sherpa-skill 2.0.6 → 2.0.7

package/skills/sherpa/templates/judge-session.md

@@ -0,0 +1,125 @@
+# Judge Simulation Session
+
+## Session ID
+
+## Judge Persona
+
+## Session Date
+
+## Session Duration
+
+## Session Scope
+
+## Judge Opening
+
+## First Impression
+
+- What does the product appear to do?
+- Is the target user obvious?
+- Is the problem obvious?
+- Is the value proposition obvious?
+- Can a judge understand the core action without explanation?
+
+## Demo Walkthrough
+
+| Step | Action | Visible Output | Confusion Points | Failure Points | Recovery |
+|------|--------|----------------|------------------|----------------|----------|
+| | | | | | |
+
+## Criterion Evaluation
+
+| Criterion | Weight | Score | Confidence | Reasoning | Evidence |
+|-----------|--------|-------|------------|-----------|----------|
+| | | | | | |
+
+## Simulated Questions Asked
+
+| Question ID | Question | Answer Quality | Confidence |
+|-------------|----------|--------------|------------|
+| | | | |
+
+## Likely Objections
+
+| Objection | Basis | Evidence | Severity |
+|-----------|-------|----------|------------|
+| | | | |
+
+## Technical Credibility
+
+- Real implementation:
+- Meaningful engineering choices:
+- Appropriate technology:
+- Reasonable architecture:
+- Error handling:
+- Testing:
+- Security awareness:
+- Maintainability:
+- Limitations:
+
+## Product Credibility
+
+- Problem clarity:
+- Target user clarity:
+- User value:
+- Practical impact:
+- Usability:
+- Limitations:
+
+## Demo Credibility
+
+- Reliability:
+- Clarity:
+- Speed:
+- Visible value:
+- Error handling:
+- Recovery:
+- Consistency:
+
+## Claim Consistency
+
+| Claim | Documented In | Repository Shows | Demo Shows | Status |
+|-------|---------------|------------------|------------|--------|
+| | | | | |
+
+CONSISTENT | INCONSISTENT | UNKNOWN
+
+## Differentiation Perception
+
+- Actual differentiation:
+- Communicated differentiation:
+- Evidence-backed differentiation:
+- Judge-visible differentiation:
+
+## Judge Trust
+
+Trust level: HIGH | MEDIUM | LOW | UNKNOWN
+
+## Critical Preparation Risks
+
+| Risk | Severity | Confidence | Mitigation |
+|------|----------|------------|------------|
+| | | | |
+
+## Unknowns
+
+| Unknown | Why unknown | Impact | Source |
+|---------|-------------|--------|--------|
+| | | | |
+
+## Limitations
+
+## Judge Readiness
+
+NOT_READY | REVIEW_IN_PROGRESS | BLOCKED | CONDITIONAL | READY
+
+## Recommended Next Action
+
+**PRIMARY NEXT ACTION:**
+
+**WHY:**
+
+**DONE WHEN:**
+
+**Time remaining:**
+
+**Blocked by:**

