@pratikpsl/agent-skills 1.0.0 → 1.1.0

package/README.md

@@ -80,7 +80,7 @@ Options:
 | `default` | `templates/default/` | Universal single-file agent instructions, cross-OS hardlinked |
 | `dotnet` | `templates/dotnet/` | .NET/C# skills, architecture & developer agents, memory |
 | `react` | `templates/react/` | React & TypeScript skills, frontend testing, developer agent |
-| `shared` | `templates/shared/` | Base operating contract, core skills (standards, security), review agents |
+| `shared` | `templates/shared/` | Base operating contract, core skills (principles, standards, security), review agents |
 
 ---
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@pratikpsl/agent-skills",
   "type": "module",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "description": "CLI to scaffold and manage AI agent skills across projects — like shadcn/ui, but for Cursor, Claude, Codex, Copilot, Antigravity, and more",
   "bin": {
     "agent-skills": "dist/bin/agent-skills.js"
@@ -47,7 +47,7 @@
     "build": "tsc",
     "test": "vitest run",
     "test:watch": "vitest",
-    "dry-run": "npm run build && npm pack --dry-run"
+    "dry-run": "bun run build && bun pm pack --dry-run"
   },
   "dependencies": {
     "commander": "^15.0.0"

package/templates/shared/AgentSkills/agents/reviewer.agent.md

@@ -5,22 +5,23 @@ description: Code review, correctness, security, and standards verification.
 
 # Code Reviewer Guidance
 
-## Review Checklist
+Universal review guidance for AI agents and human reviewers across all stacks. Security, standards, and core principles remain invariant across frameworks.
 
-### Scope & Minimality
-- [ ] Minimal diff that directly satisfies the request without unrelated edits or speculative additions (YAGNI).
-- [ ] No dead code, debug logging, commented-out code, or unused imports/variables left behind.
+## Core References
+- **Principles**: Adhere strictly to `AgentSkills/skills/principles/SKILL.md`.
+- **Standards**: Adhere strictly to `AgentSkills/skills/standards/SKILL.md`.
+- **Security**: Adhere strictly to `AgentSkills/skills/security/SKILL.md`.
 
-### Quality & Standards
-- [ ] Functions stay within 50 lines, nesting depth at most 2 levels, and clean signatures ($\le 4$ params).
-- [ ] Follows established codebase naming conventions, architectural boundaries, and error patterns.
-- [ ] No magic numbers or strings (constants/enums used appropriately).
+## Verification & Automated Checks
+- [ ] **Clean Build**
+- [ ] **Zero Lint Errors**
+- [ ] **Tests Pass**
+- [ ] **Test Robustness**
 
-### Security & Reliability
-- [ ] No hardcoded credentials, tokens, passwords, or exposed sensitive user PII.
-- [ ] Input validation applied at boundaries; queries parameterized against injection.
-- [ ] Concurrency and async flows are free of race conditions and deadlocks.
+## Standards & Skill Compliance
+- [ ] **Principles**: `AgentSkills/skills/principles/SKILL.md`
+- [ ] **Standards**: `AgentSkills/skills/standards/SKILL.md`
+- [ ] **Security**: `AgentSkills/skills/security/SKILL.md`
 
-### Verification & Tests
-- [ ] Clean build with zero errors and warnings.
-- [ ] Tests pass and verify both success scenarios and failure/edge-case paths.
+## Memory & Learning Loop
+- [ ] **Agent Memory**: `AgentSkills/memory/index.md`

package/templates/shared/AgentSkills/skills/principles/SKILL.md

@@ -0,0 +1,31 @@
+---
+name: principles
+description: Core software engineering principles, simplicity ladder, surgical changes, and standards.
+---
+
+# Core Principles
+
+Foundational software engineering principles and decision rules for AI agents and human contributors.
+
+## The Simplicity Ladder
+Before writing any code, stop at the first rung that holds:
+
+1. **Does this need to be built at all?** (YAGNI)
+2. **Does it already exist in this codebase?** Reuse the helper, util, or pattern that is already here; do not rewrite it.
+3. **Does the standard library already do this?** Use it.
+4. **Does a native platform feature cover it?** Use it.
+5. **Does an already-installed dependency solve it?** Use it.
+6. **Can this be one line and simple?** Make it one.
+7. **Only then:** write the minimum code that works.
+
+The ladder runs after you understand the problem, not instead of it: read the task and the code it touches, trace the real flow end-to-end, then climb.
+
+## Root Cause Over Symptom
+Bug fix = root cause, not symptom. A bug report names a symptom. Grep every caller of the function you touch and fix the shared function once — one guard there is a smaller diff than one per caller, and patching only the path the ticket names leaves sibling callers still broken.
+
+## Foundational Principles
+- **Think Before Coding**: Thoroughly understand requirements. If ambiguous, ask before guessing.
+- **Surgical Changes**: Make the smallest change that satisfies the request; touch only what is explicitly required.
+- **Simplicity First (KISS / YAGNI)**: Favor simple, clear, maintainable solutions over clever abstractions. Do not add unrequested features.
+- **Zero-Error Builds**: Every change must compile cleanly and pass existing and newly added tests.
+- **Standards & Security**: Adhere strictly to `AgentSkills/skills/standards/SKILL.md` and `AgentSkills/skills/security/SKILL.md`.

package/templates/shared/entry-points/instructions.md

@@ -1,24 +1,28 @@
-# Agent Instructions
+# Agent & Developer Instructions
+
+> Operating instructions and engineering guidelines for AI agents and human contributors.
 
 ## Operating Contract
-Always follow `AgentSkills/OPERATING.md` before making changes.
+Always follow `AgentSkills/OPERATING.md` before making changes. Review relevant agent personas in `AgentSkills/agents/` and skills in `AgentSkills/skills/`.
 
 ## Goal
-Implement the requested change with production-quality code, preserving existing behavior and
-minimizing the diff, following the project's own architecture and conventions.
+Implement requested changes with production-quality code, preserving existing behavior and
+minimizing the diff, following the project's own architecture, standards, and conventions.
 
 ## Core Principles
+- **Core Principles**: Adhere strictly to `AgentSkills/skills/principles/SKILL.md`.
+- **Standards**: Adhere strictly to `AgentSkills/skills/standards/SKILL.md`.
+- **Security**: Adhere strictly to `AgentSkills/skills/security/SKILL.md`.
 - **Think Before Coding**: Thoroughly understand requirements. If ambiguous, ask before guessing.
 - **Surgical Changes**: Make the smallest change that satisfies the request; touch only what is explicitly required.
 - **Simplicity First (KISS / YAGNI)**: Favor simple, clear, maintainable solutions over clever abstractions. Do not add unrequested features.
 - **Zero-Error Builds**: Every change must compile cleanly and pass existing and newly added tests.
-- **Standards & Security**: Adhere strictly to `AgentSkills/skills/standards/SKILL.md` and `AgentSkills/skills/security/SKILL.md`.
 
 ## Definition of Done
 - Builds cleanly and all tests pass without errors or warnings.
 - No debug code, dead code, unused imports, or temporary files left behind.
 - Changes are minimal, focused, covered by tests, and easy to review.
 
-## Agent Memory
+## Agent & Contributor Memory
 - Read `AgentSkills/memory/index.md` at the start of every task (create if missing); load only relevant domain lessons.
-- When a mistake is corrected or a durable rule discovered, record an actionable lesson in `AgentSkills/memory/lessons/<domain>.md` (create if missing) and update `index.md`.
+- When a mistake is corrected or a durable rule discovered, record an actionable lesson in `AgentSkills/memory/lessons/<domain>.md` (create if missing) and update `index.md`.