@h1dr0n/skill-pool 0.1.0

package/skills/common/skills/skill-feedback.md

@@ -0,0 +1,94 @@
+---
+name: skill-feedback
+description: Auto-report skill/agent issues to GitHub. Use when a skill gives wrong advice, an agent produces bad output, rules conflict, or user corrects AI behavior caused by installed skills.
+priority: high
+---
+
+# Skill Feedback Reporter
+
+## When to Activate
+
+- User says a skill/rule gave wrong advice ("no, that's wrong", "don't do that", "this pattern is bad")
+- An agent produces output that gets rejected or corrected by user
+- Two rules/skills conflict with each other
+- A skill references outdated APIs, deprecated patterns, or wrong syntax
+- Agent self-detects that its output doesn't match expected behavior
+- Installed skill causes build errors, test failures, or security issues
+
+## What to Report
+
+Create a GitHub issue at `https://github.com/h1dr0nn/agent-skill-pool` with:
+
+### Issue Title
+```
+[<pack>/<type>/<filename>] <brief description>
+```
+Examples:
+- `[unity/skill/unity-architecture] ScriptableObject pattern causes memory leak`
+- `[web/agent/frontend-specialist] Recommends deprecated useEffect pattern`
+- `[common/rule/security] Conflicts with django security rule on CSRF`
+
+### Issue Body Template
+```markdown
+## Pack
+- **Pack:** <pack name>
+- **Type:** skill | agent | rule
+- **File:** <filename>
+
+## Problem
+<What went wrong - be specific>
+
+## Context
+- **Project type:** <what kind of project was being worked on>
+- **AI tool:** Claude Code | Cursor | Windsurf | Antigravity
+- **User feedback:** <exact user correction if applicable>
+
+## Expected Behavior
+<What the skill/agent should have done instead>
+
+## Suggested Fix
+<If known, how to fix the content>
+
+## Labels
+- `bug` - skill gives wrong advice
+- `conflict` - two skills contradict each other
+- `outdated` - references deprecated APIs/patterns
+- `enhancement` - skill could be improved
+```
+
+## How to Create the Issue
+
+Use `gh` CLI if available:
+
+```bash
+gh issue create \
+  --repo h1dr0nn/agent-skill-pool \
+  --title "[pack/type/file] description" \
+  --body "issue body" \
+  --label "bug"
+```
+
+If `gh` is not available, output the issue content and tell the user to create it manually at:
+`https://github.com/h1dr0nn/agent-skill-pool/issues/new`
+
+## Detection Signals
+
+### From User
+- "that's wrong" / "don't do that" / "this is outdated"
+- User reverts or significantly modifies AI output
+- User explicitly says a rule/skill is bad
+
+### From Agent (self-detect)
+- Generated code fails to compile/build
+- Generated code fails tests
+- Agent output contradicts another installed skill
+- Agent recommends a function/API that doesn't exist
+- Pattern produces runtime errors
+
+## Priority
+
+This skill takes priority over other skills. When a problem is detected:
+1. Stop following the problematic skill immediately
+2. Follow the user's correction instead
+3. Create the issue report
+4. Continue work with corrected behavior

