ilandahan/AID / skills/learning-mode
learning-mode
VerifiedDecision transparency, feedback collection, and debate invitations for AID methodology. Active in ALL phases for ALL roles.
| File | Kind | Size |
|---|---|---|
| QUICK-REFERENCE.extended.md | markdown | 5.0 KB |
| QUICK-REFERENCE.md | markdown | 2.2 KB |
| SIMULATION.extended.md | markdown | 19.2 KB |
| SIMULATION.md | markdown | 11.0 KB |
| SKILL.extended.md | markdown | 10.9 KB |
| SKILL.md | skill md | 4.5 KB |
| USER-FLOW.extended.md | markdown | 33.9 KB |
| USER-FLOW.md | markdown | 2.1 KB |
USER-FLOW.md
View on GitHub# Learning Mode - User Flow
## Master Flow
```
User Request -> Analyze Decision Type
-> Simple: Execute directly
-> Significant: Check alternatives
-> Single Clear: Decision Transparency
-> Multiple Viable: Debate Invitation
-> User vs Best Practice: Respectful Counter-point
-> Execute Work
-> Work Complete?
-> Minor: Continue
-> Major Milestone: Request Feedback
-> Positive: Continue
-> Correction: Capture Learning
```
## Flow 1: Decision Transparency
```
Significant Decision -> Transparent?
-> Yes (Arch/Tech/Trade-offs/Scope): Create Transparency Block
-> No (Syntax/Standard/No alternatives): Execute without ceremony
-> Assess Confidence
-> High: Execute
-> Medium: Execute + note concern
-> Low: Invite debate
-> Uncertain: Ask clarifying question
```
## Flow 2: Feedback Collection
```
Trigger (Phase Gate / Major Deliverable / Session End)
-> Create Feedback Request Block
-> User Response
-> Rating 4-5: Acknowledge, continue
-> Rating 3: Ask for improvement suggestions
-> Rating 1-2: Request specific corrections
-> Capture Learning if needed
-> Continue Work
```
## Flow 3: Debate Invitation
```
Multiple Options -> Evaluate Viability
-> One clear winner (>70%): Use Decision Transparency
-> Multiple viable (<70%): Create Debate Invitation
-> User Response
-> Picks Option A/B: Execute + Document why
-> Wants more info: Provide deeper analysis
-> Capture learning about preference
```
## Flow 4: Phase Gate Learning
```
Phase Work Complete
-> Prepare Phase Summary
-> Create Feedback Request (deliverables, seeking feedback, questions, rating)
-> User Response
-> Approved (>=3): Capture notes, advance phase
-> Needs Revision (<3): List items, return to phase work
```
## Flow 5: Learning Capture
```
User Provides Correction/Preference
-> Identify Category (Process/Technical/Style/Domain)
-> Create Learning Capture Block
-> Store in Session Memory
-> Apply to Future Work
```
## Integration Points
- Phase Enforcement: Request feedback at gate
- Code Review: Debate on significant findings
- System Architect: Transparency on all architecture decisions
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |