sherpa-skill 2.0.6 → 2.0.7

package/.agents/skills/sherpa/templates/idea-evaluation.md

@@ -0,0 +1,251 @@
+# Idea Evaluation — <idea-name>
+
+**One-line description:** <one-sentence description>
+
+**Submitted by:** <team member or "team">
+**Evaluation date:** <UTC date/time>
+
+---
+
+## 1. Problem & Solution Framing
+
+**Problem statement:** <problem as stated by user>
+
+**Target users:** <who the product is for, or UNKNOWN>
+
+**Proposed solution:** <one-sentence solution description>
+
+---
+
+## 2. Category Scores
+
+Each dimension is scored 1–10 with reasoning, evidence type (FACT / INFERENCE / ASSUMPTION / UNKNOWN), source, and confidence (low / medium / high).
+
+### Category 1: Problem & Solution
+
+| Dimension | Score | Reasoning | Evidence Type | Source | Confidence |
+|-----------|-------|-----------|---------------|--------|------------|
+| 1. Problem importance | | | | | |
+| 2. Problem clarity | | | | | |
+| 3. Target-user clarity | | | | | |
+| 4. User pain | | | | | |
+| 5. Solution usefulness | | | | | |
+
+**Category score:** <weighted average or simple average>
+
+---
+
+### Category 2: Innovation & Differentiation
+
+| Dimension | Score | Reasoning | Evidence Type | Source | Confidence |
+|-----------|-------|-----------|---------------|--------|------------|
+| 6. Innovation | | | | | |
+| 7. Differentiation | | | | | |
+
+**Category score:** <average>
+
+---
+
+### Category 3: Technical Feasibility
+
+| Dimension | Score | Reasoning | Evidence Type | Source | Confidence |
+|-----------|-------|-----------|---------------|--------|------------|
+| 8. Technical feasibility | | | | | |
+| 9. AI/ML necessity | | | | | |
+| 10. Implementation complexity | | | | | |
+
+**Category score:** <average>
+
+---
+
+### Category 4: Implementation Reality
+
+| Dimension | Score | Reasoning | Evidence Type | Source | Confidence |
+|-----------|-------|-----------|---------------|--------|------------|
+| 11. Time required | | | | | |
+| 12. Team skill fit | | | | | |
+
+**Category score:** <average>
+
+---
+
+### Category 5: Demo & Presentation
+
+| Dimension | Score | Reasoning | Evidence Type | Source | Confidence |
+|-----------|-------|-----------|---------------|--------|------------|
+| 13. Demo potential | | | | | |
+| 14. Judge appeal | | | | | |
+
+**Category score:** <average>
+
+---
+
+### Category 6: Criteria Alignment (Meta-Validation)
+
+| Dimension | Score | Reasoning | Evidence Type | Source | Confidence |
+|-----------|-------|-----------|---------------|--------|------------|
+| 15. Judging-criteria alignment | | | | | |
+
+**Alignment check:** <PASS / FAIL — do all category scores map to stated judging criteria?>
+
+**Note:** Category 6 does not add points. It validates that other category scores correctly map to the hackathon's stated criteria.
+
+---
+
+### Category 7: Impact & Market
+
+| Dimension | Score | Reasoning | Evidence Type | Source | Confidence |
+|-----------|-------|-----------|---------------|--------|------------|
+| 16. Scalability/potential | | | | | |
+| 17. Real-world impact | | | | | |
+
+**Category score:** <average>
+
+---
+
+### Category 8: Competition & Risk Context
+
+| Dimension | Score | Reasoning | Evidence Type | Source | Confidence |
+|-----------|-------|-----------|---------------|--------|------------|
+| 18. Competitive landscape | | | | | |
+| 19. Defensibility | | | | | |
+
+**Category score:** <average>
+
+---
+
+### Category 9: Risk & Evidence Quality
+
+| Dimension | Score | Reasoning | Evidence Type | Source | Confidence |