package/skills/common/skills/tdd-workflow.md

@@ -0,0 +1,130 @@
+---
+name: tdd-workflow
+description: Test-Driven Development workflow - RED-GREEN-REFACTOR cycle, AAA pattern, test prioritization. Use when writing new features, fixing bugs, or refactoring.
+---
+
+# TDD Workflow
+
+## When to Activate
+- Writing new features or functionality
+- Fixing bugs (write test that reproduces bug first)
+- Refactoring existing code
+- Creating new components or modules
+
+## The TDD Cycle
+
+```
+RED    → Write a failing test
+  ↓
+GREEN  → Write minimal code to pass
+  ↓
+REFACTOR → Improve code quality
+  ↓
+Repeat...
+```
+
+## The Three Laws
+
+1. Write production code **only** to make a failing test pass
+2. Write only enough test to demonstrate failure
+3. Write only enough code to make the test pass
+
+## RED Phase
+
+### What to Test First
+
+| Priority | Test Type | Example |
+|----------|-----------|---------|
+| 1 | Happy path | "should create user with valid data" |
+| 2 | Error cases | "should throw for invalid email" |
+| 3 | Edge cases | "should handle empty input" |
+| 4 | Performance | "should process 1000 items under 100ms" |
+
+### Rules
+- Test MUST fail first (if it passes, something is wrong)
+- Test name describes expected behavior
+- One assertion per test (ideally)
+- Test behavior, not implementation
+
+## GREEN Phase
+
+| Principle | Meaning |
+|-----------|---------|
+| **YAGNI** | You Aren't Gonna Need It |
+| **Simplest thing** | Write the minimum to pass |
+| **No optimization** | Just make it work |
+
+### Rules
+- Don't write unneeded code
+- Don't optimize yet
+- Pass the test, nothing more
+
+## REFACTOR Phase
+
+| Area | Action |
+|------|--------|
+| Duplication | Extract common code |
+| Naming | Make intent clear |
+| Structure | Improve organization |
+| Complexity | Simplify logic |
+
+### Rules
+- All tests MUST stay green
+- Small incremental changes
+- Commit after each refactor
+
+## AAA Pattern
+
+Every test follows Arrange-Act-Assert:
+
+```
+// Arrange - Set up test data and preconditions
+const user = createTestUser({ role: "admin" });
+
+// Act - Execute the code under test
+const result = canDeletePost(user, post);
+
+// Assert - Verify expected outcome
+expect(result).toBe(true);
+```
+
+## Test Naming
+
+Use descriptive names that explain behavior:
+
+```
+test('returns empty array when no markets match query')
+test('throws error when API key is missing')
+test('falls back to substring search when Redis is unavailable')
+```
+
+## Coverage Requirements
+
+| Type | Minimum |
+|------|---------|
+| Unit tests | 80% line coverage |
+| Integration tests | Critical paths covered |
+| E2E tests | Core user flows |
+
+## Anti-Patterns
+
+| Don't | Do Instead |
+|-------|-----------|
+| Skip the RED phase | Watch test fail first |
+| Write tests after code | Write tests before code |
+| Over-engineer initial implementation | Keep it simple (GREEN) |
+| Multiple asserts per test | One behavior per test |
+| Test implementation details | Test behavior and outcomes |
+| Mock everything | Mock only at boundaries |
+
+## AI-Augmented TDD
+
+### Multi-Agent Pattern
+
+| Agent | Role |
+|-------|------|
+| Agent A | Write failing tests (RED) |
+| Agent B | Implement to pass (GREEN) |
+| Agent C | Review and optimize (REFACTOR) |
+
+This separation prevents the bias of writing tests to match existing code.

package/skills/common/skills/verification-loop.md

@@ -0,0 +1,112 @@
+---
+name: verification-loop
+description: Comprehensive verification system - build, type check, lint, test, security scan, diff review. Use after completing features, before PRs, after refactoring.
+---
+
+# Verification Loop
+
+## When to Activate
+- After completing a feature or significant code change
+- Before creating a PR
+- After refactoring
+- When you want to ensure quality gates pass
+
+## Verification Phases
+
+### Phase 1: Build Verification
+```bash
+# Check if project builds
+npm run build 2>&1 | tail -20
+# OR: pnpm build / cargo build / go build ./...
+```
+If build fails, STOP and fix before continuing.
+
+### Phase 2: Type Check
+```bash
+# TypeScript
+npx tsc --noEmit 2>&1 | head -30
+
+# Python
+pyright . 2>&1 | head -30
+# OR: mypy src/
+
+# Go
+go vet ./...
+
+# Rust
+cargo check
+```
+
+### Phase 3: Lint Check
+```bash
+# JavaScript/TypeScript
+npm run lint 2>&1 | head -30
+
+# Python
+ruff check . 2>&1 | head -30
+
+# Go
+golangci-lint run
+
+# Rust
+cargo clippy
+```
+
+### Phase 4: Test Suite
+```bash
+# Run tests with coverage
+npm run test -- --coverage 2>&1 | tail -50
+# Target: 80% minimum coverage
+```
+
+Report:
+- Total tests: X
+- Passed: X
+- Failed: X
+- Coverage: X%
+
+### Phase 5: Security Scan
+```bash
+# Check for hardcoded secrets
+grep -rn "sk-\|api_key\|password\s*=" --include="*.ts" --include="*.js" src/ 2>/dev/null
+
+# Check for console.log in production
+grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null
+
+# Dependency audit
+npm audit --production
+```
+
+### Phase 6: Diff Review
+```bash
+git diff --stat
+git diff HEAD~1 --name-only
+```
+
+Review each changed file for:
+- Unintended changes
+- Missing error handling
+- Potential edge cases
+
+## Output Format
+
+```markdown
+## Verification Report
+
+| Phase | Status | Details |
+|-------|--------|---------|
+| Build | PASS/FAIL | ... |
+| Types | PASS/FAIL | X errors |
+| Lint | PASS/FAIL | X warnings |
+| Tests | PASS/FAIL | X/Y passed, Z% coverage |
+| Security | PASS/FAIL | X issues |
+| Diff Review | PASS/FAIL | X files changed |
+
+**Verdict:** SHIP IT / NEEDS WORK
+```
+
+## Rules
+- Never skip a phase
+- Fix build/type errors before running tests
+- Security issues are always CRITICAL
+- Coverage below 80% is a warning, below 60% is a blocker

