@agentskillkit/agent-skills 1.0.1 → 3.2.1

package/.agent/skills/governance/proposals/v1.1-change-proposal-template.md

@@ -1,197 +0,0 @@
----
-name: v1.1-change-proposal-template
-version: 1.0.0
-status: TEMPLATE
-authority: GOVERNANCE
-parent: coinpika-master-constitution
----
-
-# 🏷️ CoinPika Change Proposal — v1.1+  
-**(Controlled Doctrine Evolution Request)**
-
-⚠️ **THIS IS NOT A PULL REQUEST**
-
-This document proposes a **potential change** to CoinPika’s
-Constitution, doctrines, or enforcement rules.
-
-If this proposal is **REJECTED**,  
-**NO IMPLEMENTATION MAY PROCEED**.
-
-Doctrine evolution is **rare by design**.
-
----
-
-## 1. Proposal Metadata
-
-- **Proposal ID:** CP-YYYY-MM-DD-XX
-- **Author(s):**
-- **Date:**
-- **Target Version:** v1.1.x / v2.0.0
-- **Status:** Draft / Under Review / Approved / Rejected
-
----
-
-## 2. Change Summary (Plain Language)
-
-Describe the proposed change **without implementation details**:
-
-- What is changing?
-- Which law, doctrine, or invariant is affected?
-- What problem does this change attempt to solve?
-
-If this cannot be explained clearly,  
-the proposal is **INVALID**.
-
----
-
-## 3. Change Classification (MANDATORY)
-
-This proposal affects (check all that apply):
-
-- [ ] Constitution
-- [ ] Architecture Doctrine
-- [ ] Backend Data Engine Doctrine
-- [ ] Chart Data Doctrine
-- [ ] Frontend Mobile / Gesture Doctrine
-- [ ] Performance Doctrine
-- [ ] Commercial Guardrails
-- [ ] Review / Enforcement Rules
-- [ ] AI Learning / Agent Governance
-
-Unclassified impact = **AUTOMATIC REJECTION**.
-
----
-
-## 4. Constitutional Impact Analysis (MANDATORY)
-
-For EACH Prime Directive, explicitly state impact:
-
-- **Correctness > Convenience:** Affected / Not Affected
-- **Trust > Speed:** Affected / Not Affected
-- **Architecture > Trends:** Affected / Not Affected
-- **Predictability > Cleverness:** Affected / Not Affected
-- **Explicit Trade-offs Only:** Affected / Not Affected
-
-If ANY directive is weakened,  
-the proposal is **EXTREMELY UNLIKELY TO PASS**.
-
----
-
-## 5. Doctrine Impact Matrix
-
-List **ALL** affected documents.
-
-| Doctrine / File | Impact Level | Explanation |
-|-----------------|--------------|-------------|
-| coinpika-master-constitution | None / Minor / Major | |
-| coinpika-architecture-doctrine | | |
-| coinpika-backend-data-engine-doctrine | | |
-| coinpika-chart-data-doctrine | | |
-| coinpika-frontend-mobile-doctrine | | |
-| coinpika-swipe-tabs-doctrine | | |
-| coinpika-performance-doctrine | | |
-| coinpika-commercial-guardrails-doctrine | | |
-| coinpika-code-review-doctrine | | |
-| coinpika-learning-engine-doctrine | | |
-| coinpika-agent-enforcement-protocol | | |
-
-Missing an affected doctrine = **REJECTION**.
-
----
-
-## 6. Motivation & Evidence (MANDATORY)
-
-This section MUST include **concrete evidence**:
-
-- Production incidents
-- Real-world constraints
-- Measurable limitations
-- Audit or compliance findings
-
-Speculation, taste, or elegance  
-are **NOT VALID MOTIVATIONS**.
-
----
-
-## 7. Alternatives Considered
-
-List alternatives that were considered and rejected:
-
-- Alternative A:
-- Alternative B:
-
-Explain **why each alternative fails**
-without changing doctrine.
-
-No alternatives considered = **INCOMPLETE PROPOSAL**.
