Elicitation Skill
Purpose
Enable expert agents to self-review and self-correct their code before external validation (sniper). Based on BMAD-METHOD's 75 elicitation techniques.
3 Execution Modes
Mode 1: MANUAL (default)
Expert presents 5 relevant techniques → User chooses → Expert applies
Mode 2: AUTO (--auto)
Expert auto-detects code type → Auto-selects techniques → Applies silently
Mode 3: SKIP (--skip)
Skip elicitation → Go directly to sniper validation
Quick Start
After Execute phase, expert runs:
# Manual mode (default)
> Apply elicitation skill
# Auto mode (no prompts)
> Apply elicitation skill --auto
# Skip self-review
> Apply elicitation skill --skip
Workflow Overview
┌─────────────────────────────────────────────────────────┐
│ ELICITATION WORKFLOW │
│ │
│ Step 0: Init → Load context │
│ Step 1: Analyze Code → Detect code type │
│ Step 2: Select → Choose techniques (or auto) │
│ Step 3: Apply Review → Execute techniques │
│ Step 4: Self-Correct → Fix own issues │
│ Step 5: Report → Summary before sniper │
└─────────────────────────────────────────────────────────┘
Auto-Detection Matrix
| Code Type Detected |
Auto-Selected Techniques |
| Authentication/Security |
Security Audit, OWASP Check, Input Validation |
| API Endpoints |
Error Handling, Type Coverage, API Contracts |
| Database/ORM |
N+1 Detection, Migration Safety, Data Integrity |
| UI Components |
Accessibility, Edge Cases, Loading States |
| Business Logic |
SOLID Compliance, Unit Test Coverage, Edge Cases |
| Refactoring |
Breaking Changes, Regression Analysis, Backward Compat |
| Performance Critical |
Profiling, Memory Analysis, Complexity Check |
Technique Categories (12)
Full catalog: references/techniques-catalog.md
- Code Quality (7): Code review, Pattern detection, Complexity analysis...
- Security (7): OWASP audit, Input validation, Auth check...
- Performance (6): Profiling, N+1 detection, Memory analysis...
- Architecture (6): SOLID check, Dependency analysis, Coupling review...
- Testing (6): Edge cases, Boundary testing, Error paths...
- Documentation (6): API review, Comment check, Type coverage...
- UX (6): Accessibility, Error messages, Loading states...
- Data (6): Schema validation, Migration safety, Data integrity...
- Concurrency (6): Race conditions, Deadlock analysis, State sync...
- Integration (7): API contracts, Backward compat, Breaking changes...
- Observability (6): Logging, Metrics, Error tracking...
- Maintainability (6): Readability, Naming, File organization...
Total: 75 techniques
Integration with APEX
A-nalyze → P-lan → E-xecute → [ELICIT] → X-amine
│ │ │
▼ ▼ ▼
Expert Expert sniper
code self-review (final)
Benefits:
- Expert catches own mistakes before sniper
- Faster validation (less sniper corrections)
- Knowledge retention (expert learns from self-review)
Forbidden
- ❌ Skip init step (must load context)
- ❌ Apply techniques without understanding code type
- ❌ Self-correct without documenting changes
- ❌ Report without listing applied techniques
- ❌ Use techniques outside expertise domain
Steps Reference
| Step |
File |
Purpose |
| 0 |
steps/step-00-init.md |
Load context, detect mode |
| 1 |
steps/step-01-analyze-code.md |
Analyze written code |
| 2 |
steps/step-02-select-techniques.md |
Select techniques |
| 3 |
steps/step-03-apply-review.md |
Apply review |
| 4 |
steps/step-04-self-correct.md |
Self-correct |
| 5 |
steps/step-05-report.md |
Generate report |
1---2name: elicitation3description: Auto-review skill for expert agents. After coding, expert applies elicitation techniques to self-correct before sniper validation. Inspired by BMAD-METHOD.4---5
6# Elicitation Skill
7
8## Purpose
9
10Enable expert agents to **self-review and self-correct** their code before external validation (sniper). Based on BMAD-METHOD's 75 elicitation techniques.
