Claude Skills by micsapp

'Create markdown-based behavioral rules preventing unwanted actions.

'Use this skill to quickly understand "what changed and what matters".

'Use this skill for systematic change analysis with risk scoring. Use

'Feature review and prioritization with RICE/WSJF/Kano scoring. Creates

'Enforces "prove before claim" discipline - validation, testing, and

'Use this skill at the BEGINNING of any detailed review for consistent

'Prevents sycophantic reasoning through checklist-based analysis, categorical

'Use this skill BEFORE implementing any new feature. This is NON-NEGOTIABLE

'Consult this skill when formatting final review deliverables. Use when

automatically create GitHub issues for workflow improvements via /fix-workflow.

'Authentication patterns for external services: API keys, OAuth, token

Sanitization guidelines for external content

Recovery protocols for agents encountering broken state: crash recovery, context overflow, merge conflict resolution, and state reconciliation. Provides triage decision trees and step-by-step procedures to restore forward progress without losing work.

'Standardized error handling patterns with classification, recovery,

Consult this skill when building evaluation or scoring systems. Use when

'Git platform detection and cross-platform command mapping for GitHub,

Canonical markdown formatting conventions for diff-friendly documentation. Consult this skill when generating, editing, or reviewing markdown prose. Defines hybrid line wrapping, heading style, list spacing, and link conventions.

'Context-aware progressive module loading with hub-and-spoke pattern

'Standardized pytest configuration for Claude Night Market plugin testing

'Quota tracking, threshold monitoring, and graceful degradation for rate-limited

'Inline risk classification for agent tasks using a 4-tier model. Hybrid

Consult this skill when implementing service registry patterns. Use when

Consult this skill when working on any plugin to apply stewardship principles and virtues. Provides the five principles, five virtues (Care, Curiosity, Humility, Diligence, Foresight), layer-specific guidance, a decision heuristic for identifying stewardship moments, and a reflection template for workflow boundaries.

Consult this skill when designing storage and documentation systems.

'Cross-plugin testing quality metrics and standards. Referenced by pensive:test-review

Consult this skill when implementing usage logging and audit trails.

'Consult this skill when cultivating and maintaining digital gardens.

'Process external resources into actionable knowledge with evaluation,

'Consult this skill when searching or navigating stored knowledge. Use

'Consult this skill when designing permanent memory palace structures.

Capture and retrieve PR review knowledge in project memory palaces.

'Consult this skill for session-scoped temporary knowledge structures.

'Outputs markdown digests and CSV exports for GitHub issues and PRs.

'Standardizes release approvals with GitHub-aware checklists. Use when

'Consult this skill for async Python patterns and concurrency. Use when

'Consult this skill for Python package creation and distribution. Use

'Consult this skill for Python performance profiling and optimization.

'Consult this skill for Python testing implementation and patterns. Use

'Use this skill for API surface evaluation and design review. Use when

'Use this skill for architecture assessment and compliance. Use when

'Use this skill for systematic bug hunting with evidence trails. Use

'Analyze and improve living code quality: duplication, algorithmic efficiency,

'Use this skill for Makefile audit and optimization. Use when auditing

'Use this skill for mathematical code verification. Use when reviewing

'Use this skill for Rust-specific code audits. Use when reviewing Rust

'Guidelines from the NASA Power of 10 rules for writing robust, verifiable

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

'Use this skill for test suite evaluation and quality assessment. Use

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