All authors
Claude Skills by lythos-labs
github.com/lythos-labs34 skills0 installs0 views
- 02 Accepted| Status | Date | Note | |--------|------|------| | proposed | 2026-05-06 | Created | | accepted | 2026-05-06 | Accepted |Votes: 0GitHub stars: 3
- 02 Accepted<!-- machine-parseable table: directory = current status, last row = latest record -->Votes: 0GitHub stars: 3
- 02 Accepted<!-- machine-parseable table: directory = current status, last row = latest record -->Votes: 0GitHub stars: 3
- 04 Completed<!-- machine-parseable table: directory = current status, last row = latest record -->Votes: 0GitHub stars: 3
- SkillTest 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`, nev...Votes: 0GitHub stars: 3
- SkillAnalyzes SKILL.md files against Agent Skills best practices. Reviews body size, description quality, progressive disclosure, frontmatter usage, and context efficiency. Provides actionable optimization advice.Votes: 0GitHub stars: 3
- SkillScaffold 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).Votes: 0GitHub stars: 3
- SkillSkill 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...Votes: 0GitHub stars: 3
- SkillDeclarative 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...Votes: 0GitHub stars: 3
- SkillProject 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 fo...Votes: 0GitHub stars: 3
- SkillA minimal hello-world skill. No scripts, no dependencies. Demonstrates the simplest possible thin-skill: just a SKILL.md.Votes: 0GitHub stars: 3
- SkillRegister 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 conv...Votes: 0GitHub stars: 3
- SkillSession 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).Votes: 0GitHub stars: 3
- SkillWeekly 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).Votes: 0GitHub stars: 3
- SkillSession 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).Votes: 0GitHub stars: 3
- SkillUser-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.Votes: 0GitHub stars: 3
- SkillReconciles a declarative session-reminder registry (cortex/REMINDERS.toml) against the host's session-scoped cron tools. The committed TOML is the SSOT of what should be scheduled; cron jobs are derived, ephemeral state (they die with the session). On entry: diff the registry against CronList, CronCreate the missing (cron + prompt copied verbatim), CronDelete orphans and re-calibrated entries. Multi-session safety via a lease lock with heartbeat; prompts are zero-context executable (task + fi...Votes: 0GitHub stars: 3
- SkillStay 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.Votes: 0GitHub stars: 3
- SkillHuman-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.Votes: 0GitHub stars: 3
- Lythoskill ArenaTest 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`, nev...Votes: 0GitHub stars: 3
- Lythoskill CoachAnalyzes SKILL.md files against Agent Skills best practices. Reviews body size, description quality, progressive disclosure, frontmatter usage, and context efficiency. Provides actionable optimization advice.Votes: 0GitHub stars: 3
- Lythoskill CreatorScaffold 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).Votes: 0GitHub stars: 3
- Lythoskill CuratorSkill 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...Votes: 0GitHub stars: 3
- Lythoskill DeckDeclarative 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...Votes: 0GitHub stars: 3
- Lythoskill DreamingProject 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 fo...Votes: 0GitHub stars: 3
- Lythoskill Hello WorldA minimal hello-world skill. No scripts, no dependencies. Demonstrates the simplest possible thin-skill: just a SKILL.md.Votes: 0GitHub stars: 3
- Lythoskill Project CortexRegister 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 conv...Votes: 0GitHub stars: 3
- Lythoskill Project OnboardingSession 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).Votes: 0GitHub stars: 3
- Lythoskill Project Scribe WeeklyWeekly 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).Votes: 0GitHub stars: 3
- Lythoskill Project ScribeSession 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).Votes: 0GitHub stars: 3
- Lythoskill Red Green ReleaseUser-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.Votes: 0GitHub stars: 3
- Lythoskill RemindersReconciles a declarative session-reminder registry (cortex/REMINDERS.toml) against the host's session-scoped cron tools. The committed TOML is the SSOT of what should be scheduled; cron jobs are derived, ephemeral state (they die with the session). On entry: diff the registry against CronList, CronCreate the missing (cron + prompt copied verbatim), CronDelete orphans and re-calibrated entries. Multi-session safety via a lease lock with heartbeat; prompts are zero-context executable (task + fi...Votes: 0GitHub stars: 3
- Lythoskill SoberStay 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.Votes: 0GitHub stars: 3
- Lythoskill WriterHuman-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.Votes: 0GitHub stars: 3