
Claude Skills by masharratt
github.com/masharratt**Version:** 1.0.0 **Purpose:** Estimate task complexity and predict iteration requirements for CFN v3
set -euo pipefail SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" DB_PATH="${SCRIPT_DIR}/../cfn-memory-persistence/task_intelligence.db" LOG_FILE="${SCRIPT_DIR}/task_intelligence.log" init_database() { mkdir -p "$(dirname "$DB_PATH")" sqlite3 "$DB_PATH" <<EOF CREATE TABLE IF NOT EXISTS task_classifications ( id INTEGER PRIMARY KEY AUTOINCREMENT, task_hash TEXT UNIQUE, description TEXT, category TEXT, subcategories TEXT, recommended_agents TEXT, confidence REAL, created_at DATETIME ...
Dynamically add specialist agents to existing Loop 3 team based on recurring feedback themes. - Preserve existing team composition - Add specialists without removing current agents - Match specialist to specific feedback themes - Security Specialist - Performance Engineer - Testing Expert - Architecture Consultant - Domain-Specific Experts ```bash ./recommend-specialist.sh \ --current-loop3 "backend-dev,coder" \ --feedback-themes "security,authentication,jwt" \ --r
Classify tasks, initialize structured configs with scope boundaries, decompose complex tasks
Test execution, running, and webapp testing for CFN
**Version:** 1.0.0 **Status:** Production **Purpose:** Unified test execution with benchmarking and regression detection ---
**Version:** 1.0.0 **Purpose:** Visual regression testing with screenshot capture, comparison, and baseline management **Integration:** Playwright + SQLite + Redis coordination ---
Agent interaction capture, logging, and analysis with memory tracking and security (Rust implementation). Use when you need to capture and analyze agent interactions, track tool usage and performance metrics, query execution history, or export audit trails for compliance.
Reusable bash utility functions for CFN Loop - logging, error handling, retry, file operations. Use when you need structured logging, atomic file operations, retry logic with exponential backoff, or standardized error handling in bash scripts.
./execute.sh validate-json --file deliverables.json --schema schema.json ./execute.sh calculate-deliverable-confidence --deliverables ./artifacts/ ./execute.sh run-instrumented --command "npm test" --output-dir ./test-results/
**Version:** 1.0.0 **Purpose:** Domain-specific validation criteria for CFN Loop v3
do { implement → screenshot → analyze_image → video → analyze_video → score } while (score < 85%)
**Audit Date:** 2025-12-08 **Auditor:** Code Review Agent **Skill Version:** 1.0.0 **Skill Location:** `.claude/skills/cfn-sprint-execution/`