lythos-labs
- 21 skills
- 0 followers
- 15 hours ago last updated
- ▌ Lythoskill Deck 2 · lythos-labs bundleDeclarative skill deck governance. `deck link` reconciles the working set to match skill-deck.toml — deny-by-default removes undeclared skills. DEFAULT patterns: PHASE SWITCH via separate deck files (deck link --deck phase<N>.toml), SEED bootstrap (minimal deck → agent self-expands via deck add + curator discovery). Always restores parent deck. Zero state pollution between phases. INNATE FIRST: after compaction, session reload, or skill refresh — read every innate skill's full SKILL.md before any tool skill. Innate = eagerly loaded, always full context. Tool = lazy, read only on trigger. CRITICAL when writing a deck for others: verify every locator path against the REAL repo structure before publishing.
- ▌ Lythoskill Arena 2 · lythos-labs bundleTest play for skills and deck configurations. DEFAULT: agent reads config, spawns parallel subagents via native Agent tool, judges outputs. Single-deck test AND multi-deck A/B comparison both run agent-orchestrated (no CLI). Cross-player comparison (kimi vs codex) is the ONLY case that needs the CLI runner. Always restores parent deck. No install, no working-set pollution, no deck overwrite. Subagent-friendly: resumes interrupted runs from saved state. CRITICAL: experiments run in `/tmp`, never in committed directories. Subagent inherits parent CWD — prompt must explicitly set workDir.
- ▌ Lythoskill Creator 2 · lythos-labs bundleScaffold 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 2 · lythos-labs bundleSkill curator (买家秀 — "buyer show": hands-on QA notes, as opposed to the author's own 卖家秀 "seller show" claims). Scans your local cold pool, indexes SKILL.md frontmatter into REGISTRY.json + catalog.db. CLI is mechanical glue (scan/query/tag/audit/find) — YOU are the agent who combines curator's local cache with WebSearch, deep research, and arena testing to discover, annotate, fact-check, and recommend. Curator = card searcher (查卡器) + personal notes (备注) + composition taste (组卡审美). Reconciler-style: any filesystem state → scan → converges to clean index. Auto-backup; rollback via `restore`.
- ▌ Lythoskill Project Cortex 2 · lythos-labs bundleRegister tasks BEFORE fixing bugs. Close epics when work is done. Always move state through the CLI — never mv files by hand: CLI moves write Status History, manual moves create probe mismatches. Never leave state drift for the next agent to discover via git log. GTD (Getting Things Done)-style governance across ADR (architecture decision record) / Epic / Task / Wiki. Zero-knowledge (ZK) review = a fresh-agent pass over a task card (WHAT/WHY/HOW) before assignment, so an executor with no conversation context can still run it. `cortex probe` = drift detector: stale backlog, drifted epics, history mismatches vs git reality. **Task-git discipline**: one task = 2-5 commits (core, tests, docs, trailer); every commit carries its full TASK-id (see ID Format — truncated IDs are not addressable).
- ▌ Lythoskill Project Scribe 2 · lythos-labs bundleSession context dump. Self-assess what the conversation contains that has NO other carrier (no task, no ADR, no epic) — pitfalls, working-tree anomalies, why-we-chose-this, specific next steps — and write to daily/YYYY-MM-DD.md. Things WITH structured carriers go to their carriers. Things WITHOUT carriers but needed by the next agent go here. Forms CQRS write-side pair with project-onboarding (read-side).
- ▌ Lythoskill Project Scribe Weekly 2 · lythos-labs bundleWeekly synthesis writer. Distills the past 7 days' core thread + quest DAG (task dependency graph) 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 Deck · lythos-labs bundleDeclarative skill deck governance. `deck link` reconciles the working set to match skill-deck.toml — deny-by-default removes undeclared skills. DEFAULT patterns: PHASE SWITCH via separate deck files (deck link --deck phase<N>.toml), SEED bootstrap (minimal deck → agent self-expands via deck add + curator discovery). Always restores parent deck. Zero state pollution between phases. INNATE FIRST: after compaction, session reload, or skill refresh — read every innate skill's full SKILL.md before any tool skill. Innate = eagerly loaded, always full context. Tool = lazy, read only on trigger. CRITICAL when writing a deck for others: verify every locator path against the REAL repo structure before publishing.