package/skills/sherpa/templates/judge-simulation.md

@@ -0,0 +1,264 @@
+# Judge Simulation
+
+## Project
+
+- Repository root:
+- Revision/commit:
+- Selected idea (read-only):
+- Implementation readiness evidence:
+- Phase 2 idea evaluation evidence:
+- Phase 3 project plan evidence:
+- Phase 4 implementation evidence:
+- Phase 5 testing/security evidence:
+- Phase 7 UX evidence:
+- Phase 8 Red Team evidence:
+- Simulation date:
+
+---
+
+## Judge Simulation Baseline
+
+- Hackathon name:
+- Hackathon platform:
+- Hackathon URL:
+- Deadline date/time:
+- Time remaining:
+- Time-aware strategy:
+- Judging criteria:
+- Criteria weights:
+- Judge personas simulated:
+- Environment/runtime actually used:
+- Viewports/devices inspected:
+- Accessibility tools/methods:
+- Paths/files/screens reviewed:
+- Excluded or blocked scope:
+- Limitations:
+
+For each baseline claim label FACT | INFERENCE | ASSUMPTION | UNKNOWN and cite evidence. Missing details are UNKNOWN.
+
+---
+
+## Judge Personas Simulated
+
+| Persona | Focus | Included |
+|---------|-------|----------|
+| Technical Judge | architecture, implementation quality, technical depth | |
+| Product Judge | problem clarity, target users, usefulness | |
+| Demo Judge | demo clarity, reliability, flow | |
+| Skeptical Judge | unsupported claims, weak differentiation | |
+
+---
+
+## Hackathon Judging Criteria
+
+| Criterion | Weight | Source |
+|-----------|--------|--------|
+| | | |
+
+Criteria status: KNOWN | UNKNOWN
+
+---
+
+## First Impression
+
+- What does the product appear to do?
+- Is the target user obvious?
+- Is the problem obvious?
+- Is the value proposition obvious?
+- Can a judge understand the core action without explanation?
+- Does the interface look complete?
+- Is anything misleading?
+
+Evidence status:
+
+---
+
+## Judge-Visible Strengths
+
+| Strength | Evidence | Evidence Type | Confidence |
+|----------|----------|---------------|------------|
+| | | | |
+
+---
+
+## Judge-Visible Weaknesses
+
+| Weakness | Evidence | Evidence Type | Confidence |
+|----------|----------|---------------|------------|
+| | | | |
+
+---
+
+## Criterion-by-Criterion Observations
+
+| Criterion | Weight | Strengths | Weaknesses | Likely Judge Reaction | Confidence | Unknowns |
+|-----------|--------|-------------|------------|-----------------------|------------|----------|
+| | | | | | | |
+
+Store detailed criterion observations in `.sherpa/judge/criterion-NNN.md`.
+
+---
+
+## Simulated Judge Questions
+
+| Question ID | Persona | Question | Criterion | Expected Answer Points | Evidence Supporting Answer | Potential Trap | Confidence | Status |
+|-------------|---------|----------|-----------|------------------------|----------------------------|----------------|------------|--------|
+| | | | | | | | | |
+
+Store detailed questions in `.sherpa/judge/question-NNN.md`.
+
+---
+
+## Expected Answer Quality
+
+| Question ID | Quality | Readiness | Reasoning | Evidence |
+|-------------|---------|-----------|-----------|----------|
+| | | | | |
+
+STRONG | ADEQUATE | WEAK | UNKNOWN | UNSUPPORTED
+
+READY | PARTIALLY_READY | WEAK | UNKNOWN | NOT_APPLICABLE
+
+---
+
+## Likely Objections
+
+| Objection | Basis | Evidence | Severity | Confidence |
+|-----------|-------|----------|----------|------------|
+| | | | | |
+
+---
+
+## Technical Credibility
+
+- Real implementation:
+- Meaningful engineering choices:
+- Appropriate technology:
+- Reasonable architecture:
+- Error handling:
+- Testing:
+- Security awareness:
+- Maintainability:
+- Limitations:
+
+---
+
+## Product Credibility
+
+- Problem clarity:
+- Target user clarity:
+- User value:
+- Practical impact:
+- Usability:
+- Limitations:
+
+---
+
+## Demo Credibility
+
+- Reliability:
+- Clarity:
+- Speed:
+- Visible value:
+- Error handling:
+- Recovery:
+- Consistency:
+
+Demo execution status: NOT_TESTED | PASSED | FAILED | BLOCKED
+
+---
+
+## Claim Consistency
+
+| Claim | Documented In | Repository Shows | Demo Shows | Status |
+|-------|---------------|------------------|------------|--------|
+| | | | | |
+
+CONSISTENT | INCONSISTENT | UNKNOWN
+
+---
+
+## Differentiation Perception
+
+- Actual differentiation:
+- Communicated differentiation:
+- Evidence-backed differentiation:
+- Judge-visible differentiation:
+
+---
+
+## Judge Trust
+
+- Claims backed by evidence:
+- Metrics backed by evidence:
+- Documentation consistent with implementation:
+- Demo consistent with repository:
+- No exaggerated AI claims:
+- No unsupported production claims:
+- Limitations visible:
+
+Trust level: HIGH | MEDIUM | LOW | UNKNOWN
+
+---
+
+## Critical Preparation Risks
+
+| Risk | Severity | Confidence | Mitigation |
+|------|----------|------------|------------|
+| | | | |
+
+---
+
+## Unknowns
+
+| Unknown | Why unknown | Impact | Source |
+|---------|-------------|--------|--------|
+| | | | |
+
+---
+
+## Limitations
+
+- Static code inspection only:
+- No browser/runtime execution:
+- No mobile device testing:
+- No accessibility tooling:
+- No WCAG compliance evaluation:
+- No performance testing:
+- No real user testing:
+
+---
+
+## Judge Readiness Gate
+
+NOT_READY | REVIEW_IN_PROGRESS | BLOCKED | CONDITIONAL | READY
+
+Current:
+
+Reason against every READY criterion:
+
+- Actual project evidence inspected:
+- Relevant criteria identified:
+- Major judge-visible flows reviewed:
+- Critical questions identified:
+- Major claims challenged:
+- Unsupported claims visible:
+- Major objections documented:
+- Evidence limitations documented:
+- No fabricated judge feedback:
+- Phase 1–8 remain locked:
+- Exactly one primary next action:
+
+---
+
+## Recommended Next Action
+
+**PRIMARY NEXT ACTION:**
+
+**WHY:**
+
+**DONE WHEN:**
+
+**Time remaining:**
+
+**Blocked by:**