+|-----------|-------|-----------|---------------|--------|------------|
+| 20. Risk | | | | | |
+| 21. Evidence quality | | | | | |
+
+**Category score:** <average>
+
+---
+
+## 3. Research Evidence
+
+List all external research used to support dimension scores. Each entry must be tagged FACT / INFERENCE / ASSUMPTION / UNKNOWN with a source.
+
+| # | Claim | Type | Source | Confidence |
+|---|-------|------|--------|------------|
+| 1 | | | | |
+| 2 | | | | |
+| 3 | | | | |
+
+**Rule:** Never claim research was performed unless evidence was actually retrieved. If no evidence exists, mark UNKNOWN.
+
+---
+
+## 4. Feasibility & Risk Gate
+
+**Calculation:**
+
+```
+feasibility_composite = avg(
+    dimension_8,                        // technical feasibility
+    (11 - dimension_10),                // implementation complexity inverted
+    (11 - dimension_11),                // time required inverted
+    dimension_12,                        // team skill fit
+    (11 - dimension_20)                 // risk inverted
+)
+```
+
+| Component | Value |
+|-----------|-------|
+| Dimension 8 (technical feasibility) | |
+| Dimension 10 (implementation complexity) | |
+| 11 − dimension_10 (inverted complexity) | |
+| Dimension 11 (time required) | |
+| 11 − dimension_11 (inverted time) | |
+| Dimension 12 (team skill fit) | |
+| Dimension 20 (risk) | |
+| 11 − dimension_20 (inverted risk) | |
+| **feasibility_composite** | **<value> / 10** |
+
+**Gate result:** <PASS (≥ 6.0) | FAIL (< 6.0)>
+
+---
+
+## 5. Red-Team Outcome
+
+**Outcome:** <KILL | MAJOR CONCERN | MINOR CONCERN>
+
+**KILL conditions checked:**
+- [ ] Feasibility gate FAIL with no credible revision path within time
+- [ ] Dimension 20 (risk) ≥ 9 AND Dimension 8 (feasibility) ≤ 3
+- [ ] Dimension 9 (AI necessity) ≤ 3 AND idea claims "AI-powered"
+
+**Weaknesses identified:**
+1. <weakness 1>
+2. <weakness 2>
+3. <weakness 3>
+
+**Kill question that exposes biggest weakness:** <question>
+
+---
+
+## 6. Scoring
+
+**Judging criteria used:** <list criteria and weights, or "UNKNOWN — equal weights applied">
+
+| Criterion | Weight | Score |
+|-----------|--------|-------|
+| | | |
+| | | |
+| | | |
+
+**Raw score:** <0–100>
+
+**Feasibility factor:** <feasibility_composite / 10>
+
+**Final score:** <raw_score × feasibility_factor>
+
+**Overall confidence:** <low | medium | high>
+
+**Confidence factors:**
+- Evidence quality (dimension 21): <score>
+- Criteria known: <yes / partial / UNKNOWN>
+- All dimensions filled: <yes / no>
+
+---
+
+## 7. Decision-Relevant Fields
+
+**Recommended outcome:** <SELECT | REVISE | REJECT_ALL>
+
+**Why this outcome:**
+<explanation tied to category scores and red-team outcome>
+
+**Strongest advantages:**
+<top 3 category strengths with scores>
+
+**Biggest risks:**
+<red-team findings that survived but remain concerns>
+
+**What must be true for this idea to succeed:**
+<assumptions that must hold>
+
+**Minimum viable version:**
+<scope that can be built in remaining time>
+
+**Highest-value differentiator:**
+<the one thing that makes this win>
+
+**Estimated implementation difficulty:** <low | medium | high>
+
+**Recommended next action:**
+<exactly ONE action>
+
+---
+
+## 8. Human Confirmation
+
+**Human confirmation status:** <pending | confirmed | rejected>
+
+**Confirmed by:** <name or "pending">
+**Confirmed at:** <UTC date/time or "pending">
+
+**Rule:** Only explicit human confirmation can set `selected idea` in `.sherpa/project-state.md`. The engine recommends; the human decides.

