4-Phase Orchestration: How 5 Universal Agent Skills Achieve YAML-Driven Rules + Composable Components + Graceful Degradation
When you're hard-coding your 3rd scoring if-else, maybe it's time to ask: can I move the rules into YAML and let the business change config instead of code?
The Problem: Why Do Agent Skills Keep Reinventing the Wheel?
Every Agent developer faces the same dilemma — every business scenario rewrites a similar pipeline:
- Scoring: Extract features → Match rules → Calculate score → Generate report
- Complaints: Extract ticket → Cross-validate → Pinpoint root cause → Archive
- Querying: Understand intent → Build SQL → Execute query → Render chart
The skeleton is identical. What changes is only the "content" at each step. Yet every team builds pipelines from scratch.
teleagent-skills offers an answer: freeze the skeleton into 5 universal Skills with 4-Phase orchestration, and let business changes live in YAML config only.
Architecture Overview: 4-Phase Pipeline + 5 Universal Skills
2.1 4-Phase Orchestration Diagram
┌─────────────────────────────────────────────────────────────┐
│ Upper Business Skill │
│ (Scoring Engine / Evidence Chain / Data Aggregator / ...) │
└──────────┬──────────┬──────────┬──────────┬────────────────┘
│ │ │ │
▼ ▼ ▼ ▼
┌──────────┐┌──────────┐┌──────────┐┌──────────┐
│ Phase 1 ││ Phase 2 ││ Phase 3 ││ Phase 4 │
│ Extract ││ Analyze ││ Generate ││ Archive │
│ ││ ││ ││ │
│Info- ││Data- ││Report- ││Archive- │
│Extractor ││Analyst ││Generator ││Manager │
└────┬─────┘└────┬─────┘└────┬─────┘└────┬─────┘
│ │ │ │
▼ ▼ ▼ ▼
┌─────────────────────────────────────────────────┐
│ JSON Contract (Structured Data Contract) │
│ phase1_output.json → phase2_input.json → ... │
└─────────────────────────────────────────────────┘
Core idea: each Phase is an independent component, and Phases pass data only through JSON contracts.
- Any Phase can be replaced (want a more powerful Analyzer? Swap it out)
- Any Phase can be skipped (degradation mode)
- Any Phase can be reused (5 Skills share the same Extract component)
2.2 JSON Contract Example
{
"phase": "extract",
"skill": "scoring-engine",
"output": {
"entities": [
{
"name": "客户A",
"type": "enterprise_customer",
"attributes": {
"annual_revenue": 50000000,
"employee_count": 320,
"industry": "制造"
}
}
],
"metadata": {
"extraction_time": "2026-07-01T10:30:00Z",
"source": "CRM_API",
"confidence": 0.92
}
},
"next_phase": "analyze"
}
Three Design Principles, Deep Dive
Principle 1: YAML-Driven, Parameterized Rules
The traditional approach hard-codes scoring rules:
# Hard-coded — every business change means a code change
if customer.revenue > 10000000:
score += 30
elif customer.revenue > 5000000:
score += 20
teleagent-skills does it differently — all rules are externalized to YAML:
# scoring_rules.yaml
scoring_engine:
name: "政企客户商机评分"
version: "2.1"
dimensions:
- id: revenue
name: "营收规模"
weight: 0.30
rules:
- condition: "attributes.annual_revenue >= 100000000"
score: 30
label: "超大型"
- condition: "attributes.annual_revenue >= 50000000"
score: 20
label: "大型"
- condition: "attributes.annual_revenue >= 10000000"
score: 10
label: "中型"
- id: industry
name: "行业属性"
weight: 0.25
rules:
- condition: "attributes.industry in ['金融','医疗']"
score: 25
label: "高价值行业"
- id: growth
name: "增长潜力"
weight: 0.20
- id: connectivity
name: "接入成熟度"
weight: 0.15
- id: decision_chain
name: "决策链清晰度"
weight: 0.10
thresholds:
high: 70
medium: 40
low: 0
Business changed? Edit YAML. Need a new dimension? Add YAML. Zero code changes.
