pensive

Evaluate public API surfaces against guidelines and exemplars.

Principal-level architecture assessment against ADRs and design patterns.

Systematic bug detection with language-specific expertise.

Run a detailed review using intelligent skill selection based on codebase analysis.

Audit Makefiles for best practices and portability.

Intensive mathematical analysis for numerical stability and correctness.

Analyze and improve living code quality across 6 dimensions

Expert-level Rust audits for safety and correctness.

Audit shell scripts for correctness, safety, and portability.

View recent skill executions with full context and error details for review.

Analyze skill execution metrics and identify unstable or underperforming skills using continual learning analysis.

Evaluate and upgrade test suites with TDD/BDD rigor.

Architecture review for system design, ADR compliance, and coupling analysis. Use for major refactors.

Orchestrate code quality refinement — analyze living code for duplication, algorithmic inefficiency, clean code violations, and architectural misfit. Generate actionable refactoring plans with before/after examples. Use PROACTIVELY for: code quality improvement, refactoring sprints, anti-slop remediation PRE-INVOCATION CHECK (parent must verify BEFORE calling): - "Fix this one function"? -> Parent refactors directly - "Rename this variable"? -> Parent does it - "Run linter"? -> Parent runs ruff/eslint ONLY invoke for: multi-file quality analysis, systematic refactoring, codebase-wide duplication scan, or architectural alignment review.

Expert code review agent specializing in bug detection, API analysis, test quality, and detailed code audits. Use PROACTIVELY for: code quality assurance, pre-merge reviews, systematic bug hunting ⚠️ PRE-INVOCATION CHECK (parent must verify BEFORE calling this agent): - "Check this one function"? → Parent reads and reviews directly - "Is syntax correct"? → Parent or linter checks - "Run lint"? → Parent runs `ruff check` or `eslint` - Trivial style question? → Parent answers directly ONLY invoke this agent for: multi-file reviews, security audits, test coverage analysis, full PR reviews, or architecture/API consistency reviews.

Rust security audits for ownership, unsafe code, concurrency, and dependency scanning.

Use this skill for API surface evaluation and design review. Use when reviewing API design, auditing consistency, governing documentation, researching API exemplars. Do not use when architecture review - use architecture-review. DO NOT use when: implementation bugs - use bug-review.

Use this skill for architecture assessment and compliance. Use when reviewing architecture decisions, auditing ADR compliance, analyzing coupling, validating design principles. Do not use when selecting architecture paradigms - use archetypes skills. DO NOT use when: API surface review - use api-review.

Use this skill for systematic bug hunting with evidence trails. Use when deep bug hunting needed, documenting defects, verifying fixes, systematic debugging required. Do not use when test coverage audit - use test-review instead. DO NOT use when: architecture issues - use architecture-review.

Analyze and improve living code quality: duplication, algorithmic efficiency, clean code principles, architectural fit, anti-slop patterns, and error handling robustness. Use when improving code quality, reducing AI slop, refactoring for clarity, optimizing algorithms, applying clean code principles. Do not use when removing dead/unused code (use conserve:bloat-detector). reviewing for bugs (use pensive:bug-review). selecting architecture paradigms (use archetypes skills). This skill actively improves living code, complementing bloat detection (dead code removal) with quality refinement (living code improvement).

Use this skill for Makefile audit and optimization. Use when auditing Makefiles, reviewing build system, checking portability, eliminating recipe duplication. Do not use when creating new Makefiles - use abstract:make-dogfood. DO NOT use when: architecture review - use architecture-review.

Use this skill for mathematical code verification. Use when reviewing math-heavy code, verifying algorithm correctness, checking numerical stability, aligning with mathematical standards. Do not use when general algorithm review - use architecture-review. DO NOT use when: performance optimization - use parseltongue:python-performance.

Use this skill for Rust-specific code audits. Use when reviewing Rust code, auditing unsafe blocks, analyzing ownership patterns, scanning Cargo dependencies for security. Do not use when general code review without Rust - use unified-review. DO NOT use when: performance profiling - use parseltongue:python-performance pattern.

Guidelines from the NASA Power of 10 rules for writing robust, verifiable code. Adapted for general software development with context-appropriate rigor. Use when writing critical code paths, reviewing for robustness, improving code quality. Do not use as rigid requirements for all code - match rigor to consequence.

Audit shell scripts for correctness, portability, and common pitfalls.

Use this skill for test suite evaluation and quality assessment. Use when auditing test suites, analyzing coverage gaps, improving test quality, evaluating TDD/BDD compliance. Do not use when writing new tests - use parseltongue:python-testing. DO NOT use when: updating existing tests - use sanctum:test-updates.

Audit a codebase using a three-tier escalation model. Tier 1 analyzes git history (fast, bounded). Tier 2 deep-dives into flagged areas (sequential). Tier 3 reviews the full codebase (requires approval). Always starts at Tier 1 unless explicitly overridden.

Use this skill when orchestrating multiple review types. Use when general review needed without knowing which specific skill applies, full multi-domain review desired, integrated reporting needed. Do not use when specific review type known - use bug-review, test-review, etc. DO NOT use when: architecture-only focus - use architecture-review.