Leyline

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.

Git platform detection and cross-platform command mapping for GitHub, GitLab, and Bitbucket. git platform, forge, github, gitlab, bitbucket, cross-platform Use when: executing forge operations (issues, PRs/MRs, CI, API calls) in any skill or command Do not use directly: consumed by sanctum and other plugins as infrastructure.

Standardized pytest configuration for Claude Night Market plugin testing with reusable fixtures and CI integration. Use when configuring pytest, setting up conftest patterns, or establishing shared test fixtures.

Consult this skill when implementing usage logging and audit trails. Use when implementing audit trails, tracking costs, collecting usage analytics, managing session logging. Do not use when simple operations without logging needs.

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, and logging strategies. error handling, error recovery, graceful degradation, resilience.

Quota tracking, threshold monitoring, and graceful degradation for rate-limited API services. quota, rate limiting, usage limits, thresholds.

Consult this skill when implementing service registry patterns. Use when managing multiple external services, implementing health checks, centralizing service configuration, unified service execution. Do not use when single service integration without registry needs.

Consult this skill when designing storage and documentation systems. Use when organizing knowledge storage, managing configuration lifecycle, creating structured documentation, establishing naming conventions. Do not use when simple storage without lifecycle or structure needs.

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 for token optimization. progressive loading, lazy loading, hub-spoke, module selection.

Inline risk classification for agent tasks using a 4-tier model. Hybrid routing: GREEN/YELLOW use heuristic file-pattern matching, RED/CRITICAL escalate to war-room-checkpoint for full reversibility scoring.

Sanitization guidelines for external content consumed by skills and hooks. Use when loading external content (GitHub Issues, PRs, Discussions), processing WebFetch/WebSearch results, or any workflow consuming untrusted input.

Consult this skill when building evaluation or scoring systems. Use when implementing evaluation systems, creating quality gates, designing scoring rubrics, building decision frameworks. Do not use when simple pass/fail without scoring needs.

Authentication patterns for external services: API keys, OAuth, token management, verification. authentication, API keys, OAuth, token management, credentials.

Cross-plugin testing quality metrics and standards. Referenced by pensive:test-review and parseltongue:python-testing. testing standards, quality metrics, coverage thresholds, anti-patterns Use when: test quality evaluation, coverage thresholds, quality standards DO NOT use when: simple scripts without quality requirements.