Principle 2: Composable Components — 4-Phase Orchestration + JSON Contracts
All 5 Skills share the same 4-Phase skeleton, but each Skill's Phase behavior differs:
| Skill | Phase 1 Extract | Phase 2 Analyze | Phase 3 Generate | Phase 4 Archive |
|---|---|---|---|---|
| Scoring Engine | Extract scoring object attributes | Load YAML rules & match scores | Generate scoring report + recommendations | Archive scoring records |
| Evidence Chain | Extract evidence from multiple sources | Cross-validate + conflict detection | Generate evidence chain report | Archive validation records |
| Data Aggregator | Validate & clean raw data | Aggregation + YoY/MoM calculation | Output statistical report | Archive aggregated results |
| Visualization Renderer | Analyze data characteristics | Generate ECharts config | Render HTML/Dashboard | Cache chart assets |
| NL2Query | Extract query intent + entities | Build SQL + confidence assessment | Format query results | Record query logs |
The power of composability: upper-level Skills can chain lower-level Skills on demand. For example, the data query gateway pipeline:
NL2Query(Phase1-2) → Data Aggregator(Phase1-2) → Visualization Renderer(Phase1-3)
One natural language query automatically flows through "understand → query → aggregate → visualize" end to end.
Principle 3: Graceful Degradation — When Sub-Components Fail
The 4-Phase architecture has built-in 3-tier degradation:
┌─────────────┐ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐
│ Phase 1 │────▶│ Phase 2 │────▶│ Phase 3 │────▶│ Phase 4 │
│ Extract │ │ Analyze │ │ Generate │ │ Archive │
└──────┬──────┘ └──────┬──────┘ └──────┬──────┘ └──────┬──────┘
│ │ │ │
▼ ▼ ▼ ▼
┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐
│ Return │ │ Skip │ │ Simplify │ │ Local │
│ raw │ │ analysis │ │ template │ │ cache + │
│ input + │ │ mark low │ │ raw data │ │ deferred │
│ conf=0 │ │ confidence│ │ passthrough│ │ retry │
└──────────┘ └──────────┘ └──────────┘ └──────────┘
The core principle of degradation: I'd rather give the user a low-confidence result than crash with an error.
The 5 Skills, One by One
4.1 Scoring Engine
What it is: A multi-dimensional weighted scoring component driven by YAML rule configs.
Typical scenarios: enterprise opportunity scoring, vendor evaluation, customer churn prediction, partner tiering.
Input → Rule matching → Scoring output flow:
{
"customer": "客户A",
"total_score": 78,
"grade": "A级-重点跟进",
"dimension_breakdown": {
"revenue": { "score": 20, "max": 30, "label": "大型" },
"industry": { "score": 15, "max": 25, "label": "中价值行业" },
"growth": { "score": 20, "max": 20 },
"connectivity": { "score": 15, "max": 15 },
"decision_chain": { "score": 8, "max": 10 }
},
"recommendation": "建议安排专属客户经理，优先推荐5G专网+云网融合方案"
}
4.2 Evidence Chain
What it is: A multi-source evidence cross-validation component that detects conflicts, evaluates confidence, and pinpoints root causes.
Data Source 1: Customer complaints ──┐
│ ┌──────────────────┐
Data Source 2: System alert logs ──┼────▶│ Evidence Chain │
│ │ Phase2: Analyze │
Data Source 3: SLA monitoring data ──┘ └────────┬─────────┘
│
┌───────────────────────┐│
│ Cross-validation: │
│ • Complaint: "2hr outage"
│ • Alert: "optical attenuation"│
│ • SLA: "99.1% availability" │
│ Conflict detected: │
│ Complaint vs SLA surface contradiction│
│ Root cause="optical attenuation": 0.87│
└───────────────────────┘
4.3 Data Aggregator
What it is: A raw data re-processing component supporting validation/cleaning, aggregation, YoY/MoM, and TOP rankings.
