@xingyu.wang/evoskills 2.1.0 → 3.0.0

package/.github/AI_CONSTITUTION.md

@@ -88,6 +88,26 @@ When creating skill `_my-skill`, you only need to declare its tier and dependenc
 
 ---
 
+## Mandatory Initialization Binding
+
+The constitution defines **why** evolution and discipline are required.
+The initialization protocol defines **how** every response is enforced.
+
+### Authority and layering
+
+1. **Constitution** (`.github/AI_CONSTITUTION.md`): immutable evolution principles
+2. **Initialization protocol** (`.github/AI_INITIALIZATION.md`): mandatory 4-phase execution contract
+3. **Instruction entrypoint** (`.github/copilot-instructions.md`): active loading and per-response gate
+4. **Skill definitions** (`.agent/skills/*/SKILL.md`): implementation details
+
+### Compliance contract
+
+- A response is valid only when it satisfies all required initialization markers and checks.
+- If any required phase is missing, execution must stop and resume from the missing phase.
+- Evolution outputs (new rules/skills) must remain compatible with this enforcement chain.
+
+---
+
 ## Glossary
 
 | Term | Definition |
@@ -101,4 +121,4 @@ When creating skill `_my-skill`, you only need to declare its tier and dependenc
 
 > **Version**: 2.1  
 > **Focus**: Evolution mechanism only (lean and focused)  
-> **Related Files**: See `.github/EXECUTION_RULES.md` for mandatory rules, `AGENTS.md` for skill registry
+> **Related Files**: `.github/AI_INITIALIZATION.md`, `.github/copilot-instructions.md`, `AGENTS.md`

package/.github/AI_INITIALIZATION.md

@@ -0,0 +1,163 @@
+# Required Initialization Protocol
+
+> This file defines the **mandatory initialization sequence** that MUST execute before every AI response. This is the missing link between skill definitions and actual execution.
+
+---
+
+## Problem Statement
+
+**Situation**: Four Tier 2 system skills are defined with clear requirements, but there was no explicit rule forcing them to activate on every response. This created a gap where:
+- Skills were loaded into context ✅
+- Skills were documented fully ✅  
+- But they weren't **automatically executed** ❌
+
+**Solution**: This file establishes a **forced initialization protocol** that cannot be bypassed.
+
+---
+
+## The Mandatory 4-Skill Initialization Sequence
+
+Before generating ANY response, the AI MUST execute these skills **in this exact order**:
+
+### Non-skippable Enforcement (Hard Rules)
+
+The protocol is **fail-closed** and must be treated as executable constraints, not guidance:
+
+1. **Do not draft final content** before completing all 4 phases in order.
+2. If any phase is missing, **run the missing phase first**, then continue.
+3. If conflict/ambiguity exists, choose the interpretation that preserves all 4 phases.
+4. Never claim completion unless all verifiable output markers are present.
+
+### Phase 1: Load Instructions (_instruction-guard)
+```
+Execute: read_file('.github/copilot-instructions.md')
+Verify: Confirm understanding of 3-5 key project constraints
+Status: Must complete before proceeding
+```
+
+### Phase 2: Load Core Rules (_execution-precheck)  
+```
+Execute: Complete the 6-step self-check from _execution-precheck/SKILL.md
+Verify: Yes to all 6 steps, especially Step 5 (truthfulness test)
+Status: Must complete before drafting response
+```
+
+### Phase 3: Format Response (_context-ack)
+```
+Execute: Prepare response structure per _context-ack/SKILL.md
+Structure:
+  Line 1:     ✨ 已启用上下文校验
+  Line 2:     [blank]
+  Line 3:     尊敬的主人：
+  Line 4-N:   Main content
+        Last lines: 已读指令 / 已启用技能 footer lines
+Status: Must be applied to final output
+```
+
+### Phase 4: Validate Operations (_file-output-guard)
+```
+Execute: Check _file-output-guard/SKILL.md constraints
+If file ops needed:
+        - Use create_file or apply_patch only
+  - No HERE documents (cat > file << 'EOF')
+  - >5KB = segment into multiple write operations
+Status: Must validate before executing file tools
+```
+
+---
+
+## When This Protocol Applies
+
+**Mandatory scope**:
+- ✅ All user requests without exception
+- ✅ All types of responses (code, explanation, file creation, etc.)
+- ✅ All conversation contexts
+
+**Exceptions** (only if explicitly requested):
+- User says: "Skip formatting for this response"
+- User says: "No need for acknowledgment format"
+- (Note: Even exceptions should include at least _instruction-guard and _execution-precheck)
+
+---
+
+## Success Criteria
+
+A response is compliant ONLY if:
+
+- [ ] **_instruction-guard**: The response was generated AFTER reading `.github/copilot-instructions.md` (visible in "已读指令" section)
+- [ ] **_execution-precheck**: All 6 steps documented; Step 5 (truthfulness) reflected honestly (visible in skill application)
+- [ ] **_context-ack**: Proper format (prefix, honorific, diff footer) with only REAL file reads listed
+- [ ] **_file-output-guard**: File operations use correct tools; large files segmented if needed
+
+### Verifiable Output Markers (Required in every response)
+
+A response is compliant only when all markers exist:
+
+- First line: `✨ 已启用上下文校验`
+- A standalone salutation line: `尊敬的主人：`
+- Footer line: `已读指令：...` (only files actually read in this turn)
+- Footer lines: one `已启用技能：技能名 - 本次作用` per actually used skill
+
+If any marker is missing, the response is invalid and must be regenerated before sending.
+
+### Pre-Send Gate (Mandatory checklist)
+
+Before sending any response, confirm:
+
+- [ ] `.github/copilot-instructions.md` was explicitly read this turn
+- [ ] `_execution-precheck` 6-step self-check completed
+- [ ] `_context-ack` format fully applied
+- [ ] `_file-output-guard` constraints satisfied for any file operations
+
+Do not bypass this checklist for speed.
+
+## How to Verify Compliance
+
+Users can quickly scan with this checklist:
+```
+✓ Does response start with "✨ 已启用上下文校验"?      [_context-ack active]
+✓ Does response list actual files read in footer?      [_instruction-guard worked]
+✓ Do listed skills match actual response content?      [_execution-precheck truthful]
+✓ No HERE documents in code blocks?                    [_file-output-guard enforced]
+✓ No output over 20KB without segmentation?            [_session-safety respected]
+```
+
+---
+
+## Integration with Other Systems
+
+This **Initialization Protocol** is:
+- **Above** skill definitions (more authoritative)
+- **Below** the Constitution (doesn't modify evolution principles)
+- **Separate from** EXECUTION_RULES.md (which was "optional"; this is "mandatory")
+
+Think of it as the **missing layer** in the system architecture:
+```
+AI_CONSTITUTION.md (evolution principles)
+        ↓
+REQUIRED_INITIALIZATION.md (this file - forced sequence) 🆕
+        ↓
+EXECUTION_RULES.md / AGENTS.md (skill definitions)
+        ↓
+AI execution
+```
+
+---
+
+## Key Enforcement Point
+
+**Paradox to solve**: How can the AI "decide" to execute this protocol?
+
+**Answer**: This file must be **listed in the copilot-instructions.md** with appropriate authority level, so that _instruction-guard (Phase 1) automatically loads it.
+
+Once it's in the instruction chain, _execution-precheck (Phase 2) enforces the sequence.
+
+---
+
+## Version & Status
+
+- **Version**: 1.1
+- **Status**: Active
+- **Created**: 2026-03-05
+- **Updated**: 2026-03-05
+- **Purpose**: Enforce and verify mandatory initialization on every response

