Stateless one-shot skill execution and controlled-variable comparison. single mode runs any deck against any task with zero local state — no install, no working-set pollution, no deck overwrite. vs mode runs declarative arena.toml for reproducible multi-deck comparison with Pareto frontier analysis. Always restores your parent deck after. First run: arena checks which players are available (kimi/codex/claude) and records your preference. Subagent-friendly: can resume interrupted arena runs from saved state.
EnglishAnalyzes SKILL.md files against Agent Skills best practices. Reviews body size, description quality, progressive disclosure, frontmatter usage, and context efficiency. Provides actionable optimization advice.
EnglishScaffold and build projects for the lythoskill ecosystem only. Creates thin-skill monorepos: heavy logic in npm packages (Starter), agent-facing instructions in lightweight SKILL.md (Skill), build output committed to skills/ (Output).
EnglishSkill discovery engine. Scans your local cold pool (~/.agents/skill-repos), indexes all SKILL.md frontmatter into REGISTRY.json + catalog.db, and lets you query by type, niche, source, or keyword. The CLI is a dumb indexer — YOU are the smart agent who combines curator data with web search, deep research, and project context to make recommendations. Reconciler-style: any filesystem state → scan → converges to clean index. Auto-backs up old index; rollback via restore.
EnglishDeclarative skill deck governance. Syncs .claude/skills/ working set to match skill-deck.toml declarations via symlinks. Undeclared skills are physically removed (deny-by-default), eliminating silent conflicts and context pollution from excess skill descriptions.
EnglishA minimal hello-world skill. No scripts, no dependencies. Demonstrates the simplest possible thin-skill: just a SKILL.md.
EnglishSession context loader. Reads the latest daily handoff to restore project context without redundant file exploration. Three-layer loading: CLAUDE.md (stable) → daily handoff (session state) → git verification (ground truth). Degrades to file exploration when no handoff exists. CQRS read-side pair with project-scribe.
EnglishSession memory writer. Dumps what file exploration cannot recover — pitfalls, true working-tree state, uncommitted decisions, specific next steps — into daily/YYYY-MM-DD.md. Forms CQRS write-side pair with project-onboarding (read-side).
EnglishWeekly synthesis writer. Distills the past 7 days' core thread + quest DAG into a frontmatter-rich short doc. Never replays git log or cortex INDEX (those are direct queries already). Forms the weekly counterpart to project-scribe (daily) and project-onboarding (read-side).
EnglishUser-acceptance-driven release workflow using heredoc patch files. Each iteration produces a timestamped pr- - .sh that self-archives after execution. No tag without explicit user LGTM. Supports rollback via archived backups.
EnglishGTD-style project governance with ADR, Epic, Task, and Wiki. Numeric-prefixed directories (01-backlog, 02-in-progress, etc.) ensure GTD workflow ordering. Timestamp IDs avoid collision without a central database. CLI creates documents, generates indexes, and probes for status inconsistencies.
English
AGENT SKILLS ATLASIncludes Lythoskill Arena, Lythoskill Coach, Lythoskill Creator, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Lythoskill Arena
Stateless one-shot skill execution and controlled-variable comparison. single mode runs any deck against any task with zero local state — no install, no working-set pollution, no deck overwrite. vs mode runs declarative arena.toml for reproducible multi-deck comparison with Pareto frontier analysis. Always restores your parent deck after. First run: arena checks which players are available (kimi/codex/claude) and records your preference. Subagent-friendly: can resume interrupted arena runs from saved state.
Lythoskill Coach
Analyzes SKILL.md files against Agent Skills best practices. Reviews body size, description quality, progressive disclosure, frontmatter usage, and context efficiency. Provides actionable optimization advice.
Lythoskill Creator
Scaffold and build projects for the lythoskill ecosystem only. Creates thin-skill monorepos: heavy logic in npm packages (Starter), agent-facing instructions in lightweight SKILL.md (Skill), build output committed to skills/ (Output).
Lythoskill Curator
Skill discovery engine. Scans your local cold pool (~/.agents/skill-repos), indexes all SKILL.md frontmatter into REGISTRY.json + catalog.db, and lets you query by type, niche, source, or keyword. The CLI is a dumb indexer — YOU are the smart agent who combines curator data with web search, deep research, and project context to make recommendations. Reconciler-style: any filesystem state → scan → converges to clean index. Auto-backs up old index; rollback via restore.
Lythoskill Deck
Declarative skill deck governance. Syncs .claude/skills/ working set to match skill-deck.toml declarations via symlinks. Undeclared skills are physically removed (deny-by-default), eliminating silent conflicts and context pollution from excess skill descriptions.
Lythoskill Hello World
A minimal hello-world skill. No scripts, no dependencies. Demonstrates the simplest possible thin-skill: just a SKILL.md.
Lythoskill Project Onboarding
Session context loader. Reads the latest daily handoff to restore project context without redundant file exploration. Three-layer loading: CLAUDE.md (stable) → daily handoff (session state) → git verification (ground truth). Degrades to file exploration when no handoff exists. CQRS read-side pair with project-scribe.
Lythoskill Project Scribe
Session memory writer. Dumps what file exploration cannot recover — pitfalls, true working-tree state, uncommitted decisions, specific next steps — into daily/YYYY-MM-DD.md. Forms CQRS write-side pair with project-onboarding (read-side).
Lythoskill Project Scribe Weekly
Weekly synthesis writer. Distills the past 7 days' core thread + quest DAG into a frontmatter-rich short doc. Never replays git log or cortex INDEX (those are direct queries already). Forms the weekly counterpart to project-scribe (daily) and project-onboarding (read-side).
Lythoskill Red Green Release
User-acceptance-driven release workflow using heredoc patch files. Each iteration produces a timestamped pr- - .sh that self-archives after execution. No tag without explicit user LGTM. Supports rollback via archived backups.
Project Cortex
GTD-style project governance with ADR, Epic, Task, and Wiki. Numeric-prefixed directories (01-backlog, 02-in-progress, etc.) ensure GTD workflow ordering. Timestamp IDs avoid collision without a central database. CLI creates documents, generates indexes, and probes for status inconsistencies.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Lythoskill Arena skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.