package/.agents/skills/sherpa/templates/implementation-plan.md

@@ -0,0 +1,96 @@
+# Implementation Plan
+
+## Project
+- Name: UNKNOWN
+- Source project-state: `.sherpa/project-state.md`
+- Plan status: NOT READY | READY | IN PROGRESS | BLOCKED | COMPLETE
+- Last reviewed: UNKNOWN
+
+## Selected Idea
+- Name: UNKNOWN
+- Phase 2 evidence: UNKNOWN
+
+## Readiness
+- Selected idea: UNKNOWN
+- Repository baseline: UNKNOWN
+- Phase 3 repository analysis: UNKNOWN
+- Phase 3 project plan: UNKNOWN
+- Architecture: UNKNOWN
+- MVP: UNKNOWN
+- Implementation readiness: NOT READY | READY
+- Blocking issues: UNKNOWN
+
+## Development Baseline
+- Repository root: UNKNOWN
+- Revision: UNKNOWN
+- Working tree: UNKNOWN
+- Runtime: UNKNOWN
+- Framework: UNKNOWN
+- Package manager: UNKNOWN
+- Entry points: UNKNOWN
+- Existing tests: UNKNOWN
+- Build command: UNKNOWN
+- Run command: UNKNOWN
+- Environment/configuration: UNKNOWN (record variable names only; never secret values)
+- Current implementation status: UNKNOWN
+
+## Workstreams
+
+### Workstream 1 — <name>
+- Objective: UNKNOWN
+- Files/components: UNKNOWN
+- Dependencies: UNKNOWN
+- Tasks: UNKNOWN
+- Validation: UNKNOWN
+- Status: NOT_STARTED | IN_PROGRESS | BLOCKED | COMPLETE
+
+### Workstream 2 — <name>
+- Objective: UNKNOWN
+- Files/components: UNKNOWN
+- Dependencies: UNKNOWN
+- Tasks: UNKNOWN
+- Validation: UNKNOWN
+- Status: NOT_STARTED | IN_PROGRESS | BLOCKED | COMPLETE
+
+## Critical Path
+
+1. UNKNOWN
+
+## Task Queue
+
+| ID | Task | Workstream | MVP priority | Dependencies | Status |
+|---|---|---|---|---|---|
+| UNKNOWN | UNKNOWN | UNKNOWN | MUST HAVE / SHOULD HAVE / OPTIONAL | UNKNOWN | NOT_STARTED / IN_PROGRESS / BLOCKED / COMPLETE |
+
+## Implementation Risks
+
+| Risk | Likelihood | Impact | Mitigation | Evidence type |
+|---|---|---|---|---|
+| UNKNOWN | UNKNOWN | UNKNOWN | UNKNOWN | UNKNOWN |
+
+## Blockers
+- UNKNOWN
+
+## Validation Strategy
+- Relevant checks by task/component: UNKNOWN
+- Checks actually executed and results: UNKNOWN
+- Checks not run: UNKNOWN
+
+## Execution Evidence
+- Record command, date/time, exit/result, scope, and relevant output for each execution claim. Do not use generated planning artifacts as execution evidence.
+- Evidence: UNKNOWN
+
+## Time Strategy
+- Time remaining: UNKNOWN
+- Priority focus: UNKNOWN
+
+## Unknowns
+- UNKNOWN
+
+## Current Implementation Status
+- Overall: NOT_STARTED | IN_PROGRESS | BLOCKED | COMPLETE
+- Current task: UNKNOWN
+- Completed workstreams: UNKNOWN
+
+## Recommended Next Action
+- PRIMARY NEXT ACTION: UNKNOWN

package/.agents/skills/sherpa/templates/implementation-task.md

@@ -0,0 +1,57 @@
+# Implementation Task
+
+## Task ID
+UNKNOWN
+
+## Title
+UNKNOWN
+
+## Objective
+UNKNOWN
+
+## Why This Task Exists
+Approved plan reference: UNKNOWN
+MVP priority: MUST HAVE | SHOULD HAVE | OPTIONAL
+
+## Workstream
+UNKNOWN
+
+## Priority
+MUST HAVE | SHOULD HAVE | OPTIONAL
+
+## Dependencies
+- UNKNOWN
+
+## Files / Components
+- UNKNOWN
+
+## Preconditions
+- Readiness evidence: UNKNOWN
+- Architecture approval: UNKNOWN
+- Required dependencies available: UNKNOWN
+
+## Planned Change
+UNKNOWN
+
+## Validation Required
+- Commands/checks: UNKNOWN
+- Expected evidence: UNKNOWN
+
+## Execution Result
+- Status: NOT_STARTED | IN_PROGRESS | BLOCKED | COMPLETE
+- Change summary: UNKNOWN
+- Validation result: UNKNOWN
+- Failures/blockers: UNKNOWN
+
+## Evidence
+- Command, date/time, exit/result, scope, and relevant output: UNKNOWN
+- Source (repository path or execution record): UNKNOWN
+
+## Risks
+- UNKNOWN
+
+## Status
+NOT_STARTED | IN_PROGRESS | BLOCKED | COMPLETE
+
+## Notes
+UNKNOWN

