopold. One-shot setup that makes a project extract the most from the harness (Claude Code or Codex CLI): generates the project memory file (/init), teaches the agent how to build/run the app (/run-skill-generator), verifies MCP + permissions, then hands off to /leopold-brief. Run this once per project.

Update the whole Leopold toolchain to the latest release: pulls the source, re-runs the installer, and brings the npm driver to the same version.

Launch a local live web dashboard to watch the current project's Leopold run — status, cost meters (context/subagents/forks), event feed, decisions, and a Stop button. Local-only (127.0.0.1), zero dependencies.

Compile a Leopold brief into a dynamic workflow and run it. The plan lives in code instead of one growing context window, every item gets an independent adversarial review, and git stays locked — nothing is committed. The workflow is resumable and shows up in /workflows.

Researches and compiles an evidence-grounded, domain-agnostic persona contract for any target, market, product, service, workflow, policy, content, or decision context. Use when an agent must create, refresh, segment, or validate a synthetic persona before role-play, evaluation, messaging, discovery, or experience testing. Do not use to enact an existing persona contract.

Validates and enacts an existing persona contract for immersive first-person reactions, decisions, evaluations, conversations, or experience tests while preserving knowledge limits, voice, evidence boundaries, and state across turns. Use when an agent must consume, role-play, audit, or run a persona contract. Do not use to research or invent a missing persona.