11
12---
13
14## 3 Execution Modes
15
16### Mode 1: MANUAL (default)
17```
18Expert presents 5 relevant techniques → User chooses → Expert applies
19```
20
21### Mode 2: AUTO (--auto)
22```
23Expert auto-detects code type → Auto-selects techniques → Applies silently
24```
25
26### Mode 3: SKIP (--skip)
27```
28Skip elicitation → Go directly to sniper validation
29```
30
31---
32
33## Quick Start
34
35**After Execute phase, expert runs:**
36```bash
37# Manual mode (default)
38> Apply elicitation skill
39
40# Auto mode (no prompts)
41> Apply elicitation skill --auto
42
43# Skip self-review
44> Apply elicitation skill --skip
45```
46
47---
48
49## Workflow Overview
50
51```
52┌─────────────────────────────────────────────────────────┐
53│ ELICITATION WORKFLOW │
54│ │
55│ Step 0: Init → Load context │
56│ Step 1: Analyze Code → Detect code type │
57│ Step 2: Select → Choose techniques (or auto) │
58│ Step 3: Apply Review → Execute techniques │
59│ Step 4: Self-Correct → Fix own issues │
60│ Step 5: Report → Summary before sniper │
61└─────────────────────────────────────────────────────────┘
62```
63
64---
65
66## Auto-Detection Matrix
67
68| Code Type Detected | Auto-Selected Techniques |
69|--------------------|--------------------------|
70| Authentication/Security | Security Audit, OWASP Check, Input Validation |
71| API Endpoints | Error Handling, Type Coverage, API Contracts |
72| Database/ORM | N+1 Detection, Migration Safety, Data Integrity |
73| UI Components | Accessibility, Edge Cases, Loading States |
74| Business Logic | SOLID Compliance, Unit Test Coverage, Edge Cases |
75| Refactoring | Breaking Changes, Regression Analysis, Backward Compat |
76| Performance Critical | Profiling, Memory Analysis, Complexity Check |
77
78---
79
80## Technique Categories (12)
81
82Full catalog: `references/techniques-catalog.md`
83
841. **Code Quality** (7): Code review, Pattern detection, Complexity analysis...
852. **Security** (7): OWASP audit, Input validation, Auth check...
863. **Performance** (6): Profiling, N+1 detection, Memory analysis...
874. **Architecture** (6): SOLID check, Dependency analysis, Coupling review...
885. **Testing** (6): Edge cases, Boundary testing, Error paths...
896. **Documentation** (6): API review, Comment check, Type coverage...
907. **UX** (6): Accessibility, Error messages, Loading states...
918. **Data** (6): Schema validation, Migration safety, Data integrity...
929. **Concurrency** (6): Race conditions, Deadlock analysis, State sync...
9310. **Integration** (7): API contracts, Backward compat, Breaking changes...
9411. **Observability** (6): Logging, Metrics, Error tracking...
9512. **Maintainability** (6): Readability, Naming, File organization...
96
97**Total: 75 techniques**
98
99---
100
101## Integration with APEX
102
103```
104A-nalyze → P-lan → E-xecute → [ELICIT] → X-amine
105 │ │ │
106 ▼ ▼ ▼
107 Expert Expert sniper
108 code self-review (final)
109```
110
111**Benefits:**
112- Expert catches own mistakes before sniper
113- Faster validation (less sniper corrections)
114- Knowledge retention (expert learns from self-review)
115
116---
117
118## Forbidden
119
120- ❌ Skip init step (must load context)
121- ❌ Apply techniques without understanding code type
122- ❌ Self-correct without documenting changes
123- ❌ Report without listing applied techniques
124- ❌ Use techniques outside expertise domain
125
126---
127
128## Steps Reference
129
130| Step | File | Purpose |
131|------|------|---------|
132| 0 | `steps/step-00-init.md` | Load context, detect mode |
133| 1 | `steps/step-01-analyze-code.md` | Analyze written code |
134| 2 | `steps/step-02-select-techniques.md` | Select techniques |
135| 3 | `steps/step-03-apply-review.md` | Apply review |
136| 4 | `steps/step-04-self-correct.md` | Self-correct |
137| 5 | `steps/step-05-report.md` | Generate report |
majiayu000