Skills Router
Routes tasks to appropriate skills using semantic discovery across skill databases.
Skill Databases
| Database |
Location |
Count |
Purpose |
| skill-db |
~/.claude/skill-db/ |
67+ |
Primary skill source |
| skill-library |
~/.claude/skill-library/ |
48+ |
Heavy/categorized skills |
| skills (active) |
~/.claude/skills/ |
Variable |
Currently loaded skills |
Skill Categories
Reasoning Skills (skill-db)
| Skill |
Triggers |
Purpose |
think |
think, analyze, mental-model |
Cognitive enhancement |
reason |
decompose, understand, break-down |
Recursive decomposition |
AoT |
prove, atomic, formal |
Atom of Thoughts |
urf |
universal, multi-scale, complex |
Universal Reasoning |
ontolog |
holarchic, holons, ontology |
Holarchic reasoning |
telos |
physiology, biological, teleological |
Teleological analysis |
qp |
quantitative, calculate, physiological |
Quantitative physiology |
Development Skills (skill-db)
| Skill |
Triggers |
Purpose |
terminal |
tui, cli, terminal-ui |
Terminal UI design |
component |
command, agent, config |
Claude Code components |
mcp-builder |
mcp, server, protocol |
MCP development |
dspy |
dspy, prompts, optimize |
DSPy optimization |
Research Skills (skill-db)
| Skill |
Triggers |
Purpose |
deep-research |
research, thorough, citations |
7-phase research |
notebooklm |
notebook, query, audio |
NotebookLM integration |
skill-discovery |
find skill, discover, browse |
Skill discovery |
Context Skills (skill-db)
| Skill |
Triggers |
Purpose |
context-orchestrator |
context, lifelog, ltm, limitless, pieces |
Three-CLI context extraction |
limitless-cli |
pendant, personal memory, graph sync, extraction pipeline |
Limitless CLI project development |
Heavy Skills (skill-library)
| Skill |
Triggers |
Purpose |
dialectical |
persuade, thesis, synthesis |
Dialectical writing |
critique |
evaluate, lens, adversarial |
Multi-lens critique |
constraints |
deontic, rights, permissions |
Formal constraints |
saq |
saq, exam, model-answer |
SAQ generation |
mega |
complex, n-superhypergraph |
Meta-architecture |
textbook-grounding |
textbook, citations, syntopical |
Textbook grounding |
Routing Logic
# Semantic skill search
ck --sem "{query}" ~/.claude/skill-db/ --top-k 5
# Skill discovery metasystem
# (Invokes skill-discovery skill)
# mcp-skillset (when available)
mcp-skillset search "{query}"
Decision Tree
Skill Task Detected
│
├── Reasoning/Thinking?
│ ├── Cognitive? → think
│ ├── Formal proof? → AoT
│ ├── Decomposition? → reason
│ └── Complex system? → urf | mega
│
├── Development?
│ ├── Terminal UI? → terminal
│ ├── MCP server? → mcp-builder
│ └── Claude component? → component
│
├── Research?
│ ├── Deep dive? → deep-research
│ ├── Skill finding? → skill-discovery
│ └── NotebookLM? → notebooklm
│
├── Context Extraction?
│ ├── Personal/lifelog? → context-orchestrator → limitless
│ ├── Documentation? → context-orchestrator → research
│ ├── Local code/LTM? → context-orchestrator → pieces
│ └── Limitless CLI development? → limitless-cli
│
├── Writing?
│ ├── Persuasive? → dialectical
│ ├── SAQ/Exam? → saq | textbook-grounding
│ └── Critique? → critique
│
├── Data/Graph?
│ ├── Knowledge graph? → hkgb | ontolog
│ ├── Batch processing? → process | obsidian-batch
│ └── Graph reasoning? → mega | graph
│
└── Domain-specific?