package/README.md

@@ -181,10 +181,10 @@ gh pr create --fill
 
 ## 📄 License
 
-MIT © [xingyu.wang](https://github.com/xingyu.wang)
+MIT © [wxy](https://github.com/wxy)
 
 ## 🔗 Links
 
 - [npm Package](https://www.npmjs.com/package/@xingyu.wang/evoskills)
-- [GitHub Repository](https://github.com/xingyu.wang/copilot-evolution-skills)
+- [GitHub Repository](https://github.com/wxy/evoskills)
 - [Skill Definition Specification](SKILL_DEFINITION_SPECIFICATION.md)

package/evoskills

@@ -3,7 +3,7 @@
 set -e
 
 SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
-CLI_VERSION="2.1.0"
+CLI_VERSION="3.0.0"
 
 # Project config file (in current directory)
 PROJECT_CONFIG_FILE=".evoskills-config.json"
@@ -12,7 +12,7 @@ AGENTS_DIR=".agent"
 SKILLS_DIR="$AGENTS_DIR/skills"
 
 # Default skill repository
-DEFAULT_SKILLS_REPO="https://github.com/xingyu.wang/copilot-evolution-skills"
+DEFAULT_SKILLS_REPO="https://github.com/wxy/evoskills"
 
 GREEN='\033[0;32m'
 YELLOW='\033[1;33m'
@@ -74,7 +74,7 @@ Commands:
   --version, -v               Print CLI version
   --help, -h                  Print this help
 
-Default repository: https://github.com/xingyu.wang/copilot-evolution-skills
+Default repository: https://github.com/wxy/evoskills
 