-
----
-
-## 8. Risk & Blast Radius Assessment
-
-Explicitly describe:
-
-- What could break if this change is wrong
-- Which users or systems are affected
-- Worst-case failure scenario
-- Reversibility (Yes / No)
-
-Irreversible changes are  
-**STRONGLY DISCOURAGED**.
-
----
-
-## 9. Compatibility & Migration Plan
-
-- Is v1.0 behavior preserved during transition?
-- Is migration explicit and bounded?
-- Is rollback possible and documented?
-
-Breaking compatibility without transition = **REJECTION**.
-
----
-
-## 10. Recommendation
-
-The author recommends:
-
-- [ ] Approve
-- [ ] Approve with constraints
-- [ ] Reject
-
-Explain the recommendation  
-**without implementation bias**.
-
----
-
-## 11. Constitutional Review & Verdict
-
-**Reviewed by:**
-- Architecture
-- Commercial / Risk
-- Performance
-- AI Governance
-
-**Final Verdict:**
-
-- [ ] Approved → Scheduled for v1.1+
-- [ ] Rejected → Doctrine v1.0 remains authoritative
-
----
-
-## Enforcement Notice
-
-No code, PR, workflow, or agent output  
-may assume this change until it is:
-
-- Explicitly approved
-- Versioned
-- Released
-
-Doctrine changes without approval  
-are **GOVERNANCE VIOLATIONS**.
-
----
-
-**Template Status:** ACTIVE  
-**Applies To:** Humans & AI Agents  

package/.agent/skills/governance/resources/AUTHORITY_MODEL.md

@@ -1,111 +0,0 @@
-# Authority Model
-
-## Supreme Authority
-
-The `coinpika-doctrine-pack` skill has **SUPREME AUTHORITY** in the CoinPika ecosystem.
-
-### What This Means
-
-This skill **overrides**:
-- ✖ All other skills
-- ✖ Framework defaults
-- ✖ Tooling heuristics
-- ✖ Agent preferences
-- ✖ Developer convenience
-- ✖ "It works" arguments
-
-No implicit override is permitted.
-
-## Decision Precedence Order
-
-When conflicts arise, decisions are resolved in this strict order:
-
-1. 👑 **CoinPika Master Constitution** (HIGHEST)
-   - Prime Directives (immutable)
-   - System Laws (non-negotiable)
-   - Constitutional scope
-
-2. 🏛️ **Architecture & System Doctrines**
-   - System boundaries
-   - Data ownership
-   - Dependency direction
-
-3. 💼 **Commercial Guardrails**
-   - Breaking change assessment
-   - Rollback requirements
-   - Financial data protection
-
-4. ⚡ **Performance Doctrine**
-   - Caching strategy
-   - Scalability invariants
-   - Load behavior
-
-5. 📋 **Review Checklists**
-   - Domain-specific guidance
-   - Verification steps
-
-6. 🤖 **Agent Enforcement Protocol**
-   - Agent behavior constraints
-   - Learning boundaries
-
-7. 👤 **Developer or Agent Preference** (LOWEST)
-   - Personal style
-   - Convenience
-   - Short-term optimization
-
-### Enforcement Rule
-
-Anything lower **cannot override** anything higher.
-
-**There are NO exceptions.**
-
-## Agent Operating Mode
-
-All agents using this skill MUST operate in:
-
-- **POLICY_MODE = STRICT**
-- **AUTONOMY = PROPOSAL_ONLY**
-- **TRUST_LEVEL = ZERO**
-
-### Agents MAY:
-- ✅ Propose implementations
-- ✅ Explain trade-offs
-- ✅ Identify risks
-- ✅ Cite applicable doctrines
-
-### Agents MUST NOT:
-- ❌ Approve changes
-- ❌ Merge code
-- ❌ Introduce new invariants
-- ❌ Override architecture
-- ❌ Bypass enforcement
-- ❌ Argue against constitutional decisions
-
-## Violation Response
-
-When a violation is detected, the agent MUST:
-
-1. **STOP** execution immediately
-2. **CITE** the violated doctrine or law
-3. **EXPLAIN** the systemic risk
-4. **REFUSE** the request or output
-
-Partial compliance or "best effort" responses are considered **enforcement failures**.