├── Physiology? → telos | qp
├── Scientific? → rct-appraisal
└── Code quality? → code-skills/*
Skill Loading Protocol
progressive_loading:
level_0: Read SKILL.md frontmatter only
level_1: Read full SKILL.md
level_2: Load references/*.md
level_3: Load scripts/ and full capability
load_triggers:
- Explicit skill invocation
- Semantic match > 0.7
- Domain keyword match
- User request
Integration
- skill-discovery: Semantic skill search
- skill-rag-router: GraphRAG-based routing
- mcp-skillset: MCP skill discovery
- ck: Semantic code search for skill content
Quick Reference
# Find skill semantically
ck --sem "formal reasoning proof" ~/.claude/skill-db/
# Load skill progressively
1. Check skill-db/{skill}/SKILL.md
2. If not found, check skill-library/{skill}/SKILL.md
3. Load frontmatter, then full skill on demand
# Skill invocation
/skill_name or invoke via Skill tool
1---2name: skills-router3description: Routes tasks to skills in skill-db and skill-library using semantic discovery. Triggers on specialized skill requirements, domain-specific tasks, or explicit skill requests. Uses skill-discovery, mcp-skillset, and skill-rag-router for semantic matching.4---56# Skills Router78Routes tasks to appropriate skills using semantic discovery across skill databases.910## Skill Databases1112| Database | Location | Count | Purpose |13|:---------|:---------|:------|:--------|14| **skill-db** | ~/.claude/skill-db/ | 67+ | Primary skill source |15| **skill-library** | ~/.claude/skill-library/ | 48+ | Heavy/categorized skills |16| **skills (active)** | ~/.claude/skills/ | Variable | Currently loaded skills |1718## Skill Categories1920### Reasoning Skills (skill-db)21| Skill | Triggers | Purpose |22|:------|:---------|:--------|23| `think` | think, analyze, mental-model | Cognitive enhancement |24| `reason` | decompose, understand, break-down | Recursive decomposition |25| `AoT` | prove, atomic, formal | Atom of Thoughts |26| `urf` | universal, multi-scale, complex | Universal Reasoning |27| `ontolog` | holarchic, holons, ontology | Holarchic reasoning |28| `telos` | physiology, biological, teleological | Teleological analysis |29| `qp` | quantitative, calculate, physiological | Quantitative physiology |3031### Development Skills (skill-db)32| Skill | Triggers | Purpose |33|:------|:---------|:--------|34| `terminal` | tui, cli, terminal-ui | Terminal UI design |35| `component` | command, agent, config | Claude Code components |36| `mcp-builder` | mcp, server, protocol | MCP development |37| `dspy` | dspy, prompts, optimize | DSPy optimization |3839### Research Skills (skill-db)40| Skill | Triggers | Purpose |41|:------|:---------|:--------|42| `deep-research` | research, thorough, citations | 7-phase research |43| `notebooklm` | notebook, query, audio | NotebookLM integration |44| `skill-discovery` | find skill, discover, browse | Skill discovery |4546### Context Skills (skill-db)47| Skill | Triggers | Purpose |48|:------|:---------|:--------|49| `context-orchestrator` | context, lifelog, ltm, limitless, pieces | Three-CLI context extraction |50| `limitless-cli` | pendant, personal memory, graph sync, extraction pipeline | Limitless CLI project development |5152### Heavy Skills (skill-library)53| Skill | Triggers | Purpose |54|:------|:---------|:--------|55| `dialectical` | persuade, thesis, synthesis | Dialectical writing |56| `critique` | evaluate, lens, adversarial | Multi-lens critique |57| `constraints` | deontic, rights, permissions | Formal constraints |58| `saq` | saq, exam, model-answer | SAQ generation |59| `mega` | complex, n-superhypergraph | Meta-architecture |60| `textbook-grounding` | textbook, citations, syntopical | Textbook grounding |6162## Routing Logic6364```bash65# Semantic skill search66ck --sem "{query}" ~/.claude/skill-db/ --top-k 56768# Skill discovery metasystem69# (Invokes skill-discovery skill)7071# mcp-skillset (when available)72mcp-skillset search "{query}"73```7475## Decision Tree7677```78Skill Task Detected79 │80 ├── Reasoning/Thinking?81 │ ├── Cognitive? → think82 │ ├── Formal proof? → AoT83 │ ├── Decomposition? → reason84 │ └── Complex system? → urf | mega85 │86 ├── Development?87 │ ├── Terminal UI? → terminal88 │ ├── MCP server? → mcp-builder89 │ └── Claude component? → component90 │91 ├── Research?92 │ ├── Deep dive? → deep-research93 │ ├── Skill finding? → skill-discovery94 │ └── NotebookLM? → notebooklm95 │96 ├── Context Extraction?97 │ ├── Personal/lifelog? → context-orchestrator → limitless98 │ ├── Documentation? → context-orchestrator → research99 │ ├── Local code/LTM? → context-orchestrator → pieces100 │ └── Limitless CLI development? → limitless-cli101 │102 ├── Writing?103 │ ├── Persuasive? → dialectical104 │ ├── SAQ/Exam? → saq | textbook-grounding105 │ └── Critique? → critique106 │107 ├── Data/Graph?108 │ ├── Knowledge graph? → hkgb | ontolog109 │ ├── Batch processing? → process | obsidian-batch110 │ └── Graph reasoning? → mega | graph111 │112 └── Domain-specific?113 ├── Physiology? → telos | qp114 ├── Scientific? → rct-appraisal115 └── Code quality? → code-skills/*116```117118## Skill Loading Protocol119120```yaml121progressive_loading:122 level_0: Read SKILL.md frontmatter only123 level_1: Read full SKILL.md124 level_2: Load references/*.md125 level_3: Load scripts/ and full capability126127load_triggers:128 - Explicit skill invocation129 - Semantic match > 0.7130 - Domain keyword match131 - User request132```133134## Integration135136- **skill-discovery**: Semantic skill search137- **skill-rag-router**: GraphRAG-based routing138- **mcp-skillset**: MCP skill discovery139- **ck**: Semantic code search for skill content140141## Quick Reference142143```yaml144# Find skill semantically145ck --sem "formal reasoning proof" ~/.claude/skill-db/146147# Load skill progressively1481. Check skill-db/{skill}/SKILL.md1492. If not found, check skill-library/{skill}/SKILL.md1503. Load frontmatter, then full skill on demand151152# Skill invocation153/skill_name or invoke via Skill tool154```