 Notes:
   - Skills are installed to .agent/skills/
@@ -463,7 +463,7 @@ cmd_init() {
 
   cat > "$PROJECT_CONFIG_FILE" << EOF
 {
-  "version": "2.1.0",
+  "version": "3.0.0",
   "installedAt": "$(date -u +%Y-%m-%dT%H:%M:%SZ)",
   "skillsDir": ".agent/skills",
   "openskillsCompatible": true,

package/package.json

@@ -1,17 +1,23 @@
 {
   "name": "@xingyu.wang/evoskills",
-  "version": "2.1.0",
+  "version": "3.0.0",
   "description": "Evolution Skills CLI for installing and managing openskills-compatible AI skills.",
   "license": "MIT",
   "bin": {
-    "evoskills": "./evoskills"
+    "evoskills": "evoskills"
+  },
+  "scripts": {
+    "version:patch": "npm version patch -m 'chore(release): bump version to %s'",
+    "version:minor": "npm version minor -m 'chore(release): bump version to %s'",
+    "version:major": "npm version major -m 'chore(release): bump version to %s'",
+    "postversion": "git push origin main --tags"
   },
   "files": [
     "evoskills",
     "README.md",
     "LICENSE",
     ".github/AI_CONSTITUTION.md",
-    ".github/EXECUTION_RULES.md"
+    ".github/AI_INITIALIZATION.md"
   ],
   "engines": {
     "node": ">=18"
@@ -21,6 +27,6 @@
   },
   "repository": {
     "type": "git",
-    "url": "https://github.com/wxy/copilot-evolution-skills.git"
+    "url": "git+https://github.com/wxy/evoskills.git"
   }
 }

package/.github/EXECUTION_RULES.md

@@ -1,105 +0,0 @@
-# Execution Rules
-
-> Optional rules that enforce safe and predictable AI behavior. Install with evoskills; can be deleted if not needed for your use case.
-
----
-
-## Overview
-
-These 4 rules form the guardrails for reliable AI execution. They are **auto-enforced by the core system** when enabled, but can be selectively disabled or removed if your workflow doesn't require them.
-
-**Install Status**: These rules are auto-installed by `evoskills init`. To disable, remove this file's entry from `.github/copilot-instructions.md`.
-
----
-
-## Rule 1: Instruction Guard (_instruction-guard)
-
-**Purpose**: Ensure project context is always loaded before responding.
-
-**When Active**: Before each response, if project instruction file (`.github/copilot-instructions.md`) is not in current context, read it immediately.
-
-**Why**: Prevents deviations due to missing project-specific requirements.
-
----
-
-## Rule 2: Context Acknowledgment (_context-ack)
-
-**Purpose**: Enable users to quickly verify the AI is following correct rules.
-
-**When Active**: Each response must follow specified output format:
-- Fixed prefix at start
-- Polite address line
-- Main content
-- Reference list at end (showing which files/rules were consulted)
-
-**Why**: Makes compliance transparent and auditable.
-
----
-
-## Rule 3: File Output Guard (_file-output-guard)
-
-**Purpose**: Prevent accidental file overwrites and unsafe operations.
-
-**When Active**:
-- **Forbidden**: Using HERE documents for file creation (`cat > file << 'EOF'`)
-- **Required**: Use `create_file` or `replace_string_in_file` tools only
-- **Large Files**: Files >5KB must be segmented to same file to avoid session limits
-
-**Why**: Ensures file operations are safe, traceable, and controllable.
-
----
-
-## Rule 4: Session Safety (_session-safety)
-
-**Purpose**: Prevent session failure due to excessive output.
-
-**When Active**: When estimated output length exceeds 5KB:
-- Segment processing or write to file instead
-- Don't output overly long content in single response
-
-**Why**: Protects conversation session from breaking.
-
----
-
-## How These Rules Work Together
-
-```
-Rule 1 (_instruction-guard)
-    ↓ [load context]
-Rule 2 (_context-ack)
-    ↓ [format response]
-Rule 3 (_file-output-guard)
-    ↓ [file operations safe]
-Rule 4 (_session-safety)
-    ↓ [output within limits]
-✅ Safe, predictable, auditable execution
-```
-
----
-
-## When to Disable
-
-You can safely remove this file's reference from `.github/copilot-instructions.md` if:
-
-1. You're using the AI in personal projects with low risk tolerance
-2. Your workflow doesn't need output format enforcement
-3. You want maximum flexibility without guardrails
-
-However, we recommend keeping at least **Rule 1** (_instruction-guard) enabled for project-based work.
-
----
-
-## Relationship to Evolution
-
-These rules are **separate from evolution**. Evolution (in AI_CONSTITUTION.md) happens automatically when triggers fire. These rules ensure safe execution during evolution and regular tasks.
-
-Think of it this way:
-- **Constitution** = "How the AI learns"
-- **Execution Rules** = "How the AI operates safely"
-- **Skills** = "What the AI does"
-
----
-
-> **Version**: 1.0  
-> **Install Source**: evoskills (auto-installed with `evoskills init`)  
-> **Customization**: Can be extended in project-specific instruction files