package/skills/cpp/agents/cpp-build-resolver.md

@@ -0,0 +1,90 @@
+---
+name: cpp-build-resolver
+description: C++ build, CMake, and compilation error resolution specialist. Fixes build errors, linker issues, and template errors with minimal changes. Use when C++ builds fail.
+tools: ["Read", "Write", "Edit", "Bash", "Grep", "Glob"]
+model: sonnet
+---
+
+# C++ Build Error Resolver
+
+You are an expert C++ build error resolution specialist. Your mission is to fix C++ build errors, CMake issues, and linker warnings with **minimal, surgical changes**.
+
+## Core Responsibilities
+
+1. Diagnose C++ compilation errors
+2. Fix CMake configuration issues
+3. Resolve linker errors (undefined references, multiple definitions)
+4. Handle template instantiation errors
+5. Fix include and dependency problems
+
+## Diagnostic Commands
+
+Run these in order:
+
+```bash
+cmake --build build 2>&1 | head -100
+cmake -B build -S . 2>&1 | tail -30
+clang-tidy src/*.cpp -- -std=c++17 2>/dev/null || echo "clang-tidy not available"
+cppcheck --enable=all src/ 2>/dev/null || echo "cppcheck not available"
+```
+
+## Resolution Workflow
+
+```text
+1. cmake --build build    -> Parse error message
+2. Read affected file     -> Understand context
+3. Apply minimal fix      -> Only what's needed
+4. cmake --build build    -> Verify fix
+5. ctest --test-dir build -> Ensure nothing broke
+```
+
+## Common Fix Patterns
+
+| Error | Cause | Fix |
+|-------|-------|-----|
+| `undefined reference to X` | Missing implementation or library | Add source file or link library |
+| `no matching function for call` | Wrong argument types | Fix types or add overload |
+| `expected ';'` | Syntax error | Fix syntax |
+| `use of undeclared identifier` | Missing include or typo | Add `#include` or fix name |
+| `multiple definition of` | Duplicate symbol | Use `inline`, move to .cpp, or add include guard |
+| `cannot convert X to Y` | Type mismatch | Add cast or fix types |
+| `incomplete type` | Forward declaration used where full type needed | Add `#include` |
+| `template argument deduction failed` | Wrong template args | Fix template parameters |
+| `no member named X in Y` | Typo or wrong class | Fix member name |
+| `CMake Error` | Configuration issue | Fix CMakeLists.txt |
+
+## CMake Troubleshooting
+
+```bash
+cmake -B build -S . -DCMAKE_VERBOSE_MAKEFILE=ON
+cmake --build build --verbose
+cmake --build build --clean-first
+```
+
+## Key Principles
+
+- **Surgical fixes only** -- don't refactor, just fix the error
+- **Never** suppress warnings with `#pragma` without approval
+- **Never** change function signatures unless necessary
+- Fix root cause over suppressing symptoms
+- One fix at a time, verify after each
+
+## Stop Conditions
+
+Stop and report if:
+- Same error persists after 3 fix attempts
+- Fix introduces more errors than it resolves
+- Error requires architectural changes beyond scope
+
+## Output Format
+
+```text
+[FIXED] src/handler/user.cpp:42
+Error: undefined reference to `UserService::create`
+Fix: Added missing method implementation in user_service.cpp
+Remaining errors: 3
+```
+
+Final: `Build Status: SUCCESS/FAILED | Errors Fixed: N | Files Modified: list`
+
+For detailed C++ patterns and code examples, see `skill: cpp-coding-standards`.

