lythoskill-curator

Solid

Skill 策展者/买家秀 (curator's perspective). 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 = 查卡器 + 备注 + 组卡审美. Reconciler-style: any filesystem state → scan → converges to clean index. Auto-backup; rollback via `restore`.

Testing & QA 3 stars 0 forks Updated 3 weeks ago MIT

Install

View on GitHub

Quality Score: 80/100

Stars 20%
20
Recency 20%
90
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Skill Curator > 策展者/买家秀 = 查卡器 + 备注 + 组卡审美 > CLI is mechanical glue (scan, query, tag, audit). Agent does the thinking. ## Mental Model: Curator = 策展者 (Curator's Perspective) Curator is NOT a discovery engine. It's the **curator's personal knowledge base** — a card searcher + personal notes system for the skill ecosystem. **Two complementary modes**: | Mode | Metaphor | What it does | |------|----------|-------------| | 记者 (Journalist) | Investigation + narrative + expression | Fact-check claims, cross-reference sources, detect bias, assign confidence | | 架构师 (Architect) | Composition aesthetics | Understand synergies, deduce combos, judge structural fit, design archetypes | **组卡审美 (composition taste) has three inputs**: 1. **Arena 实战数值** — quantitative: scores, pass/fail, performance data 2. **审美评析** — qualitative: your own judgment of a skill's design, clarity, fit 3. **Combo 推演** — systemic: how skills compose, what synergies emerge, what archetype they form A curator doesn't just verify facts (记者). A curator understands **how skills combine to be beautiful** (架构师). This is what separates a card database from a deck builder. **Curator 依赖 deck + arena 的能力**:curator 不评估孤立技能——它评估"这张牌在这个卡组里完成这个任务"的表现。Arena 测试的是 deck 级别能力,curator 记录的是 deck-task 级别的 QA。一张牌在一副卡组里表现出色,在另一副里可能无用。架构师理解这种上下文依赖性。 ## Discovery SOP (Agent-Driven) The explore slot is dominated by **agent + search** (gh CLI first, WebSearch as fallback). Curator's job is NOT to be the discovery engine — it's the...

Details

Author
lythos-labs
Repository
lythos-labs/lythoskill
Created
3 months ago
Last Updated
3 weeks ago
Language
TypeScript
License
MIT

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

skill-curator

Curate local Agent Skills libraries across coding harnesses. Use only when the user explicitly asks to inventory, audit, validate, prune, archive, restore, pin, deduplicate, merge, or maintain SKILL.md packages for Claude Code, Codex, Cursor, Gemini CLI, OpenCode, or another coding agent.

0 Updated 2 weeks ago
cskwork
AI & Automation Listed

curating-skill-portfolios

Use when deciding whether a capability deserves its own skill, whether something should be a skill or a reference, where a new skill belongs, or whether two skills overlap — 当你在判断要不要新建一个 skill、这块该不该独立成 skill 还是塞进某个 reference、一组 skill 的边界与重叠时。Triggers: 立项一个新 skill、重构 skill 版图、"这是 skill 还是 reference"、portfolio 体检、两个 skill 触发条件打架。Do NOT use when you only need to write or pressure-test a single skill body (那是 cc-master-skillsmith); Do NOT use when you need to declare J / run trigger or behavior eval / measure a skill (那是 grounding-skill-evals); Do NOT use when 你要跑 skill knowledge graph 的 health / typed change / witness(走 design_docs/skill-knowledge-graph + skill-knowledge CLI)。

9 Updated 1 weeks ago
nemori-ai
AI & Automation Listed

skills-curator

Use when the user mentions a skill or plugin by name, asks "should I install X?", asks "what skills fit this project?", asks to audit installed skills, asks whether a skill is safe to use, or wants to customize an external skill for their stack. Evaluates skills against the user's actual project (pros / cons / conflicts / ADOPT-PARTIAL-SKIP verdict), recommends what fits, scans for security red flags before adoption, persists every decision to a registry the user keeps in Project Knowledge, and forks stack-mismatched skills into project-tailored versions. Decide once, never re-decide.

2 Updated 2 weeks ago
captkernel