-
-## Change Authority
-
-This skill is **LOCKED**.
-
-Changes require:
-- An approved Change Proposal
-- Explicit version bump
-- Constitutional review
-
-Unauthorized modification of doctrine files is a **governance violation**.
-
-## Final Authority Statement
-
-> This Constitution overrides all other considerations.
-> CoinPika optimizes for **long-term trust, correctness, and durability**—not short-term velocity.
-> Safety overrides productivity.
-> If in doubt — **REFUSE**.

package/.agent/skills/governance/resources/ENFORCEMENT_GUIDE.md

@@ -1,242 +0,0 @@
-# Enforcement Guide
-
-## How to Enforce CoinPika Doctrines
-
-This guide explains how to actively enforce constitutional and doctrinal requirements in code reviews, architecture decisions, and AI agent behavior.
-
-## Enforcement Levels
-
-### Level 1: Constitutional (IMMUTABLE)
-**Source**: `constitution/coinpika-master-constitution.md`
-
-**Violations at this level are FATAL**. The work must be rejected entirely.
-
-**Examples**:
-- Modifying historical data in place (violates Law 2)
-- Frontend making truth decisions (violates Law 1)
-- Injecting realtime ticks into charts (violates Law 3)
-
-**Response**: Stop, cite, refuse.
-
----
-
-### Level 2: Architectural (NON-NEGOTIABLE)
-**Source**: `doctrines/architecture/`, `doctrines/backend/`, `doctrines/data/`
-
-**Violations at this level compromise system integrity**.
-
-**Examples**:
-- Blurred ownership between layers
-- Client-side data reconstruction
-- Implicit dependencies
-
-**Response**: Require architectural redesign before proceeding.
-
----
-
-### Level 3: Domain-Specific (STRICT)
-**Source**: `doctrines/frontend/`, `doctrines/performance/`, `doctrines/commercial/`
-
-**Violations at this level create technical debt or risk**.
-
-**Examples**:
-- Not following swipe-tab architecture
-- Missing caching strategy
-- No rollback plan for breaking changes
-
-**Response**: Block until compliance is demonstrated.
-
----
-
-### Level 4: Process (ENFORCED)
-**Source**: `enforcement/checklists/`, `doctrines/review/`
-
-**Violations at this level indicate incomplete work**.
-
-**Examples**:
-- Skipping code review checklist
-- Missing test coverage
-- Undocumented breaking changes
-
-**Response**: Return for completion.
-
----
-
-## Enforcement Workflow
-
-### 1. Pre-Review
-Before reviewing code/design:
-
-1. ✅ Load `SKILL.md` to identify applicable doctrines
-2. ✅ Load `constitution/` for Prime Directives and System Laws
-3. ✅ Load relevant `doctrines/` based on domain
-4. ✅ Select appropriate `enforcement/checklists/`
-
-### 2. During Review
-While reviewing:
-
-1. **Check Constitutional Compliance**
-   - Are Prime Directives violated?
-   - Are System Laws (1-4) upheld?
-   - Is learning subordinate to Constitution?
-
-2. **Check Architectural Compliance**
-   - Clear ownership boundaries?
-   - Proper dependency direction?
-   - No implicit coupling?
-
-3. **Check Domain Compliance**
-   - Backend: Data engine rules followed?
-   - Frontend: Mobile UX patterns correct?
-   - Data: Chart integrity maintained?
-   - Performance: Caching strategy defined?
-
-4. **Check Process Compliance**
-   - Checklist completed?
-   - Breaking changes documented?
-   - Rollback plan exists?
-
-### 3. Post-Review
-After violations found:
-
-1. **Stop execution**
-2. **Cite specific doctrine** (with file path)
-3. **Explain systemic risk**
-4. **Refuse or request redesign**
-
-### 4. Approval
-Only approve if:
-- ✅ All constitutional laws upheld
-- ✅ All architectural boundaries respected
-- ✅ All domain rules followed
-- ✅ All checklists completed
-
-**Remember**: Partial compliance is not compliance.
