Claude Skills by a-ariff

Complete methodology for preventing AI hallucinations. Use when accuracy is critical and you need Claude to verify before claiming, cite before asserting, and admit uncertainty instead of guessing.

Forces every code-related claim to include file:line citations. No citation means the claim must be verified or removed. Use when building documentation, writing code reviews, or any output that others will rely on.

Assign confidence scores (0-100) to every claim in a response. Helps users understand which parts are verified facts and which are educated guesses. Use when the user needs to know how much to trust each part of the answer.

Forces Claude to extract exact quotes from files before making claims about them. Prevents hallucinations by grounding every statement in actual text from the codebase. Use when working with large files or unfamiliar code.

Verify every claim from multiple independent angles -- code, docs, tests, git history. Use when you need high confidence that something is correct before acting on it.

Multi-angle review of responses before delivery. Audits from 4 perspectives -- factual accuracy, logical consistency, completeness, and safety. Use for high-stakes responses where errors have real consequences.

Ensure every factual claim in a response is backed by verifiable evidence from the codebase, documentation, or external sources. Use when preparing technical documentation, code reviews, or any output where accuracy is non-negotiable.

Detects when Claude is uncertain but presenting answers confidently. Teaches Claude to recognize and communicate uncertainty clearly instead of masking it with confident language.

Canvas API Connection Skill

Handles Git operations with human-style commits (no AI markers). Use when user mentions git, commits, committing code, pushing changes, or wants natural developer-style commit messages. Never includes AI attribution or automated markers.

Use this skill when asked about "hooks", "PreToolUse", "PostToolUse", "SessionStart", "hook events", "validate tool use", "block commands", "add context on session start", or implementing event-driven automation.

Analyzes pull requests for quality, completeness, and potential issues. Use when reviewing PRs, checking code changes, or ensuring PR quality before merge.

Helps refactor code for better structure, readability, and maintainability. Use when cleaning up code, improving design, or removing technical debt.

Trace bugs backward to their origin, not just symptoms

Scans code for security vulnerabilities and suggests fixes. Use when checking for security issues, validating input handling, or performing security audits.

Use fresh agents for focused subtasks to avoid context pollution

Provides systematic debugging methodology to identify and fix bugs efficiently. Use when user encounters bugs, errors, or unexpected behavior and needs structured debugging approach.

Structured approach to finding and fixing bugs

Guides test-driven development workflow with red-green-refactor cycles. Use when user wants to practice TDD, write tests first, or needs help with test-first development approach.

Writes comprehensive unit, integration, and end-to-end tests. Use when user needs help writing tests, improving test coverage, or creating test suites.

Core skill activation protocol - establishes mandatory workflows for finding and applying skills before any task

Never claim completion without fresh verification evidence

Dispatch to right technique when you hit a wall

Create detailed implementation plans with bite-sized tasks