package/skills/sherpa/templates/lesson.md

@@ -0,0 +1,14 @@
+# Reusable Lesson Record
+
+- Lesson ID: UNKNOWN
+- Title: UNKNOWN
+- Category: RULES / IDEATION / RESEARCH / PRODUCT / ENGINEERING / TESTING / SECURITY / UX / RED TEAM / JUDGE / SCORE / DEMO / PRESENTATION / SUBMISSION / TIME MANAGEMENT / TEAM / PROCESS
+- Situation: UNKNOWN
+- Observation: UNKNOWN
+- Evidence: UNKNOWN
+- Lesson: UNKNOWN
+- Why it matters: UNKNOWN
+- When to apply: UNKNOWN
+- Expected benefit: UNKNOWN
+- Confidence: UNKNOWN
+- Reusable?: UNKNOWN

package/skills/sherpa/templates/postmortem.md

@@ -0,0 +1,87 @@
+# Hackathon Post-Mortem
+
+**Evidence scope:** UNKNOWN  
+**Quality:** NOT_READY / ANALYSIS_IN_PROGRESS / BLOCKED / CONDITIONAL / COMPLETE  
+**Evidence labels:** FACT / INFERENCE / ASSUMPTION / UNKNOWN
+
+## 1. Executive Summary
+UNKNOWN
+## 2. Evidence Scope
+UNKNOWN
+## 3. Hackathon Outcome
+UNKNOWN — result requires official evidence.
+## 4. Timeline
+See timeline record; missing dates remain UNKNOWN.
+## 5. Plan vs Actual
+See plan/actual matrix; missing values remain UNKNOWN.
+## 6. Scope Changes
+Planned / Added / Removed / Deferred / Accidental: UNKNOWN
+## 7. Decision Review
+See decision log; human owner and contemporaneous evidence required.
+## 8. Incident Review
+UNKNOWN unless an incident record with evidence exists.
+## 9. Risk Outcomes
+UNKNOWN unless actual outcomes can be compared with original risks.
+## 10. Testing + Security Review
+UNKNOWN for live project unless Phase 11 evidence is available.
+## 11. UX Review
+UNKNOWN for live project unless Phase 12 evidence is available.
+## 12. Red Team Review
+UNKNOWN for live project unless Phase 13 evidence is available.
+## 13. Judge Simulation Review
+Simulated findings are not actual judge feedback. Actual feedback: UNKNOWN.
+## 14. Score Optimization Review
+Internal expectations are not actual score results. Actual impact: UNKNOWN.
+## 15. Demo Review
+UNKNOWN unless an actual demo record exists.
+## 16. Presentation Review
+UNKNOWN unless actual presentation and feedback evidence exists.
+## 17. Submission Review
+UNKNOWN unless actual submission evidence exists.
+## 18. Wins
+No unsupported wins. UNKNOWN absent evidence.
+## 19. Failures
+No unsupported failures. UNKNOWN absent evidence.
+## 20. Root Cause Analysis
+Observed outcome and possible cause are separate. Causality: UNKNOWN absent evidence.
+## 21. Keep
+| Practice | Evidence | Rationale | Benefit | Priority | Target |
+|---|---|---|---|---|---|
+## 22. Change
+| Practice | Evidence | Rationale | Benefit | Priority | Target |
+|---|---|---|---|---|---|
+## 23. Stop
+| Practice | Evidence | Rationale | Benefit | Priority | Target |