package/.agents/skills/sherpa/templates/improvement-candidate.md

@@ -0,0 +1,135 @@
+# Improvement Candidate — <ID>
+
+**Candidate ID:** <unique ID>  
+**Title:** <short title>  
+**Description:** <what specifically would change>
+
+---
+
+## 1. Target Criterion
+
+| Field | Value |
+|-------|-------|
+| Criterion | <name> |
+| Weight | <weight or UNKNOWN> |
+| Weight Label | OFFICIAL / UNKNOWN / PROVISIONAL |
+| Current Performance | <1–10 or UNKNOWN> |
+| Gap Classification | NONE / LOW / MEDIUM / HIGH / CRITICAL / UNKNOWN |
+
+---
+
+## 2. Category Assignment
+
+**Category(ies):**
+
+| ID | Category | Rationale |
+|----|----------|-----------|
+| A | Differentiation | |
+| B | Technical Credibility | |
+| C | Core Functionality | |
+| D | Demo Impact | |
+| E | UX | |
+| F | Security / Trust | |
+| G | Evidence | |
+| H | Presentation | |
+| I | Reliability | |
+
+**Rule:** Select one or more. Presentation (H) only within current phase scope; no PPT creation.
+
+---
+
+## 3. Expected Score Impact
+
+**Score Impact:** VERY LOW / LOW / MEDIUM / HIGH / VERY HIGH
+
+**Reasoning:** <why this impact level>
+
+**Evidence:** <FACT / INFERENCE / ASSUMPTION / UNKNOWN>  
+**Source:** <path or description>  
+**Confidence:** HIGH / MEDIUM / LOW / UNKNOWN
+
+**Score Label:** OFFICIAL / ESTIMATED / PROVISIONAL / UNKNOWN
+
+---
+
+## 4. Evaluation Dimensions
+
+| Dimension | Value |
+|-----------|-------|
+| Score Impact | VERY LOW / LOW / MEDIUM / HIGH / VERY HIGH |
+| Confidence | HIGH / MEDIUM / LOW / UNKNOWN |
+| Judge Visibility | LOW / MEDIUM / HIGH / VERY HIGH |
+| Implementation Cost | TRIVIAL / LOW / MEDIUM / HIGH / VERY HIGH |
+| Risk | LOW / MEDIUM / HIGH / CRITICAL / UNKNOWN |
+
+---
+
+## 5. Optimization Heuristic
+
+**OPTIMIZATION HEURISTIC — Not judging mathematics.**
+
+```
+Expected Value = Score Impact × Confidence × Judge Visibility ÷ Implementation Cost
+```
+
+**Heuristic Rank:** <number or UNKNOWN>  
+**Heuristic Basis:** <qualitative explanation>
+
+---
+
+## 6. Implementation Details
+
+| Field | Value |
+|-------|-------|
+| Time Required | <hours or UNKNOWN> |
+| Dependencies | <list or UNKNOWN> |
+| Blockers | <list or UNKNOWN> |
+| Files/Components Affected | <list or UNKNOWN> |
+| Validation Required | <commands/checks or UNKNOWN> |
+
+---
+
+## 7. Worth Doing Assessment
+
+**Is this improvement worth doing?** YES / NO / UNKNOWN
+
+**Reasoning:** <why or why not, tied to impact, cost, risk, time, and judge visibility>
+
+**Time-aware filtering applied:** YES / NO  
+**Time-aware category:** >24h / 12–24h / 6–12h / 2–6h / <2h / UNKNOWN
+
+---
+
+## 8. What Should NOT Be Changed (Related)
+
+| Item | Reason | Risk of Changing |
+|------|--------|------------------|
+| | | |
+
+---
+
+## 9. Priority Classification
+
+**Priority:** P0 — CRITICAL | P1 — HIGH IMPACT | P2 — MEDIUM IMPACT | P3 — LOW IMPACT | DROP
+
+**Reasoning:** <exactly one priority, tied to the definitions>
+
+**Rule:** Every candidate receives exactly one priority.
+
+---
+
+## 10. Unknowns
+
+| Unknown | Why Unknown | Impact | Source |
+|---------|-------------|--------|--------|
+| | | | |
+
+---
+
+## 11. Evidence Summary
+
+| Claim | Evidence Type | Source | Confidence |
+|-------|---------------|--------|------------|
+| | FACT / INFERENCE / ASSUMPTION / UNKNOWN | | HIGH / MEDIUM / LOW / UNKNOWN |
+
+**Rule:** Never convert UNKNOWN into a favorable assumption. Do not claim score improvements without evidence.