Raw query results Aggregator output
┌──────────────┐ ┌──────────────────────────────┐
│ 300 rows of │───────▶ │ Monthly summary + YoY/MoM │
│ detail data │ │ TOP10 ranking │
│ (region x │ │ Anomaly flags (>2σ) │
│ month) │ │ Trend direction │
└──────────────┘ └──────────────────────────────┘
4.4 Visualization Renderer
What it is: An automated rendering component that turns structured data into ECharts charts and Dashboards.
Chart type selection is automatic: time-series → line chart, categorical → bar/pie, multi-dimensional → radar.
4.5 NL2Query
What it is: A smart natural-language-to-structured-query conversion component.
User input: "华东区上月5G专网新增客户数"
Phase1 Extract: intent="query", entities=[region="华东", time="上月", metric="5G专网"]
Phase2 Analyze: Generate SQL + confidence 0.88
Phase3 Generate: Format results
Phase4 Archive: Record query log
Confidence scoring: When confidence drops below a threshold, the output gets a "low confidence" warning and shows the SQL for human review.
Industry Use-Case Matrix
| Industry | Scoring Engine | Evidence Chain | Data Aggregator | Viz Renderer | NL2Query |
|---|---|---|---|---|---|
| Finance | Customer credit rating | Anti-money-laundering multi-source verification | Transaction volume YoY/MoM | Risk control dashboard | "Check a customer's last 3 months of transactions" |
| Manufacturing | Supplier evaluation | QA vs. production line verification | Line OEE statistics | Capacity dashboard | "Check line A's yield this month" |
| Retail | Member value scoring | Data conflict detection | SKU sales aggregation | Sales heatmap | "Top sellers in East China" |
| Healthcare | Patient risk stratification | Diagnosis vs. lab verification | Department admission stats | Bed occupancy dashboard | "Available beds in cardiology" |
Key insight: All 5 Skills adapt to different industries purely through YAML rule configs. The scoring engine code logic is identical — only the YAML files differ.
How This Fundamentally Differs from Existing Frameworks
| Dimension | LangChain/LlamaIndex | AutoGen/CrewAI | teleagent-skills |
|---|---|---|---|
| Orchestration | Code-level Chain | Multi-Agent dialogue | 4-Phase declarative orchestration |
| Rule management | Hard-coded in code | Described in prompts | YAML parameterized config |
| Degradation strategy | try-catch | Retry dialogue | Declarative degradation config |
| Business adaptation | Change code | Change prompts | Change YAML |
Quick Start
git clone https://github.com/yuzhaopeng-up/teleagent-skills.git
cd teleagent-skills
# Scoring engine example
cp skills/scoring-engine/config/scoring_rules.yaml my_rules.yaml
# Edit my_rules.yaml to customize your scoring dimensions
# Copy the Skill directory into your Agent platform's skills directory
License: Apache 2.0
Agent Skills Open-Source Ecosystem
| Repo | What It Does | GitHub |
|---|---|---|
| financial-ai-skills | Financial AI skill library: 104 scenarios, pure Python | https://github.com/yuzhaopeng-up/financial-ai-skills |
| teleagent-skills | 5 universal business Skills: 4-Phase orchestration + YAML-driven rules | https://github.com/yuzhaopeng-up/teleagent-skills |
| agent-cluster-comm | Multi-Agent cluster 5-layer communication architecture | https://github.com/yuzhaopeng-up/agent-cluster-comm |
| skill-framework | Skill governance framework: L0-L4 classification + YAML templates + Python tools | https://github.com/yuzhaopeng-up/skill-framework |
| fintech-h5-demos | 12 zero-dependency financial H5 dashboard demos | https://github.com/yuzhaopeng-up/fintech-h5-demos |
Stop building pipelines from scratch. The 4-Phase skeleton is ready — you just need to write YAML.
Star teleagent-skills and let's standardize Agent Skills together.
Top comments (0)