fix: rename Maestro → Zenith and fix project-kickoff skill

CLAUDE.md

@@ -1,4 +1,4 @@
-# Maestro
+# Zenith
 
 A curated collection of Claude Code skills for running AI agents at the executive level. Skills are installed via [skills.sh](https://skills.sh) and tracked in GitHub Issues.
 
@@ -42,6 +42,6 @@ Checks: SKILL.md present, required frontmatter fields (`name`, `description`), m
 ## Key Files
 
 - `skills/` — publishable skills (distributed via skills.sh)
-- `.claude/skills/` — local skills used while developing maestro (dogfooding)
+- `.claude/skills/` — local skills used while developing zenith (dogfooding)
 - `skills-lock.json` — tracks installed skill versions
 - `.github/workflows/validate.yml` — CI skill validator

CONTRIBUTING.md

@@ -1,8 +1,8 @@
-# Contributing to Maestro
+# Contributing to Zenith
 
-## What makes a good Maestro skill
+## What makes a good Zenith skill
 
-Maestro skills handle **complete workflows**, not single commands. Before writing a skill, ask: does this take a user from a starting state to a finished state with no manual steps in between?
+Zenith skills handle **complete workflows**, not single commands. Before writing a skill, ask: does this take a user from a starting state to a finished state with no manual steps in between?
 
 Good: "Set up a new project from zero to first commit"
 Not good: "Run git init"

README.md

@@ -1,19 +1,19 @@
-# Maestro
+# Zenith
 
 > Conduct AI agents like a CEO — orchestrate, delegate, ship.
 
-Managing AI agents today feels like conducting an orchestra without a score. Maestro gives you the score — a growing library of battle-tested Claude Code skills that turn your agent into an executive command center.
+Managing AI agents today feels like conducting an orchestra without a score. Zenith gives you the score — a growing library of battle-tested Claude Code skills that turn your agent into an executive command center.
 
 Install a skill. Delegate the work. Stay in command.
 
 ## Install
 
 ```bash
-# Install all Maestro skills
+# Install all Zenith skills
 npx skills add openqa-labs/zenith
 
 # Or install a single skill
-npx skills add openqa-labs/zenith/project-kickoff
+npx skills add openqa-labs/zenith --skill project-kickoff
 ```
 
 ## Skills
@@ -34,7 +34,7 @@ Once installed, trigger a skill directly in Claude Code:
 
 Claude conducts a structured intake, researches the competitive landscape, sets up the repo, configures CI, writes the README, and creates your first task — end to end.
 
-## Why Maestro
+## Why Zenith
 
 - **End-to-end workflows** — each skill owns a complete job, not just a step
 - **CEO-level thinking** — skills ask the right strategic questions up front

skills/project-kickoff/README.md

@@ -5,7 +5,7 @@ Start any project from zero — discovery interview, naming, repo setup, CI, REA
 ## Install
 
 ```bash
-npx skills add openqa-labs/zenith/project-kickoff
+npx skills add openqa-labs/zenith --skill project-kickoff
 ```
 
 ## What it does

skills/project-kickoff/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: project-kickoff
 description: >
-  Your CEO/PM assistant for starting, migrating, reviving, or bootstrapping any project — coding or non-coding.
-  Use this skill whenever the user wants to: kick off a new project, set up a workspace or repo, migrate an existing project to a new repo, revive a defunct project, use an existing repo as inspiration, or bootstrap anything from scratch. This includes coding projects (Python, Node, Go, etc.), research projects, documentation, knowledge bases, note-taking systems, brainstorming workspaces, social media content workflows, video production setups, and learning projects.
-  Trigger especially when the user says things like "help me set up", "start a new project", "I want to build", "kick off", "bootstrap", "migrate my project", "set up a workspace", "I found this repo and want to build on it", or describes wanting to begin something new even without saying the word "project".
-  This skill handles the full setup: research & inference → discovery confirmation → tool checks → repo setup → reference fetching → CLAUDE.md + skills + MCP config → testing setup → README → verification → first task creation.
+  Use when the user wants to start, migrate, revive, or bootstrap any project — coding or non-coding.
+  Triggers on: "help me set up", "start a new project", "I want to build", "kick off", "bootstrap", "migrate my project", "set up a workspace", "I found this repo and want to build on it", or any intent to begin something new even without the word "project".
+  Applies to coding projects (Python, Node, Go, etc.) and non-coding projects (research, docs, knowledge bases, content workflows, learning projects).
 ---
 
 # Project Kickoff
@@ -91,7 +90,7 @@ Examples: `?q=python`, `?q=dbt`, `?q=react`, `?q=data`, `?q=testing`
 
 Queue the relevant matches for Phase 1 item 13.
 
-### Step 3 — Build draft answers
+### Step 4 — Build draft answers
 
 For every question in Phase 1, assign a confidence tier:
 

skills/project-kickoff/evals/evals.json

@@ -28,7 +28,7 @@
         "Asks grouped discovery questions and correctly identifies this as a non-coding knowledge-base project",
         "Sets up a public GitHub repo",
         "Fetches EleutherAI/lm-evaluation-harness via opensrc or git clone into opensrc/ and adds opensrc/ to .gitignore",
-        "Uses WebFetch to retrieve paper/URL content and saves to references/ directory",
+        "Uses WebFetch to retrieve paper/URL content and saves to opensrc/<name>.md (not a references/ directory)",
         "Creates CLAUDE.md adapted for non-coding project (no venv/install rules, instead workflow conventions)",
         "Creates CHECKLIST.md as the verification/review mechanism instead of test files",
         "Creates .gitignore that includes opensrc/",