-
----
-
-## Enforcement Examples
-
-### Example 1: Backend API Adding Chart Data
-
-**Request**: "Add a new endpoint to serve sparkline data"
-
-**Enforcement Checklist**:
-1. Load `doctrines/backend/coinpika-backend-data-engine-doctrine.md`
-2. Load `doctrines/data/coinpika-chart-data-doctrine.md`
-3. Load `enforcement/checklists/backend-api-review-checklist.md`
-
-**Key Checks**:
-- ✅ Historical data is immutable (Law 2)?
-- ✅ Realtime data separated from history (Law 3)?
-- ✅ Chart truthfulness maintained (Law 4)?
-- ✅ Caching strategy defined (Performance)?
-- ✅ Rate limiting implemented (Performance)?
-
-**Cite if violated**: "This violates Law 3 (Realtime Ephemerality) from `constitution/coinpika-master-constitution.md`. Realtime ticks must not be persisted as historical aggregates."
-
----
-
-### Example 2: Frontend Mobile Gesture Change
-
-**Request**: "Modify swipe behavior on Portfolio page"
-
-**Enforcement Checklist**:
-1. Load `doctrines/frontend/coinpika-frontend-mobile-doctrine.md`
-2. Load `doctrines/frontend/coinpika-swipe-tabs-doctrine.md`
-3. Load `enforcement/checklists/mobile-gesture-review-checklist.md`
-
-**Key Checks**:
-- ✅ Native gesture precedence maintained?
-- ✅ No gesture conflicts introduced?
-- ✅ Swipe-tab architecture followed?
-- ✅ Predictable behavior guaranteed?
-
-**Cite if violated**: "This violates the Native Gesture Precedence rule from `doctrines/frontend/coinpika-frontend-mobile-doctrine.md`. Native scrolling must never be blocked."
-
----
-
-### Example 3: AI Agent Proposing "Smart Fix"
-
-**Request**: Agent suggests "Let's cache prices in localStorage for offline mode"
-
-**Enforcement Checklist**:
-1. Load `constitution/` (Law 1: Truth Ownership)
-2. Load `doctrines/architecture/` (Dependency Direction Law)
-3. Load `doctrines/learning/coinpika-learning-engine-doctrine.md`
-
-**Key Checks**:
-- ❌ Frontend managing truth? (Violates Law 1)
-- ❌ Client-side caching of financial data? (Violates Architecture)
-- ❌ Agent proposing architectural change without approval? (Violates Learning)
-
-**Response**: "This violates Law 1 (Truth Ownership) from the Master Constitution. The backend must remain the single source of truth for all financial data. Frontend caching of prices is architecturally forbidden. Please propose a backend-first caching strategy instead."
-
----
-
-## Agent-Specific Enforcement
-
-### When AI Agent Violates Doctrine
-
-If an agent:
-- Produces unsafe output
-- Violates doctrine repeatedly
-- Shows unpredictable drift
-- Argues against constitutional decisions
-
-Then:
-1. **Reject output immediately**
-2. **Cite violation** with doctrine reference
-3. **Restrict agent autonomy** if repeated
-4. **Audit past outputs** if severity is high
-
-### Agent Learning Boundaries
-
-Agents MAY learn:
-- ✅ Better reasoning patterns
-- ✅ Improved architectural judgment
-- ✅ More accurate risk assessment
-
-Agents MUST NOT learn:
-- ❌ Code style preferences
-- ❌ Naming conventions
-- ❌ Temporary workarounds
-- ❌ Exceptions to laws
-
-**All learning is subordinate to the Constitution.**
-
----
-
-## Enforcement Tools
-
-### Automated Enforcement
-
-Use validation scripts when available:
-```bash
-# Validate doctrine compliance
-node scripts/validate_doctrine.js <file-path>
-
-# Audit PR for violations
-node scripts/audit_pr.js <pr-branch>
-
-# Check system boundaries
-node scripts/check_boundaries.js <directory>
-```
-
-### Manual Enforcement
-
-Use checklists:
-- `enforcement/checklists/backend-api-review-checklist.md`
-- `enforcement/checklists/chart-component-review-checklist.md`
-- `enforcement/checklists/mobile-gesture-review-checklist.md`
-- `enforcement/checklists/frontend-gesture-review-checklist.md`
-
----
-
-## Final Enforcement Principle
-
-> Agents exist to reduce human load, increase consistency, and surface risks early.
