ilandahan/AID / skills/aid-discovery
aid-discovery
VerifiedAID Phase 0 - Research & discovery. Use for validating problem spaces, identifying stakeholders, defining success metrics, deciding whether to proceed.
aid-discovery - AID Phase 0
Purpose: Validate problem space before committing to solution. Entry: Initial idea/request exists, stakeholders available. Exit: Problem validated, stakeholders identified, success metrics defined, go/no-go decision.
Deliverables
- Problem Statement (SCQ format) - Validated, no solution assumptions
- Stakeholder Map - All affected parties identified
- Success Metrics - Quantified, measurable outcomes
Discovery Questions
Ask these:
- Problem: What problem are we solving? Who has this problem? How painful? (Quantify) What if we don't solve it?
- Stakeholders: Who are end users? Who owns data/process? Who makes decisions? Who else touches this?
- Success: What does success look like? How will we measure? What's minimum viable outcome?
- Technical feasibility: Is this feasible? Major technical risks? Required skills? Infrastructure needs?
Problem Statement Template (SCQ)
## Problem Statement
### Situation
[Current state]
### Complication
[What's wrong]
### Question
[What solving this answers]
### Impact
- [Quantified impact]
### Success Metrics
| Metric | Current | Target |
|--------|---------|--------|
| [Metric] | [Now] | [Goal] |
Stakeholder Map Template
### Decision Makers
- [Name/Role]: [Responsibility]
### Data/System Owners
- [Name/Role]: [What they own]
### End Users
- [Type]: [How affected]
### Integrations
- [System]: [Relationship]
Common Pitfalls
| Pitfall | Fix |
|---|---|
| Solution-first | Start with "what problem?" |
| Missing stakeholders | Ask "who else touches this?" |
| Vague problems | If can't measure, not defined |
| Assumption blindness | Make assumptions explicit |
Phase Gate Checklist
- Problem statement validated
- All stakeholders identified
- Success metrics specific
- Technical feasibility assessed
- Proceed/not-proceed decision clear
- Scope boundaries established
Handoff to PRD
- Validated problem statement
- Stakeholder map
- Success metrics
- Constraints identified
- Scope boundaries
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |