multi-tool-orchestration-skill
Coordinate multiple tools together for complex multi-step tasks
323 repo starsObserved in 1 repos
Agent Building
Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
night-market-completion-integrity-campaign
Bind loop 'done' to unfakeable gates. Use to harden egregore/herald loops or promote completion_integrity. Not for QA gates; use night-market-validation-and-qa.
323 repo starsObserved in 1 repos
Agent Building
progressive-discovery-skill
Discover and load tools progressively as needed (reduces token overhead)
323 repo starsObserved in 1 repos
Agent Building
progressive-loading
Implements hub-and-spoke lazy loading to minimize token usage in large skills. Use when building multi-module skills that need conditional on-demand loading.
323 repo starsObserved in 1 repos
Agent Building
risk-classification
Classifies agent tasks into 4 risk tiers (GREEN/YELLOW/RED/CRITICAL). Use when assessing action reversibility before committing to an approach.
323 repo starsObserved in 1 repos
Agent Building
session-lifecycle
Session state, stream state, pause and resume behavior, and device availability monitoring
323 repo starsObserved in 1 repos
Agent Building
skill-library-mission
Build a project skill library in .claude/skills/ via discovery, parallel authoring, and review. Use when packaging tribal knowledge. Do not use for one skill.
323 repo starsObserved in 1 repos
Agent Building
speckit-orchestrator
Orchestrates Spec Driven Development by coordinating spec, plan, and task skills. Use when running the full speckit workflow from spec to implementation.
323 repo starsObserved in 1 repos
Agent Building
test_skill_smoke
Smoke-test skill for validating skills loading and selection in runtime.
323 repo starsObserved in 1 repos
Agent Building