-> 
-> Agents do NOT exist to replace architectural judgment, accelerate unsafe change, or bypass review or law.
-> 
-> **If in doubt — REFUSE.**

package/.agent/skills/governance/resources/LOAD_ORDER.md

@@ -1,82 +0,0 @@
-# CoinPika Doctrine Pack - Load Order
-
-## Progressive Disclosure Model
-
-This skill follows **Progressive Disclosure** to optimize context window usage.
-
-### Load Order (MANDATORY)
-
-1. **SKILL.md + metadata/*** (Always loaded)
-   - Lightweight routing & intent matching
-   - YAML frontmatter for semantic discovery
-   - Quick reference guide
-
-2. **constitution/*** (Load when architectural decisions needed)
-   - `coinpika-master-constitution.md` - Supreme authority
-   - Prime Directives (immutable)
-   - System Laws (non-negotiable)
-   - Learning constraints
-
-3. **doctrines/*** (Load by domain)
-   - `architecture/` - System boundaries & ownership
-   - `backend/` - Data engine & persistence
-   - `data/` - Chart & financial data integrity
-   - `frontend/` - Mobile UX & gestures
-   - `performance/` - Caching & scalability
-   - `commercial/` - Risk & rollback guardrails
-   - `review/` - Code review standards
-   - `learning/` - AI learning constraints
-
-4. **enforcement/*** (Load on-demand)
-   - `checklists/` - Domain-specific review checklists
-   - `agents/` - Agent control protocols
-   - `playbooks/` - Violation response procedures
-
-5. **proposals/*** (Advanced usage only)
-   - Change proposal templates
-   - Constitutional amendment process
-
-### Layering Principle
-
-If a lower layer conflicts with a higher layer, **the higher layer always wins**.
-
-Example precedence:
-```
-constitution/coinpika-master-constitution.md  (HIGHEST)
-  ↓
-doctrines/architecture/coinpika-architecture-doctrine.md
-  ↓
-enforcement/checklists/backend-api-review-checklist.md
-  ↓
-Developer preference  (LOWEST)
-```
-
-## When to Load What
-
-### Scenario: Backend API Changes
-1. Load `SKILL.md` (intent matching)
-2. Load `constitution/coinpika-master-constitution.md` (Laws 1-3)
-3. Load `doctrines/architecture/` (boundary laws)
-4. Load `doctrines/backend/` (data engine rules)
-5. Reference `enforcement/checklists/backend-api-review-checklist.md`
-
-### Scenario: Mobile UI/Gesture Changes
-1. Load `SKILL.md` (intent matching)
-2. Load `constitution/` (Prime Directives)
-3. Load `doctrines/frontend/coinpika-frontend-mobile-doctrine.md`
-4. Load `doctrines/frontend/coinpika-swipe-tabs-doctrine.md`
-5. Reference `enforcement/checklists/mobile-gesture-review-checklist.md`
-
-### Scenario: Chart/Financial Data
-1. Load `SKILL.md` (intent matching)
-2. Load `constitution/` (Laws 2-4: immutability, ephemerality, truthfulness)
-3. Load `doctrines/data/coinpika-chart-data-doctrine.md`
-4. Load `doctrines/backend/` (aggregation rules)
-5. Reference `enforcement/checklists/chart-component-review-checklist.md`
-
-## Optimization Tips
-
-- **Don't preload everything**: Load on-demand based on user intent
-- **Cache constitution**: It's referenced frequently
-- **Use specific doctrines**: Don't load all doctrines, only relevant ones
-- **Checklists last**: Only when performing actual review