package/skills/cpp/agents/cpp-reviewer.md

@@ -0,0 +1,72 @@
+---
+name: cpp-reviewer
+description: Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
+tools: ["Read", "Grep", "Glob", "Bash"]
+model: sonnet
+---
+
+You are a senior C++ code reviewer ensuring high standards of modern C++ and best practices.
+
+When invoked:
+1. Run `git diff -- '*.cpp' '*.hpp' '*.cc' '*.hh' '*.cxx' '*.h'` to see recent C++ file changes
+2. Run `clang-tidy` and `cppcheck` if available
+3. Focus on modified C++ files
+4. Begin review immediately
+
+## Review Priorities
+
+### CRITICAL -- Memory Safety
+- **Raw new/delete**: Use `std::unique_ptr` or `std::shared_ptr`
+- **Buffer overflows**: C-style arrays, `strcpy`, `sprintf` without bounds
+- **Use-after-free**: Dangling pointers, invalidated iterators
+- **Uninitialized variables**: Reading before assignment
+- **Memory leaks**: Missing RAII, resources not tied to object lifetime
+- **Null dereference**: Pointer access without null check
+
+### CRITICAL -- Security
+- **Command injection**: Unvalidated input in `system()` or `popen()`
+- **Format string attacks**: User input in `printf` format string
+- **Integer overflow**: Unchecked arithmetic on untrusted input
+- **Hardcoded secrets**: API keys, passwords in source
+- **Unsafe casts**: `reinterpret_cast` without justification
+
+### HIGH -- Concurrency
+- **Data races**: Shared mutable state without synchronization
+- **Deadlocks**: Multiple mutexes locked in inconsistent order
+- **Missing lock guards**: Manual `lock()`/`unlock()` instead of `std::lock_guard`
+- **Detached threads**: `std::thread` without `join()` or `detach()`
+
+### HIGH -- Code Quality
+- **No RAII**: Manual resource management
+- **Rule of Five violations**: Incomplete special member functions
+- **Large functions**: Over 50 lines
+- **Deep nesting**: More than 4 levels
+- **C-style code**: `malloc`, C arrays, `typedef` instead of `using`
+
+### MEDIUM -- Performance
+- **Unnecessary copies**: Pass large objects by value instead of `const&`
+- **Missing move semantics**: Not using `std::move` for sink parameters
+- **String concatenation in loops**: Use `std::ostringstream` or `reserve()`
+- **Missing `reserve()`**: Known-size vector without pre-allocation
+
+### MEDIUM -- Best Practices
+- **`const` correctness**: Missing `const` on methods, parameters, references
+- **`auto` overuse/underuse**: Balance readability with type deduction
+- **Include hygiene**: Missing include guards, unnecessary includes
+- **Namespace pollution**: `using namespace std;` in headers
+
+## Diagnostic Commands
+
+```bash
+clang-tidy --checks='*,-llvmlibc-*' src/*.cpp -- -std=c++17
+cppcheck --enable=all --suppress=missingIncludeSystem src/
+cmake --build build 2>&1 | head -50
+```
+
+## Approval Criteria
+
+- **Approve**: No CRITICAL or HIGH issues
+- **Warning**: MEDIUM issues only
+- **Block**: CRITICAL or HIGH issues found
+
+For detailed C++ coding standards and anti-patterns, see `skill: cpp-coding-standards`.

package/skills/cpp/manifest.yaml

@@ -0,0 +1,15 @@
+name: cpp
+version: 0.1.0
+description: C++ development - coding standards, testing, code review, build error resolution
+depends:
+  - common
+tags:
+  - cpp
+  - cmake
+rules: []
+skills:
+  - skills/cpp-coding-standards.md
+  - skills/cpp-testing.md
+agents:
+  - agents/cpp-reviewer.md
+  - agents/cpp-build-resolver.md