package/.agents/skills/sherpa/templates/improvement.md

@@ -0,0 +1,18 @@
+# Internal Improvement Record
+
+- Improvement ID: UNKNOWN
+- Title: UNKNOWN
+- Affected phase: UNKNOWN
+- Problem / contract gap: UNKNOWN
+- Evidence: UNKNOWN
+- Recommendation: UNKNOWN
+- Expected impact: UNKNOWN
+- Cost: UNKNOWN
+- Dependencies: UNKNOWN
+- Priority: P0 / P1 / P2 / P3
+- Status: UNKNOWN
+- Target / owner: UNKNOWN
+
+**INTERNAL sherpa IMPROVEMENT PRIORITY — NOT OFFICIAL HACKATHON SCORING**
+
+Recommendation only. Does not authorize modification of locked prior-phase artifacts.

package/.agents/skills/sherpa/templates/incident.md

@@ -0,0 +1,20 @@
+# Incident Retrospective Record
+
+- Incident ID: UNKNOWN
+- Title: UNKNOWN
+- Phase: UNKNOWN
+- Severity: UNKNOWN
+- Date / time: UNKNOWN
+- What happened: UNKNOWN
+- Expected behavior: UNKNOWN
+- Actual behavior: UNKNOWN
+- Evidence: UNKNOWN
+- Impact: UNKNOWN
+- Immediate response: UNKNOWN
+- Resolution: UNKNOWN
+- Root cause status: UNKNOWN
+- Contributing factors: UNKNOWN
+- Preventive action: UNKNOWN
+- Lesson: UNKNOWN
+
+Do not create an incident without evidence. Avoid blame unless evidence supports an appropriate attribution.

package/.agents/skills/sherpa/templates/judge-criterion.md

@@ -0,0 +1,41 @@
+# Judge Criterion
+
+## Criterion ID
+
+## Criterion Name
+
+## Source
+
+OFFICIAL | USER_PROVIDED | UNKNOWN | SIMULATION CRITERION (NOT OFFICIAL RUBRIC)
+
+## Official Weight
+
+## Weight Source
+
+## Judge Question
+
+## Evidence
+
+| Evidence Item | Evidence Type | Source | Confidence | Mapping Status |
+|---------------|---------------|--------|------------|----------------|
+| | | | | SUPPORTED / PARTIALLY_SUPPORTED / UNKNOWN / CONTRADICTED / NOT_APPLICABLE |
+
+## Observed Strengths
+
+## Observed Weaknesses
+
+## Likely Judge Reaction
+
+## Confidence
+
+HIGH | MEDIUM | LOW | UNKNOWN
+
+## Unknowns
+
+## Potential Concern
+
+## Contributing Categories
+
+| Category | Diagnostic Dimensions |
+|----------|----------------------|
+| | | |

package/.agents/skills/sherpa/templates/judge-question.md

@@ -0,0 +1,41 @@
+# Judge Question
+
+## Question ID
+
+## Persona
+
+TECHNICAL | PRODUCT | DEMO | SKEPTICAL
+
+## Question
+
+## Why a judge might ask
+
+## Relevant criterion
+
+## Expected answer points
+
+1.
+2.
+3.
+
+## Evidence supporting answer
+
+## Potential trap
+
+## Confidence
+
+HIGH | MEDIUM | LOW | UNKNOWN
+
+## Status
+
+EXPECTED | ANSWERED | UNANSWERED | BLOCKED | UNKNOWN
+
+## Answer quality
+
+STRONG | ADEQUATE | WEAK | UNKNOWN | UNSUPPORTED
+
+## Answer readiness
+
+READY | PARTIALLY_READY | WEAK | UNKNOWN | NOT_APPLICABLE
+
+## Reasoning