output-styles
Understanding output styles in Claude Code (deprecated feature). Use when user asks about customizing Claude's behavior, output styles, or explanatory/learning modes.
498 repo starsObserved in 2 repos
Agent Building
Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Output Styles Guide
Adapt Claude Code for different use cases beyond software engineering by customizing system prompts for teaching, learning, analysis, or domain-specific workflows.
498 repo starsObserved in 2 repos
Agent Building
parallel-session-orchestration
Run multiple agent tasks in parallel cloud sandboxes with real-time progress monitoring, achieving 2x throughput vs sequential execution. Use for multi-repo tasks, independent bug fixes, concurrent feature development, or team workflows requiring parallel workstreams. Supports session management, result aggregation, and local teleport. Triggers on "parallel tasks", "multiple repos", "concurrent work", "parallel sessions", "multi-repo".
498 repo starsObserved in 2 repos
Agent Building
parallel-task
복잡한 작업을 depth 분석 후 병렬 서브에이전트로 분해하여 실행. 대규모 탐색, 다중 파일 분석, 리서치 작업 시 사용. "병렬로", "동시에", "여러 개를" 키워드 시 자동 활성화.
498 repo starsObserved in 2 repos
Agent Building
pattern-learner
Self-improving pattern database. Analyzes successful assets (≥95/100) → extracts effective prompt language → abstracts reusable patterns → updates library automatically.
498 repo starsObserved in 2 repos
Agent Building
peer-review-prompt-plan
Run prompt plan review using the codex CLI as an independent reviewer. Returns structured findings without applying fixes. Use when the user asks to "peer review my prompt plan", "get a second opinion on my prompts", "codex review my prompt plan", or "run codex on my prompts".
498 repo starsObserved in 2 repos
Agent Building
pensive:shared
DO NOT use directly: this skill is infrastructure for other pensive skills. This skill provides shared patterns consumed by other pensive skills. Use when other pensive skills need common patterns, creating new review skills, ensuring consistency across pensive plugin.
498 repo starsObserved in 2 repos
Agent Building
plugin-registry-scanner
This skill should be used when the user wants to discover available looplia skills, scan installed plugins, or list what capabilities are available. Use when someone says "what looplia skills are installed", "list available skills", "scan plugins", "/build", "what can looplia do", or "show me all looplia capabilities". First step in looplia workflow building: scans plugins/*/skills/*/SKILL.md to build a registry of available skills. Part of the skills-first architecture where one workflow step invokes one skill-executor to orchestrate multiple skills.
498 repo starsObserved in 2 repos
Agent Building
pmtl-skill-governance
PMTL_VN governance skill for designing, auditing, and evolving repo-local skills so they behave like reusable operational modules instead of one-off prompt notes.
498 repo starsObserved in 2 repos
Agent Building
pmtl-workflow-router
PMTL_VN workflow routing layer. Use when a task needs the right combination of repo-local PMTL skills, Superpowers workflow skills, and generic tool skills without making the user remember the skill names.
498 repo starsObserved in 2 repos
Agent Building