- ▌ Lythoskill Arena · lythos-labs bundleTest play for skills and deck configurations. DEFAULT: agent reads config, spawns parallel subagents via native Agent tool, judges outputs. Single-deck test AND multi-deck A/B comparison both run agent-orchestrated (no CLI). Cross-player comparison (kimi vs codex) is the ONLY case that needs the CLI runner. Always restores parent deck. No install, no working-set pollution, no deck overwrite. Subagent-friendly: resumes interrupted runs from saved state. CRITICAL: experiments run in `/tmp`, never in committed directories. Subagent inherits parent CWD — prompt must explicitly set workDir.
- ▌ Lythoskill Coach · lythos-labs bundleAnalyzes 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 Sober · lythos-labs bundleStay clear-headed. Before you commit to a conclusion, check your basis. Is this evidence or assumption? Do the sources agree? What's the confidence per claim — not in general, but specifically? When you catch yourself listing risks without checking, or hesitating between directions without data, that's the signal to stop and verify.
- ▌ Lythoskill Writer · lythos-labs bundleHuman-first documentation writer and reviewer. Reviews README, wiki, ADR, daily handoff, showcase, and reference docs for information density, structural rhythm, and anti-template patterns. Ensures human readers get clear prose, not AI-flavored filler.
- ▌ Lythoskill Creator · lythos-labs bundleScaffold 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 · lythos-labs bundleSkill curator (买家秀 — "buyer show": hands-on QA notes, as opposed to the author's own 卖家秀 "seller show" claims). Scans your local cold pool, indexes SKILL.md frontmatter into REGISTRY.json + catalog.db. CLI is mechanical glue (scan/query/tag/audit/find) — YOU are the agent who combines curator's local cache with WebSearch, deep research, and arena testing to discover, annotate, fact-check, and recommend. Curator = card searcher (查卡器) + personal notes (备注) + composition taste (组卡审美). Reconciler-style: any filesystem state → scan → converges to clean index. Auto-backup; rollback via `restore`.
- ▌ Lythoskill Dreaming · lythos-labs bundleProject memory consolidation — 夜有所梦 ("night dreams": the day's scattered notes get consolidated into long-term memory while "sleeping"). Daily (scribe) captures raw experience, weekly extracts patterns and anomalies, dreaming consolidates the accumulated memory into the single source of truth (SSOT). External review via a zero-knowledge subagent (a fresh agent with no conversation context — the same pattern Hermes Curator uses for forked-agent review), with cross-model validation via arena for critical docs.
- ▌ Lythoskill Hello World · lythos-labs bundleA minimal hello-world skill. No scripts, no dependencies. Demonstrates the simplest possible thin-skill: just a SKILL.md.
- ▌ Lythoskill Project Cortex · lythos-labs bundleRegister tasks BEFORE fixing bugs. Close epics when work is done. Always move state through the CLI — never mv files by hand: CLI moves write Status History, manual moves create probe mismatches. Never leave state drift for the next agent to discover via git log. GTD (Getting Things Done)-style governance across ADR (architecture decision record) / Epic / Task / Wiki. Zero-knowledge (ZK) review = a fresh-agent pass over a task card (WHAT/WHY/HOW) before assignment, so an executor with no conversation context can still run it. `cortex probe` = drift detector: stale backlog, drifted epics, history mismatches vs git reality. **Task-git discipline**: one task = 2-5 commits (core, tests, docs, trailer); every commit carries its full TASK-id (see ID Format — truncated IDs are not addressable).
- ▌ Lythoskill Project Scribe · lythos-labs bundleSession context dump. Self-assess what the conversation contains that has NO other carrier (no task, no ADR, no epic) — pitfalls, working-tree anomalies, why-we-chose-this, specific next steps — and write to daily/YYYY-MM-DD.md. Things WITH structured carriers go to their carriers. Things WITHOUT carriers but needed by the next agent go here. Forms CQRS write-side pair with project-onboarding (read-side).
- ▌ Lythoskill Red Green Release · lythos-labs bundleUser-acceptance-driven release workflow using heredoc patch files. Each iteration produces a timestamped pr-<timestamp>-<desc>.sh that self-archives after execution. No tag without explicit user LGTM. Supports rollback via archived backups.
- ▌ Lythoskill Project Onboarding · lythos-labs bundleSession 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. Read-side pair with project-scribe (scribe writes the daily, onboarding reads it).
- ▌ Lythoskill Project Scribe Weekly · lythos-labs bundleWeekly synthesis writer. Distills the past 7 days' core thread + quest DAG (task dependency graph) 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).