Loading...
Loading...
Found 131 Skills
Autonomously deep-scan entire codebase line-by-line, understand architecture and patterns, then systematically transform it to production-grade, corporate-level professional quality with optimizations
Dead code & legacy audit worker (L3). Checks unreachable code, unused imports/variables/functions, commented-out code, backward compatibility shims, deprecated patterns. Returns findings.
Execute a complete, deterministic, read-only repository audit and produce a single `improvements.md` action plan with traceable findings (file + lines), severity, category, impact, and high-level fixes. Use when users ask for full code audits, security/performance/architecture reviews, file-by-file analysis, or technical debt mapping without modifying project files.
Audit OpenCode configuration quality, safety, and operability with a 100-point rubric and concrete remediations.
Audit rapidly generated or AI-produced code for structural flaws, fragility, and production risks.
Detect hardcoded values, magic numbers, and leaked secrets. TRIGGERS - hardcode audit, magic numbers, PLR2004, secret scanning.
Performs comprehensive codebase analysis covering architecture, code quality, security, performance, testing, and maintainability. Use when user wants to audit code quality, identify technical debt, find security issues, assess test coverage, or get a codebase health check.
Compare a paper's claims against its public codebase. Use when the user asks to audit a paper, check code-claim consistency, verify reproducibility of a specific paper, or find mismatches between a paper and its implementation.
Forensic audit of the user's recent Claude Code sessions to surface step-change workflow improvements — not marginal ones. Use when the user asks to "audit my Claude Code sessions", "analyze how I use Claude Code", "find patterns in my usage", "improve my Claude Code workflow", "review my sessions", "find leverage in my setup", or wants to understand where their Claude Code setup is leaking time. Samples dozens of real transcripts, extracts quantitative signal via scripts, uses parallel subagents for deep reads, then synthesizes into a short prioritized report with drafted implementations (new skills, CLAUDE.md rules, hooks, settings diffs) that the user can install directly. Trigger even when the user doesn't say the word "audit" — if they're asking about improving or reviewing their Claude Code habits at scale, use this skill.
PHP Web source code CRLF/response splitting audit tool. Identifies user input that enters HTTP response headers, analyzes filtering and encoding of newlines/control characters, and outputs severity ratings, PoCs and fix suggestions (omission is prohibited).
A general skill for performing security reviews and auditing codebases for vulnerabilities. ALWAYS run this at the end of each task.
Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.