+|---|---|---|---|---|---|
+## 24. Start
+| Practice | Evidence | Rationale | Benefit | Priority | Target |
+|---|---|---|---|---|---|
+## 25. Reusable Lessons
+Use `templates/lesson.md`; unsupported project lessons remain UNKNOWN.
+## 26. Reusable Assets
+Use asset schema: asset, location, purpose, quality, reuse recommendation, required changes.
+## 27. sherpa Effectiveness
+Evaluate Phases 1–19 from use evidence; otherwise UNKNOWN.
+## 28. Process Bottlenecks
+UNKNOWN absent evidence; classify owner/category where supported.
+## 29. Process Debt
+UNKNOWN absent evidence; do not invent skipped work or workarounds.
+## 30. sherpa Contract Gaps
+Record recommendations only; do not rewrite prior phases.
+## 31. Improvement Backlog
+Label `INTERNAL sherpa IMPROVEMENT PRIORITY — NOT OFFICIAL HACKATHON SCORING`.
+## 32. Final Lessons
+UNKNOWN unless derived from cited evidence.
+## 33. Human Review
+Reviewer / status / date: UNKNOWN
+## 34. Post-Mortem Status
+NOT_READY / ANALYSIS_IN_PROGRESS / BLOCKED / CONDITIONAL / COMPLETE
+## 35. PRIMARY NEXT ACTION
+Exactly one evidence-backed closure action. Never Phase 21.
+
+## 26. Reusable Assets
+| Asset | Location | Purpose | Quality | Reuse Recommendation | Required Changes |
+|---|---|---|---|---|---|
+| UNKNOWN | UNKNOWN | UNKNOWN | UNKNOWN | UNKNOWN | UNKNOWN |
+
+Bottleneck categories: TOOLING / PROCESS / KNOWLEDGE / TIME / DEPENDENCY / HUMAN_DECISION / COMMUNICATION / UNKNOWN.

package/skills/sherpa/templates/presentation-evidence.md

@@ -0,0 +1,33 @@
+# Presentation Evidence
+
+**Evidence ID:** <unique ID>  
+**Claim ID:** <reference to presentation claim or UNKNOWN>  
+**Slide ID:** <reference to slide or UNKNOWN>  
+
+---
+
+## Evidence
+
+| Evidence Item | Evidence Type | Source | Evidence Status | Confidence |
+|---------------|---------------|--------|-----------------|------------|
+| | UI / output / test / log / artifact / live behavior / screenshot / recording / documentation / benchmark / source/code inspection | | FACT / INFERENCE / ASSUMPTION / UNKNOWN | HIGH / MEDIUM / LOW / UNKNOWN |
+
+---
+
+## Verification
+
+| Verification Method | Result | Status |
+|---------------------|--------|--------|
+| | | PLANNED / EXECUTED / PASSED / FAILED / BLOCKED / UNKNOWN / NOT_APPLICABLE |
+
+---
+
+## Judge Takeaway
+
+**Expected Takeaway:** <what the judge should remember>
+
+**Confidence:** HIGH / MEDIUM / LOW / UNKNOWN
+
+---
+
+**Rule:** No evidence → UNKNOWN. Weak evidence cannot be upgraded merely because a slide exists. Generated documentation is not proof of runtime behavior. A screenshot must not be presented as current live behavior unless independently verified.